tools
stringlengths 151
9.9k
| conversations
listlengths 1
11
| answer
stringlengths 33
4.78k
| raw_system
stringlengths 406
471
| data_source
stringclasses 1
value | prompt
listlengths 2
12
| ability
stringclasses 1
value | reward_model
dict | extra_info
dict |
|---|---|---|---|---|---|---|---|---|
[{"name": "getplatformlist", "description": "Fetches the list of platforms with their IDs and names from the API endpoint as JSON.", "parameters": {"page": {"description": "Page number to retrieve the platform list from the API.", "type": "int", "default": "0"}}}, {"name": "user_aliases", "description": "Gets a list of user aliases and the timestamps when they were changed.", "parameters": {"is_id": {"description": "The Steam ID of the user for whom the aliases are retrieved.", "type": "str", "default": "sindex"}}}, {"name": "gamesdata", "description": "Fetches data for a specific game using its APP_ID from the Steam Games Data API.", "parameters": {"app_id": {"description": "The unique identifier for the game whose data is to be fetched.", "type": "int", "default": "1581770"}}}, {"name": "get_card_by_slug", "description": "Fetches card information by slug from the Hearthstone API.", "parameters": {"slug": {"description": "The slug identifier for the card.", "type": "str", "default": "a-light-in-the-darkness"}}}]
|
[
{
"from": "human",
"value": "Retrieve platform list for page six. Also, find user aliases for the Steam ID '76561197998991414'. In addition, get game data for app with ID '730'. Finally, gather card information for the Hearthstone card with slug 'EX1_557'."
}
] |
[{"name": "getplatformlist", "arguments": {"page": 6}}, {"name": "user_aliases", "arguments": {"is_id": "76561197998991414"}}, {"name": "gamesdata", "arguments": {"app_id": 730}}, {"name": "get_card_by_slug", "arguments": {"slug": "EX1_557"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"getplatformlist\", \"description\": \"Fetches the list of platforms with their IDs and names from the API endpoint as JSON.\", \"parameters\": {\"page\": {\"description\": \"Page number to retrieve the platform list from the API.\", \"type\": \"int\", \"default\": \"0\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"user_aliases\", \"description\": \"Gets a list of user aliases and the timestamps when they were changed.\", \"parameters\": {\"is_id\": {\"description\": \"The Steam ID of the user for whom the aliases are retrieved.\", \"type\": \"str\", \"default\": \"sindex\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"gamesdata\", \"description\": \"Fetches data for a specific game using its APP_ID from the Steam Games Data API.\", \"parameters\": {\"app_id\": {\"description\": \"The unique identifier for the game whose data is to be fetched.\", \"type\": \"int\", \"default\": \"1581770\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_card_by_slug\", \"description\": \"Fetches card information by slug from the Hearthstone API.\", \"parameters\": {\"slug\": {\"description\": \"The slug identifier for the card.\", \"type\": \"str\", \"default\": \"a-light-in-the-darkness\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Retrieve platform list for page six. Also, find user aliases for the Steam ID '76561197998991414'. In addition, get game data for app with ID '730'. Finally, gather card information for the Hearthstone card with slug 'EX1_557'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"getplatformlist\", \"arguments\": {\"page\": 6}}, {\"name\": \"user_aliases\", \"arguments\": {\"is_id\": \"76561197998991414\"}}, {\"name\": \"gamesdata\", \"arguments\": {\"app_id\": 730}}, {\"name\": \"get_card_by_slug\", \"arguments\": {\"slug\": \"EX1_557\"}}]",
"style": "rule"
}
|
{
"index": 0,
"split": "train"
}
|
[{"name": "measure_distance", "description": "Calculates the distance between two geographic locations based on their latitude and longitude coordinates. The unit of measurement for the distance can be specified.", "parameters": {"lon2": {"description": "Longitude of the second location.", "type": "int", "default": "31.23788289124186"}, "lat1": {"description": "Latitude of the first location.", "type": "int", "default": "31.1991806"}, "lon1": {"description": "Longitude of the first location.", "type": "int", "default": "29.8951716"}, "lat2": {"description": "Latitude of the second location.", "type": "int", "default": "30.02313795"}, "unit": {"description": "Unit of distance measurement. Valid options are 'km' (default), 'mi', 'ft', and 'yd'.", "type": "str, optional", "default": "km"}}}, {"name": "timezones", "description": "Fetch a list of the world's time zones with various filtering options.", "parameters": {"offset": {"description": "Filter on non-daylight savings offset in hours.", "type": "str, optional", "default": ""}, "name": {"description": "Filter as \"contains\" on timezone name in the chosen language.", "type": "str, optional", "default": ""}, "code": {"description": "Filter on 3-letter non-daylight savings timezone code (not unique).", "type": "str, optional", "default": ""}, "timezone": {"description": "Filter on timezone name in English.", "type": "str, optional", "default": ""}, "daylights_offset": {"description": "Filter on daylight savings offset in hours.", "type": "str, optional", "default": ""}, "lang": {"description": "Language selection ISO 639-1 two-letter code. Overrides the Accept-Language header. Default is 'de'.", "type": "str, optional", "default": "de"}, "daylights_code": {"description": "Filter on daylight savings letter code (not unique).", "type": "str, optional", "default": ""}, "fields": {"description": "Select fields to return in the result. Default is 'offset,daylights_offset,daylights,daylights_code,timezone'.", "type": "str, optional", "default": "offset,daylights_offset,daylights,daylights_code,timezone"}, "daylights": {"description": "Filter on daylight savings/non-daylight savings time zones (`true` or `false`).", "type": "str, optional", "default": ""}}}, {"name": "get_countries", "description": "Fetches a list of countries based on various search criteria.", "parameters": {"keyword": {"description": "Search countries by keyword. Defaults to 'ind'.", "type": "str, optional", "default": "ind"}, "subregion_id": {"description": "Filter countries by subregion ID.", "type": "str, optional", "default": ""}, "state_id": {"description": "Filter countries by state ID.", "type": "str, optional", "default": ""}, "timezone_id": {"description": "Filter countries by timezone ID.", "type": "str, optional", "default": ""}, "region_id": {"description": "Filter countries by subregion ID.", "type": "str, optional", "default": ""}, "perpage": {"description": "Number of results per page. Defaults to 50.", "type": "int, optional", "default": "50"}, "is_id": {"description": "Filter countries by country ID.", "type": "str, optional", "default": ""}, "page": {"description": "Number of results per page. Defaults to 50.", "type": "int, optional", "default": "1"}}}]
|
[
{
"from": "human",
"value": "Retrieve time zones that are in daylight savings time and have a code containing 'EST'."
}
] |
[{"name": "timezones", "arguments": {"daylights": "true", "code": "EST"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"measure_distance\", \"description\": \"Calculates the distance between two geographic locations based on their latitude and longitude coordinates. The unit of measurement for the distance can be specified.\", \"parameters\": {\"lon2\": {\"description\": \"Longitude of the second location.\", \"type\": \"int\", \"default\": \"31.23788289124186\"}, \"lat1\": {\"description\": \"Latitude of the first location.\", \"type\": \"int\", \"default\": \"31.1991806\"}, \"lon1\": {\"description\": \"Longitude of the first location.\", \"type\": \"int\", \"default\": \"29.8951716\"}, \"lat2\": {\"description\": \"Latitude of the second location.\", \"type\": \"int\", \"default\": \"30.02313795\"}, \"unit\": {\"description\": \"Unit of distance measurement. Valid options are 'km' (default), 'mi', 'ft', and 'yd'.\", \"type\": \"str, optional\", \"default\": \"km\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"timezones\", \"description\": \"Fetch a list of the world's time zones with various filtering options.\", \"parameters\": {\"offset\": {\"description\": \"Filter on non-daylight savings offset in hours.\", \"type\": \"str, optional\", \"default\": \"\"}, \"name\": {\"description\": \"Filter as \\\"contains\\\" on timezone name in the chosen language.\", \"type\": \"str, optional\", \"default\": \"\"}, \"code\": {\"description\": \"Filter on 3-letter non-daylight savings timezone code (not unique).\", \"type\": \"str, optional\", \"default\": \"\"}, \"timezone\": {\"description\": \"Filter on timezone name in English.\", \"type\": \"str, optional\", \"default\": \"\"}, \"daylights_offset\": {\"description\": \"Filter on daylight savings offset in hours.\", \"type\": \"str, optional\", \"default\": \"\"}, \"lang\": {\"description\": \"Language selection ISO 639-1 two-letter code. Overrides the Accept-Language header. Default is 'de'.\", \"type\": \"str, optional\", \"default\": \"de\"}, \"daylights_code\": {\"description\": \"Filter on daylight savings letter code (not unique).\", \"type\": \"str, optional\", \"default\": \"\"}, \"fields\": {\"description\": \"Select fields to return in the result. Default is 'offset,daylights_offset,daylights,daylights_code,timezone'.\", \"type\": \"str, optional\", \"default\": \"offset,daylights_offset,daylights,daylights_code,timezone\"}, \"daylights\": {\"description\": \"Filter on daylight savings/non-daylight savings time zones (`true` or `false`).\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_countries\", \"description\": \"Fetches a list of countries based on various search criteria.\", \"parameters\": {\"keyword\": {\"description\": \"Search countries by keyword. Defaults to 'ind'.\", \"type\": \"str, optional\", \"default\": \"ind\"}, \"subregion_id\": {\"description\": \"Filter countries by subregion ID.\", \"type\": \"str, optional\", \"default\": \"\"}, \"state_id\": {\"description\": \"Filter countries by state ID.\", \"type\": \"str, optional\", \"default\": \"\"}, \"timezone_id\": {\"description\": \"Filter countries by timezone ID.\", \"type\": \"str, optional\", \"default\": \"\"}, \"region_id\": {\"description\": \"Filter countries by subregion ID.\", \"type\": \"str, optional\", \"default\": \"\"}, \"perpage\": {\"description\": \"Number of results per page. Defaults to 50.\", \"type\": \"int, optional\", \"default\": \"50\"}, \"is_id\": {\"description\": \"Filter countries by country ID.\", \"type\": \"str, optional\", \"default\": \"\"}, \"page\": {\"description\": \"Number of results per page. Defaults to 50.\", \"type\": \"int, optional\", \"default\": \"1\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Retrieve time zones that are in daylight savings time and have a code containing 'EST'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"timezones\", \"arguments\": {\"daylights\": \"true\", \"code\": \"EST\"}}]",
"style": "rule"
}
|
{
"index": 1,
"split": "train"
}
|
[{"name": "get_train_data_mrt_id_id_get", "description": "Fetch train data using MRT ID from the RapidAPI service.", "parameters": {"is_id": {"description": "The MRT ID to fetch the train data for.", "type": "str", "default": ""}}}, {"name": "us_dc", "description": "Fetches current or historical gas price data for Washington D.C.", "parameters": {"date": {"description": "The date for which to fetch historical gas price data. Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "interior_colors", "description": "Fetches interior color details for a car based on various query parameters.", "parameters": {"model": {"description": "The model of the car.", "type": "str, optional", "default": ""}, "name": {"description": "The name of the color.", "type": "str, optional", "default": ""}, "trim": {"description": "The trim level of the car.", "type": "str, optional", "default": ""}, "page": {"description": "The page number for pagination.", "type": "int, optional", "default": ""}, "direction": {"description": "The sorting direction, either 'asc' or 'desc'. Default is 'asc'.", "type": "str, optional", "default": "asc"}, "limit": {"description": "The maximum number of results to return.", "type": "int, optional", "default": ""}, "make_model_trim_id": {"description": "The unique ID for make, model, and trim combination.", "type": "str, optional", "default": ""}, "year": {"description": "The year of the car.", "type": "str, optional", "default": ""}, "rgb": {"description": "The RGB value of the color.", "type": "str, optional", "default": ""}, "sort": {"description": "The field to sort by. Default is 'id'.", "type": "str, optional", "default": "id"}, "verbose": {"description": "If 'yes', includes detailed information about make, model, and trim. Default is 'yes'.", "type": "str, optional", "default": "yes"}, "json": {"description": "A URL encoded JSON array of conditions to filter results.", "type": "str, optional", "default": ""}, "make_id": {"description": "The ID of the car make.", "type": "str, optional", "default": ""}, "make": {"description": "The make of the car.", "type": "str, optional", "default": ""}, "make_model_id": {"description": "The ID for make and model combination.", "type": "str, optional", "default": ""}}}]
|
[
{
"from": "human",
"value": "Get current gas prices for Washington D.C."
}
] |
[{"name": "us_dc", "arguments": {}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_train_data_mrt_id_id_get\", \"description\": \"Fetch train data using MRT ID from the RapidAPI service.\", \"parameters\": {\"is_id\": {\"description\": \"The MRT ID to fetch the train data for.\", \"type\": \"str\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"us_dc\", \"description\": \"Fetches current or historical gas price data for Washington D.C.\", \"parameters\": {\"date\": {\"description\": \"The date for which to fetch historical gas price data. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"interior_colors\", \"description\": \"Fetches interior color details for a car based on various query parameters.\", \"parameters\": {\"model\": {\"description\": \"The model of the car.\", \"type\": \"str, optional\", \"default\": \"\"}, \"name\": {\"description\": \"The name of the color.\", \"type\": \"str, optional\", \"default\": \"\"}, \"trim\": {\"description\": \"The trim level of the car.\", \"type\": \"str, optional\", \"default\": \"\"}, \"page\": {\"description\": \"The page number for pagination.\", \"type\": \"int, optional\", \"default\": \"\"}, \"direction\": {\"description\": \"The sorting direction, either 'asc' or 'desc'. Default is 'asc'.\", \"type\": \"str, optional\", \"default\": \"asc\"}, \"limit\": {\"description\": \"The maximum number of results to return.\", \"type\": \"int, optional\", \"default\": \"\"}, \"make_model_trim_id\": {\"description\": \"The unique ID for make, model, and trim combination.\", \"type\": \"str, optional\", \"default\": \"\"}, \"year\": {\"description\": \"The year of the car.\", \"type\": \"str, optional\", \"default\": \"\"}, \"rgb\": {\"description\": \"The RGB value of the color.\", \"type\": \"str, optional\", \"default\": \"\"}, \"sort\": {\"description\": \"The field to sort by. Default is 'id'.\", \"type\": \"str, optional\", \"default\": \"id\"}, \"verbose\": {\"description\": \"If 'yes', includes detailed information about make, model, and trim. Default is 'yes'.\", \"type\": \"str, optional\", \"default\": \"yes\"}, \"json\": {\"description\": \"A URL encoded JSON array of conditions to filter results.\", \"type\": \"str, optional\", \"default\": \"\"}, \"make_id\": {\"description\": \"The ID of the car make.\", \"type\": \"str, optional\", \"default\": \"\"}, \"make\": {\"description\": \"The make of the car.\", \"type\": \"str, optional\", \"default\": \"\"}, \"make_model_id\": {\"description\": \"The ID for make and model combination.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Get current gas prices for Washington D.C.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"us_dc\", \"arguments\": {}}]",
"style": "rule"
}
|
{
"index": 2,
"split": "train"
}
|
[{"name": "monthly_mortgage_payment", "description": "Calculates the monthly mortgage payment based on the loan amount, annual interest rate, and loan term.", "parameters": {"loan_amount": {"description": "The total amount of the loan.", "type": "float"}, "annual_interest_rate": {"description": "The annual interest rate as a decimal (e.g., 0.05 for 5%).", "type": "float"}, "loan_term_years": {"description": "The loan term in years.", "type": "int"}}}]
|
[
{
"from": "human",
"value": "Compute the monthly mortgage payment for a $350,000 loan with an annual interest rate of 2.9% for 15 years."
}
] |
[{"name": "monthly_mortgage_payment", "arguments": {"loan_amount": 350000, "annual_interest_rate": 0.029, "loan_term_years": 15}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"monthly_mortgage_payment\", \"description\": \"Calculates the monthly mortgage payment based on the loan amount, annual interest rate, and loan term.\", \"parameters\": {\"loan_amount\": {\"description\": \"The total amount of the loan.\", \"type\": \"float\"}, \"annual_interest_rate\": {\"description\": \"The annual interest rate as a decimal (e.g., 0.05 for 5%).\", \"type\": \"float\"}, \"loan_term_years\": {\"description\": \"The loan term in years.\", \"type\": \"int\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Compute the monthly mortgage payment for a $350,000 loan with an annual interest rate of 2.9% for 15 years.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"monthly_mortgage_payment\", \"arguments\": {\"loan_amount\": 350000, \"annual_interest_rate\": 0.029, \"loan_term_years\": 15}}]",
"style": "rule"
}
|
{
"index": 3,
"split": "train"
}
|
[{"name": "can_attend_all_meetings", "description": "Determines if a person can attend all meetings given a list of meeting time intervals.", "parameters": {"intervals": {"description": "A list of meeting time intervals, where each interval is represented as [start_time, end_time].", "type": "List[List[int]]"}}}, {"name": "cell_density", "description": "Calculates the cell density based on the optical density (OD) and dilution factor.", "parameters": {"od": {"description": "The optical density of the sample.", "type": "float", "default": 1000000000.0}, "dilution": {"description": "The dilution factor applied to the sample.", "type": "int", "default": 1000000000.0}, "factor": {"description": "The calibration factor for converting OD to cell density. Defaults to 1e9.", "type": "float, optional"}}}]
|
[
{
"from": "human",
"value": "Determine if a person can attend all of their meetings scheduled from 9:00 AM to 10:00 AM, 10:30 AM to 11:30 AM, and 12:00 PM to 1:00 PM."
}
] |
[{"name": "can_attend_all_meetings", "arguments": {"intervals": [[900, 1000], [1030, 1130], [1200, 1300]]}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"can_attend_all_meetings\", \"description\": \"Determines if a person can attend all meetings given a list of meeting time intervals.\", \"parameters\": {\"intervals\": {\"description\": \"A list of meeting time intervals, where each interval is represented as [start_time, end_time].\", \"type\": \"List[List[int]]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"cell_density\", \"description\": \"Calculates the cell density based on the optical density (OD) and dilution factor.\", \"parameters\": {\"od\": {\"description\": \"The optical density of the sample.\", \"type\": \"float\", \"default\": 1000000000.0}, \"dilution\": {\"description\": \"The dilution factor applied to the sample.\", \"type\": \"int\", \"default\": 1000000000.0}, \"factor\": {\"description\": \"The calibration factor for converting OD to cell density. Defaults to 1e9.\", \"type\": \"float, optional\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Determine if a person can attend all of their meetings scheduled from 9:00 AM to 10:00 AM, 10:30 AM to 11:30 AM, and 12:00 PM to 1:00 PM.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"can_attend_all_meetings\", \"arguments\": {\"intervals\": [[900, 1000], [1030, 1130], [1200, 1300]]}}]",
"style": "rule"
}
|
{
"index": 4,
"split": "train"
}
|
[{"name": "latest", "description": "Fetches the latest news from Google News for a specified language region.", "parameters": {"lr": {"description": "Language region to get news for, e.g., 'en-US'.", "type": "str", "default": "en-US"}}}, {"name": "top_headlines", "description": "Fetches top headline news articles based on specified parameters.", "parameters": {"language": {"description": "Language code to filter news articles. Default is 'en'. Options include:", "type": "str", "default": "en"}, "category": {"description": "Category of news articles to filter by. Default is 'sports'. Options include:", "type": "str", "default": "sports"}, "country": {"description": "Country code to filter news articles. Default is 'us'. Options include:", "type": "str", "default": "us"}, "sortby": {"description": "Criterion to sort news articles by. Default is 'published_date'.", "type": "str", "default": ""}, "pagesize": {"description": "Number of news articles to return per page. Default is 10.", "type": "int", "default": "10"}}}, {"name": "news_source", "description": "Fetch the latest news stories for a given news source in chronological order.", "parameters": {"source_id": {"description": "The identifier of the news source for which to retrieve the latest news stories.", "type": "str", "default": "bbc"}}}]
|
[
{
"from": "human",
"value": "Please get me the top health news in German from Germany, and also the latest news from the BBC source."
}
] |
[{"name": "top_headlines", "arguments": {"language": "de", "country": "de", "category": "health"}}, {"name": "news_source", "arguments": {"source_id": "bbc"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"latest\", \"description\": \"Fetches the latest news from Google News for a specified language region.\", \"parameters\": {\"lr\": {\"description\": \"Language region to get news for, e.g., 'en-US'.\", \"type\": \"str\", \"default\": \"en-US\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"top_headlines\", \"description\": \"Fetches top headline news articles based on specified parameters.\", \"parameters\": {\"language\": {\"description\": \"Language code to filter news articles. Default is 'en'. Options include:\", \"type\": \"str\", \"default\": \"en\"}, \"category\": {\"description\": \"Category of news articles to filter by. Default is 'sports'. Options include:\", \"type\": \"str\", \"default\": \"sports\"}, \"country\": {\"description\": \"Country code to filter news articles. Default is 'us'. Options include:\", \"type\": \"str\", \"default\": \"us\"}, \"sortby\": {\"description\": \"Criterion to sort news articles by. Default is 'published_date'.\", \"type\": \"str\", \"default\": \"\"}, \"pagesize\": {\"description\": \"Number of news articles to return per page. Default is 10.\", \"type\": \"int\", \"default\": \"10\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"news_source\", \"description\": \"Fetch the latest news stories for a given news source in chronological order.\", \"parameters\": {\"source_id\": {\"description\": \"The identifier of the news source for which to retrieve the latest news stories.\", \"type\": \"str\", \"default\": \"bbc\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Please get me the top health news in German from Germany, and also the latest news from the BBC source.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"top_headlines\", \"arguments\": {\"language\": \"de\", \"country\": \"de\", \"category\": \"health\"}}, {\"name\": \"news_source\", \"arguments\": {\"source_id\": \"bbc\"}}]",
"style": "rule"
}
|
{
"index": 5,
"split": "train"
}
|
[{"name": "get_movies_by_cast_name", "description": "Fetches movies associated with a given cast member's name from the IMDB API.", "parameters": {"cast_name": {"description": "Name of the cast member to search for. Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "get_movies_by_director", "description": "Gets a list of movies by a specified director using the IMDb API.", "parameters": {"movie_director": {"description": "The name of the director. If not provided, an empty query will be sent.", "type": "str, optional", "default": ""}}}, {"name": "season_episodes", "description": "Fetch episodes for a given season from the Netflix RapidAPI.", "parameters": {"ids": {"description": "Season IDs (separated by commas) for which episodes are to be fetched.", "type": "str", "default": "80077209,80117715"}, "lang": {"description": "Language code for the episodes. Defaults to 'en'.", "type": "str, optional", "default": "en"}, "limit": {"description": "The maximum number of episodes to return. Defaults to 25.", "type": "int, optional", "default": "25"}, "offset": {"description": "The offset for pagination. Defaults to 0.", "type": "int, optional", "default": "0"}}}, {"name": "actors_random", "description": "Fetches a random list of actors from the Movies Database RapidAPI.", "parameters": {"limit": {"description": "The number of random actors to retrieve. Defaults to None, and the API will use its default value if not specified.", "type": "int, optional", "default": ""}}}]
|
[
{
"from": "human",
"value": "I'm trying to find all the movies directed by Steven Spielberg and the ones starring Tom Hanks. Can you also get me the episodes of the first season of Breaking Bad? And while you're at it, fetch me a list of 5 random actors."
}
] |
[{"name": "get_movies_by_director", "arguments": {"movie_director": "Steven Spielberg"}}, {"name": "get_movies_by_cast_name", "arguments": {"cast_name": "Tom Hanks"}}, {"name": "season_episodes", "arguments": {"ids": "1"}}, {"name": "actors_random", "arguments": {"limit": 5}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_movies_by_cast_name\", \"description\": \"Fetches movies associated with a given cast member's name from the IMDB API.\", \"parameters\": {\"cast_name\": {\"description\": \"Name of the cast member to search for. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_movies_by_director\", \"description\": \"Gets a list of movies by a specified director using the IMDb API.\", \"parameters\": {\"movie_director\": {\"description\": \"The name of the director. If not provided, an empty query will be sent.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"season_episodes\", \"description\": \"Fetch episodes for a given season from the Netflix RapidAPI.\", \"parameters\": {\"ids\": {\"description\": \"Season IDs (separated by commas) for which episodes are to be fetched.\", \"type\": \"str\", \"default\": \"80077209,80117715\"}, \"lang\": {\"description\": \"Language code for the episodes. Defaults to 'en'.\", \"type\": \"str, optional\", \"default\": \"en\"}, \"limit\": {\"description\": \"The maximum number of episodes to return. Defaults to 25.\", \"type\": \"int, optional\", \"default\": \"25\"}, \"offset\": {\"description\": \"The offset for pagination. Defaults to 0.\", \"type\": \"int, optional\", \"default\": \"0\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"actors_random\", \"description\": \"Fetches a random list of actors from the Movies Database RapidAPI.\", \"parameters\": {\"limit\": {\"description\": \"The number of random actors to retrieve. Defaults to None, and the API will use its default value if not specified.\", \"type\": \"int, optional\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I'm trying to find all the movies directed by Steven Spielberg and the ones starring Tom Hanks. Can you also get me the episodes of the first season of Breaking Bad? And while you're at it, fetch me a list of 5 random actors.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_movies_by_director\", \"arguments\": {\"movie_director\": \"Steven Spielberg\"}}, {\"name\": \"get_movies_by_cast_name\", \"arguments\": {\"cast_name\": \"Tom Hanks\"}}, {\"name\": \"season_episodes\", \"arguments\": {\"ids\": \"1\"}}, {\"name\": \"actors_random\", \"arguments\": {\"limit\": 5}}]",
"style": "rule"
}
|
{
"index": 6,
"split": "train"
}
|
[{"name": "get_3_summary", "description": "Fetches a summary of stock performance and related metrics from the Stocky API.", "parameters": {"keyword": {"description": "The stock keyword to search for. Default is 'GOOG'.", "type": "str", "default": "GOOG"}}}, {"name": "get_liquidity_value", "description": "Retrieves the liquidity value of a specified cryptocurrency in US Dollars.", "parameters": {"symbol": {"description": "The ticker symbol of the cryptocurrency.", "type": "str", "default": "BTC"}}}, {"name": "market_trends", "description": "Fetches market trends data from the Joj Finance API.", "parameters": {"t": {"description": "Tab name, specifying the category of market trends. One of the following:", "type": "str", "default": "indexes"}, "gl": {"description": "Geolocation for the data, default is 'US'.", "type": "str, optional", "default": "US"}, "s": {"description": "Subtab name for 'indexes' tab to specify the region. One of the following:", "type": "str, optional", "default": ""}, "hl": {"description": "Language code, default is 'en'.", "type": "str, optional", "default": "en"}}}]
|
[
{
"from": "human",
"value": "I need the liquidity value of Stellar (XLM) and the market trends for indexes in the Americas. Also, could you give me the summary of the stock performance for Facebook (FB)?"
}
] |
[{"name": "get_liquidity_value", "arguments": {"symbol": "XLM"}}, {"name": "market_trends", "arguments": {"t": "indexes", "s": "americas"}}, {"name": "get_3_summary", "arguments": {"keyword": "FB"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_3_summary\", \"description\": \"Fetches a summary of stock performance and related metrics from the Stocky API.\", \"parameters\": {\"keyword\": {\"description\": \"The stock keyword to search for. Default is 'GOOG'.\", \"type\": \"str\", \"default\": \"GOOG\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_liquidity_value\", \"description\": \"Retrieves the liquidity value of a specified cryptocurrency in US Dollars.\", \"parameters\": {\"symbol\": {\"description\": \"The ticker symbol of the cryptocurrency.\", \"type\": \"str\", \"default\": \"BTC\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"market_trends\", \"description\": \"Fetches market trends data from the Joj Finance API.\", \"parameters\": {\"t\": {\"description\": \"Tab name, specifying the category of market trends. One of the following:\", \"type\": \"str\", \"default\": \"indexes\"}, \"gl\": {\"description\": \"Geolocation for the data, default is 'US'.\", \"type\": \"str, optional\", \"default\": \"US\"}, \"s\": {\"description\": \"Subtab name for 'indexes' tab to specify the region. One of the following:\", \"type\": \"str, optional\", \"default\": \"\"}, \"hl\": {\"description\": \"Language code, default is 'en'.\", \"type\": \"str, optional\", \"default\": \"en\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I need the liquidity value of Stellar (XLM) and the market trends for indexes in the Americas. Also, could you give me the summary of the stock performance for Facebook (FB)?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_liquidity_value\", \"arguments\": {\"symbol\": \"XLM\"}}, {\"name\": \"market_trends\", \"arguments\": {\"t\": \"indexes\", \"s\": \"americas\"}}, {\"name\": \"get_3_summary\", \"arguments\": {\"keyword\": \"FB\"}}]",
"style": "rule"
}
|
{
"index": 7,
"split": "train"
}
|
[{"name": "aerospace_material_optimization", "description": "Optimize material usage for aerospace 3D printing projects based on specific requirements.", "parameters": {"type": "dict", "properties": {"project_id": {"type": "string", "description": "Unique identifier for the 3D printing project."}, "material_requirements": {"type": "array", "description": "List of material specifications needed for the project.", "items": {"type": "dict", "properties": {"material_type": {"type": "string", "description": "Type of material required (e.g., titanium, aluminum)."}, "quantity": {"type": "float", "description": "Required quantity in kilograms."}, "properties": {"type": "dict", "properties": {"strength": {"type": "int", "description": "Required strength measured in MPa."}, "temperature_resistance": {"type": "int", "description": "Maximum temperature resistance required (in degrees Celsius)."}}, "required": ["strength", "temperature_resistance"]}}, "required": ["material_type", "quantity"]}}, "optimization_time": {"type": "string", "enum": ["Immediate", "End of Day", "Within 24 Hours"], "description": "Preferred time for optimization results.", "default": "Immediate"}}, "required": ["project_id", "material_requirements"]}, "required": null}]
|
[
{
"from": "human",
"value": "I need an optimization for three aerospace 3D printing projects. The details are as follows:\n1. Project ID: A123, Materials: Titanium (50 kg, strength: 900 MPa, temperature resistance: 500°C), Aluminum (30 kg, strength: 400 MPa, temperature resistance: 300°C)\n2. Project ID: B456, Materials: Carbon Fiber (20 kg, strength: 1500 MPa, temperature resistance: 200°C)\n3. Project ID: C789, Materials: Titanium (40 kg, strength: 850 MPa, temperature resistance: 450°C), Steel (25 kg, strength: 1200 MPa, temperature resistance: 700°C)\nAll optimizations should be immediate."
}
] |
[{"name": "aerospace_material_optimization", "arguments": {"project_id": "A123", "material_requirements": [{"material_type": "Titanium", "quantity": 50.0, "properties": {"strength": 900, "temperature_resistance": 500}}, {"material_type": "Aluminum", "quantity": 30.0, "properties": {"strength": 400, "temperature_resistance": 300}}], "optimization_time": "Immediate"}}, {"name": "aerospace_material_optimization", "arguments": {"project_id": "B456", "material_requirements": [{"material_type": "Carbon Fiber", "quantity": 20.0, "properties": {"strength": 1500, "temperature_resistance": 200}}], "optimization_time": "Immediate"}}, {"name": "aerospace_material_optimization", "arguments": {"project_id": "C789", "material_requirements": [{"material_type": "Titanium", "quantity": 40.0, "properties": {"strength": 850, "temperature_resistance": 450}}, {"material_type": "Steel", "quantity": 25.0, "properties": {"strength": 1200, "temperature_resistance": 700}}], "optimization_time": "Immediate"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out.
The current time is 2026-12-22 09:05:35.Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out.\nThe current time is 2026-12-22 09:05:35.Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"aerospace_material_optimization\", \"description\": \"Optimize material usage for aerospace 3D printing projects based on specific requirements.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"project_id\": {\"type\": \"string\", \"description\": \"Unique identifier for the 3D printing project.\"}, \"material_requirements\": {\"type\": \"array\", \"description\": \"List of material specifications needed for the project.\", \"items\": {\"type\": \"dict\", \"properties\": {\"material_type\": {\"type\": \"string\", \"description\": \"Type of material required (e.g., titanium, aluminum).\"}, \"quantity\": {\"type\": \"float\", \"description\": \"Required quantity in kilograms.\"}, \"properties\": {\"type\": \"dict\", \"properties\": {\"strength\": {\"type\": \"int\", \"description\": \"Required strength measured in MPa.\"}, \"temperature_resistance\": {\"type\": \"int\", \"description\": \"Maximum temperature resistance required (in degrees Celsius).\"}}, \"required\": [\"strength\", \"temperature_resistance\"]}}, \"required\": [\"material_type\", \"quantity\"]}}, \"optimization_time\": {\"type\": \"string\", \"enum\": [\"Immediate\", \"End of Day\", \"Within 24 Hours\"], \"description\": \"Preferred time for optimization results.\", \"default\": \"Immediate\"}}, \"required\": [\"project_id\", \"material_requirements\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I need an optimization for three aerospace 3D printing projects. The details are as follows:\n1. Project ID: A123, Materials: Titanium (50 kg, strength: 900 MPa, temperature resistance: 500°C), Aluminum (30 kg, strength: 400 MPa, temperature resistance: 300°C)\n2. Project ID: B456, Materials: Carbon Fiber (20 kg, strength: 1500 MPa, temperature resistance: 200°C)\n3. Project ID: C789, Materials: Titanium (40 kg, strength: 850 MPa, temperature resistance: 450°C), Steel (25 kg, strength: 1200 MPa, temperature resistance: 700°C)\nAll optimizations should be immediate.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"aerospace_material_optimization\", \"arguments\": {\"project_id\": \"A123\", \"material_requirements\": [{\"material_type\": \"Titanium\", \"quantity\": 50.0, \"properties\": {\"strength\": 900, \"temperature_resistance\": 500}}, {\"material_type\": \"Aluminum\", \"quantity\": 30.0, \"properties\": {\"strength\": 400, \"temperature_resistance\": 300}}], \"optimization_time\": \"Immediate\"}}, {\"name\": \"aerospace_material_optimization\", \"arguments\": {\"project_id\": \"B456\", \"material_requirements\": [{\"material_type\": \"Carbon Fiber\", \"quantity\": 20.0, \"properties\": {\"strength\": 1500, \"temperature_resistance\": 200}}], \"optimization_time\": \"Immediate\"}}, {\"name\": \"aerospace_material_optimization\", \"arguments\": {\"project_id\": \"C789\", \"material_requirements\": [{\"material_type\": \"Titanium\", \"quantity\": 40.0, \"properties\": {\"strength\": 850, \"temperature_resistance\": 450}}, {\"material_type\": \"Steel\", \"quantity\": 25.0, \"properties\": {\"strength\": 1200, \"temperature_resistance\": 700}}], \"optimization_time\": \"Immediate\"}}]",
"style": "rule"
}
|
{
"index": 8,
"split": "train"
}
|
[{"name": "find_minimum_rotated_sorted_array", "description": "Finds the minimum element in a rotated sorted array.", "parameters": {"nums": {"description": "The rotated sorted array.", "type": "List[int]"}}}, {"name": "average", "description": "Calculates the arithmetic mean of a list of numbers.", "parameters": {"numbers": {"description": "The list of numbers.", "type": "List[float]"}}}, {"name": "greatest_common_divisor", "description": "Computes the greatest common divisor (GCD) of two non-negative integers.", "parameters": {"a": {"description": "The first non-negative integer.", "type": "int"}, "b": {"description": "The second non-negative integer.", "type": "int"}}}]
|
[
{
"from": "human",
"value": "Determine the greatest common divisor of 105 and 24."
}
] |
[{"name": "greatest_common_divisor", "arguments": {"a": 105, "b": 24}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"find_minimum_rotated_sorted_array\", \"description\": \"Finds the minimum element in a rotated sorted array.\", \"parameters\": {\"nums\": {\"description\": \"The rotated sorted array.\", \"type\": \"List[int]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"average\", \"description\": \"Calculates the arithmetic mean of a list of numbers.\", \"parameters\": {\"numbers\": {\"description\": \"The list of numbers.\", \"type\": \"List[float]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"greatest_common_divisor\", \"description\": \"Computes the greatest common divisor (GCD) of two non-negative integers.\", \"parameters\": {\"a\": {\"description\": \"The first non-negative integer.\", \"type\": \"int\"}, \"b\": {\"description\": \"The second non-negative integer.\", \"type\": \"int\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Determine the greatest common divisor of 105 and 24.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"greatest_common_divisor\", \"arguments\": {\"a\": 105, \"b\": 24}}]",
"style": "rule"
}
|
{
"index": 9,
"split": "train"
}
|
[{"name": "List User Followings", "description": "Retrieve a list of users that a given user is following on TikTok", "parameters": {"type": "dict", "properties": {"user_id": {"description": "The ID of the user to retrieve followings for", "type": "string"}, "sec_uid": {"description": "The secure user ID of the user to retrieve followings for", "type": "string"}, "proxy": {"description": "Optional proxy URL for the request", "type": "string", "default": ""}, "offset": {"description": "Optional offset for pagination", "type": "float", "default": 0}, "count": {"description": "Optional count for pagination", "type": "float", "default": 10}}, "required": ["user_id", "sec_uid"]}, "required": null}, {"name": "Twitter Auto Complete API", "description": "Returns autocomplete results for Twitter search queries.", "parameters": {"type": "dict", "properties": {"query": {"description": "The search query to autocomplete", "type": "string"}}, "required": ["query"]}, "required": null}, {"name": "Get User Tweets and Replies by REST ID", "description": "Retrieves a user's tweets and replies by providing a REST ID.", "parameters": {"type": "dict", "properties": {"user_id": {"description": "The ID of the user whose tweets and replies are to be retrieved.", "type": "string"}, "limit": {"description": "The maximum number of tweets and replies to return.", "type": "string", "default": "40"}, "cursor": {"description": "The cursor value to use for pagination.", "type": "string", "default": ""}}, "required": ["user_id"]}, "required": null}, {"name": "Search Followers by PK and Query", "description": "Search for users who are followers of a specific Instagram account, given the account's public key (pk) and a search query.", "parameters": {"type": "dict", "properties": {"pk": {"description": "Public key of the Instagram account", "type": "float"}, "query": {"description": "Search query to filter followers", "type": "string"}}, "required": ["pk", "query"]}, "required": null}, {"name": "Performer Model Information", "description": "Retrieves detailed information about a performer or model on the onlyfans platform.", "parameters": {"type": "dict", "properties": {"username": {"description": "The username or ID of the performer or model.", "type": "string"}}, "required": ["username"]}, "required": null}, {"name": "Twitter Space Stream URL API", "description": "This API receives the m3u8 URL for a Twitter Space stream by providing the mediaId.", "parameters": {"type": "dict", "properties": {"mediaId": {"description": "The mediaId obtained from the Twitter Space details and media_key value.", "type": "string"}}, "required": ["mediaId"]}, "required": null}]
|
[
{
"from": "human",
"value": "Role definition:\n Inquirer: A user who raises an inquiry.\n Response assistant: Communicates with the inquirer and provides answers and solutions.\n\n Historical dialog data is as follows:\nInquirer: I want to listen to the upcoming Twitter Space on AI advancements, but I'm struggling with finding the stream URL. Can you help me with that?\nResponse assistant: Can you provide the mediaId for the Twitter Space you mentioned?\nInquirer: Yes, the mediaId is \"12345\"\n\n Please continue your answer given the historical dialog. Your role is the Response assistant."
}
] |
[{"name": "Twitter Space Stream URL API", "arguments": {"mediaId": "12345"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out.
The current time is 2023-10-19 17:34:44.Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out.\nThe current time is 2023-10-19 17:34:44.Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"List User Followings\", \"description\": \"Retrieve a list of users that a given user is following on TikTok\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"user_id\": {\"description\": \"The ID of the user to retrieve followings for\", \"type\": \"string\"}, \"sec_uid\": {\"description\": \"The secure user ID of the user to retrieve followings for\", \"type\": \"string\"}, \"proxy\": {\"description\": \"Optional proxy URL for the request\", \"type\": \"string\", \"default\": \"\"}, \"offset\": {\"description\": \"Optional offset for pagination\", \"type\": \"float\", \"default\": 0}, \"count\": {\"description\": \"Optional count for pagination\", \"type\": \"float\", \"default\": 10}}, \"required\": [\"user_id\", \"sec_uid\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Twitter Auto Complete API\", \"description\": \"Returns autocomplete results for Twitter search queries.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"query\": {\"description\": \"The search query to autocomplete\", \"type\": \"string\"}}, \"required\": [\"query\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Get User Tweets and Replies by REST ID\", \"description\": \"Retrieves a user's tweets and replies by providing a REST ID.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"user_id\": {\"description\": \"The ID of the user whose tweets and replies are to be retrieved.\", \"type\": \"string\"}, \"limit\": {\"description\": \"The maximum number of tweets and replies to return.\", \"type\": \"string\", \"default\": \"40\"}, \"cursor\": {\"description\": \"The cursor value to use for pagination.\", \"type\": \"string\", \"default\": \"\"}}, \"required\": [\"user_id\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Search Followers by PK and Query\", \"description\": \"Search for users who are followers of a specific Instagram account, given the account's public key (pk) and a search query.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"pk\": {\"description\": \"Public key of the Instagram account\", \"type\": \"float\"}, \"query\": {\"description\": \"Search query to filter followers\", \"type\": \"string\"}}, \"required\": [\"pk\", \"query\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Performer Model Information\", \"description\": \"Retrieves detailed information about a performer or model on the onlyfans platform.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"username\": {\"description\": \"The username or ID of the performer or model.\", \"type\": \"string\"}}, \"required\": [\"username\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Twitter Space Stream URL API\", \"description\": \"This API receives the m3u8 URL for a Twitter Space stream by providing the mediaId.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"mediaId\": {\"description\": \"The mediaId obtained from the Twitter Space details and media_key value.\", \"type\": \"string\"}}, \"required\": [\"mediaId\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Role definition:\n Inquirer: A user who raises an inquiry.\n Response assistant: Communicates with the inquirer and provides answers and solutions.\n\n Historical dialog data is as follows:\nInquirer: I want to listen to the upcoming Twitter Space on AI advancements, but I'm struggling with finding the stream URL. Can you help me with that?\nResponse assistant: Can you provide the mediaId for the Twitter Space you mentioned?\nInquirer: Yes, the mediaId is \"12345\"\n\n Please continue your answer given the historical dialog. Your role is the Response assistant.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"Twitter Space Stream URL API\", \"arguments\": {\"mediaId\": \"12345\"}}]",
"style": "rule"
}
|
{
"index": 10,
"split": "train"
}
|
[{"name": "greatest_common_divisor", "description": "Computes the greatest common divisor (GCD) of two non-negative integers.", "parameters": {"a": {"description": "The first non-negative integer.", "type": "int"}, "b": {"description": "The second non-negative integer.", "type": "int"}}}, {"name": "linear_regression_prediction", "description": "Predicts the y-value for a given x-value using linear regression.", "parameters": {"x_values": {"description": "The x-coordinates of the data points.", "type": "List[float]"}, "y_values": {"description": "The y-coordinates of the data points.", "type": "List[float]"}, "target_x": {"description": "The x-value for which to predict the y-value.", "type": "float"}}}, {"name": "count_bits", "description": "Counts the number of set bits (1's) in the binary representation of a number.", "parameters": {"num": {"description": "The input number.", "type": "int"}}}, {"name": "merge_sorted_lists", "description": "Merges two sorted lists into a single sorted list.", "parameters": {"list1": {"description": "The first sorted list.", "type": "List[int]"}, "list2": {"description": "The second sorted list.", "type": "List[int]"}}}, {"name": "investment_profit", "description": "Calculates the profit from an investment based on the initial amount, annual return rate, and time.", "parameters": {"amount": {"description": "The initial investment amount.", "type": "float"}, "rate": {"description": "The annual return rate expressed as a decimal.", "type": "float"}, "years": {"description": "The number of years the investment is held.", "type": "int"}}}]
|
[
{
"from": "human",
"value": "Merge two sorted lists: [1, 3, 5] and [2, 4, 6] into a single sorted list."
}
] |
[{"name": "merge_sorted_lists", "arguments": {"list1": [1, 3, 5], "list2": [2, 4, 6]}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"greatest_common_divisor\", \"description\": \"Computes the greatest common divisor (GCD) of two non-negative integers.\", \"parameters\": {\"a\": {\"description\": \"The first non-negative integer.\", \"type\": \"int\"}, \"b\": {\"description\": \"The second non-negative integer.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"linear_regression_prediction\", \"description\": \"Predicts the y-value for a given x-value using linear regression.\", \"parameters\": {\"x_values\": {\"description\": \"The x-coordinates of the data points.\", \"type\": \"List[float]\"}, \"y_values\": {\"description\": \"The y-coordinates of the data points.\", \"type\": \"List[float]\"}, \"target_x\": {\"description\": \"The x-value for which to predict the y-value.\", \"type\": \"float\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"count_bits\", \"description\": \"Counts the number of set bits (1's) in the binary representation of a number.\", \"parameters\": {\"num\": {\"description\": \"The input number.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"merge_sorted_lists\", \"description\": \"Merges two sorted lists into a single sorted list.\", \"parameters\": {\"list1\": {\"description\": \"The first sorted list.\", \"type\": \"List[int]\"}, \"list2\": {\"description\": \"The second sorted list.\", \"type\": \"List[int]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"investment_profit\", \"description\": \"Calculates the profit from an investment based on the initial amount, annual return rate, and time.\", \"parameters\": {\"amount\": {\"description\": \"The initial investment amount.\", \"type\": \"float\"}, \"rate\": {\"description\": \"The annual return rate expressed as a decimal.\", \"type\": \"float\"}, \"years\": {\"description\": \"The number of years the investment is held.\", \"type\": \"int\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Merge two sorted lists: [1, 3, 5] and [2, 4, 6] into a single sorted list.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"merge_sorted_lists\", \"arguments\": {\"list1\": [1, 3, 5], \"list2\": [2, 4, 6]}}]",
"style": "rule"
}
|
{
"index": 11,
"split": "train"
}
|
[{"name": "generate_meme", "description": "Generate a meme with a specified image and text", "parameters": {"type": "dict", "properties": {"image": {"type": "string", "description": "The URL or path of the image to be used"}, "text": {"type": "string", "description": "The text to be added to the meme"}}, "required": ["image", "text"]}, "required": null}]
|
[
{
"from": "human",
"value": "Can you create two memes for me? Use this image (https://example.com/image1.jpg) for the first meme with the text \"When you realize it's Friday!\", and this image (https://example.com/image2.jpg) for the second meme with the text \"Monday mornings be like...\"."
}
] |
[{"name": "generate_meme", "arguments": {"image": "https://example.com/image1.jpg", "text": "When you realize it's Friday!"}}, {"name": "generate_meme", "arguments": {"image": "https://example.com/image2.jpg", "text": "Monday mornings be like..."}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out.
The current time is 2020-12-24 19:32:06.Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out.\nThe current time is 2020-12-24 19:32:06.Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"generate_meme\", \"description\": \"Generate a meme with a specified image and text\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"image\": {\"type\": \"string\", \"description\": \"The URL or path of the image to be used\"}, \"text\": {\"type\": \"string\", \"description\": \"The text to be added to the meme\"}}, \"required\": [\"image\", \"text\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Can you create two memes for me? Use this image (https://example.com/image1.jpg) for the first meme with the text \"When you realize it's Friday!\", and this image (https://example.com/image2.jpg) for the second meme with the text \"Monday mornings be like...\".",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"generate_meme\", \"arguments\": {\"image\": \"https://example.com/image1.jpg\", \"text\": \"When you realize it's Friday!\"}}, {\"name\": \"generate_meme\", \"arguments\": {\"image\": \"https://example.com/image2.jpg\", \"text\": \"Monday mornings be like...\"}}]",
"style": "rule"
}
|
{
"index": 12,
"split": "train"
}
|
[{"name": "is_prime", "description": "Checks if a number is prime.", "parameters": {"num": {"description": "The number to be checked.", "type": "int"}}}, {"name": "average", "description": "Calculates the arithmetic mean of a list of numbers.", "parameters": {"numbers": {"description": "The list of numbers.", "type": "List[float]"}}}, {"name": "density", "description": "Calculates the density of an object given its mass and volume.", "parameters": {"mass": {"description": "The mass of the object.", "type": "float"}, "volume": {"description": "The volume of the object.", "type": "float"}}}, {"name": "find_longest_palindromic_substring", "description": "Finds the longest palindromic substring in a string.", "parameters": {"s": {"description": "The input string.", "type": "str"}}}]
|
[
{
"from": "human",
"value": "Calculate the average of the numbers [1.5, 2.5, 3.5, 4.5]."
}
] |
[{"name": "average", "arguments": {"numbers": [1.5, 2.5, 3.5, 4.5]}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"is_prime\", \"description\": \"Checks if a number is prime.\", \"parameters\": {\"num\": {\"description\": \"The number to be checked.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"average\", \"description\": \"Calculates the arithmetic mean of a list of numbers.\", \"parameters\": {\"numbers\": {\"description\": \"The list of numbers.\", \"type\": \"List[float]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"density\", \"description\": \"Calculates the density of an object given its mass and volume.\", \"parameters\": {\"mass\": {\"description\": \"The mass of the object.\", \"type\": \"float\"}, \"volume\": {\"description\": \"The volume of the object.\", \"type\": \"float\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"find_longest_palindromic_substring\", \"description\": \"Finds the longest palindromic substring in a string.\", \"parameters\": {\"s\": {\"description\": \"The input string.\", \"type\": \"str\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Calculate the average of the numbers [1.5, 2.5, 3.5, 4.5].",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"average\", \"arguments\": {\"numbers\": [1.5, 2.5, 3.5, 4.5]}}]",
"style": "rule"
}
|
{
"index": 13,
"split": "train"
}
|
[{"name": "stock_get_statistics", "description": "Retrieve statistical information for a given stock.", "parameters": {"is_id": {"description": "The ID of the stock. Use the market/auto-complete API to get the correct values.", "type": "str", "default": "aapl:us"}, "template": {"description": "Specifies the type of statistical template to use. Options include 'COMMODITY', 'CURRENCY', 'INDEX', 'INDEXFUTURE', 'RATE', and 'STOCK'. Defaults to 'STOCK'.", "type": "str, optional", "default": "STOCK"}}}, {"name": "account_transaction_history", "description": "Retrieves an array of all transactions associated with a specific address on the Optimism blockchain.", "parameters": {"address": {"description": "The blockchain address to query for transaction history.", "type": "str", "default": "0x0000000000000000000000000000000000000123"}, "network": {"description": "The network to query, either 'mainnet' or 'testnet'. Defaults to None.", "type": "str, optional", "default": ""}}}]
|
[
{
"from": "human",
"value": "I'd like to get the statistical information for the US 10-Year Treasury Bond and the transaction history of an address on the Optimism blockchain's mainnet."
}
] |
[{"name": "stock_get_statistics", "arguments": {"is_id": "DGS10", "template": "RATE"}}, {"name": "account_transaction_history", "arguments": {"address": "0x742d35Cc6634C0532925a3b844Bc454e4438f44e", "network": "mainnet"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"stock_get_statistics\", \"description\": \"Retrieve statistical information for a given stock.\", \"parameters\": {\"is_id\": {\"description\": \"The ID of the stock. Use the market/auto-complete API to get the correct values.\", \"type\": \"str\", \"default\": \"aapl:us\"}, \"template\": {\"description\": \"Specifies the type of statistical template to use. Options include 'COMMODITY', 'CURRENCY', 'INDEX', 'INDEXFUTURE', 'RATE', and 'STOCK'. Defaults to 'STOCK'.\", \"type\": \"str, optional\", \"default\": \"STOCK\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"account_transaction_history\", \"description\": \"Retrieves an array of all transactions associated with a specific address on the Optimism blockchain.\", \"parameters\": {\"address\": {\"description\": \"The blockchain address to query for transaction history.\", \"type\": \"str\", \"default\": \"0x0000000000000000000000000000000000000123\"}, \"network\": {\"description\": \"The network to query, either 'mainnet' or 'testnet'. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I'd like to get the statistical information for the US 10-Year Treasury Bond and the transaction history of an address on the Optimism blockchain's mainnet.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"stock_get_statistics\", \"arguments\": {\"is_id\": \"DGS10\", \"template\": \"RATE\"}}, {\"name\": \"account_transaction_history\", \"arguments\": {\"address\": \"0x742d35Cc6634C0532925a3b844Bc454e4438f44e\", \"network\": \"mainnet\"}}]",
"style": "rule"
}
|
{
"index": 14,
"split": "train"
}
|
[{"name": "is_valid_parentheses", "description": "Checks if a string contains valid parentheses.", "parameters": {"s": {"description": "The input string.", "type": "str"}}}, {"name": "merge_dictionaries", "description": "Merges two dictionaries into a single dictionary.", "parameters": {"dict1": {"description": "The first dictionary.", "type": "Dict"}, "dict2": {"description": "The second dictionary.", "type": "Dict"}}}]
|
[
{
"from": "human",
"value": "Is the string '()()()' a valid parentheses sequence? Can you merge {'m': 13, 'n': 14} and {'n': 15, 'o': 16}?"
}
] |
[{"name": "is_valid_parentheses", "arguments": {"s": "()()()"}}, {"name": "merge_dictionaries", "arguments": {"dict1": {"m": 13, "n": 14}, "dict2": {"n": 15, "o": 16}}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"is_valid_parentheses\", \"description\": \"Checks if a string contains valid parentheses.\", \"parameters\": {\"s\": {\"description\": \"The input string.\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"merge_dictionaries\", \"description\": \"Merges two dictionaries into a single dictionary.\", \"parameters\": {\"dict1\": {\"description\": \"The first dictionary.\", \"type\": \"Dict\"}, \"dict2\": {\"description\": \"The second dictionary.\", \"type\": \"Dict\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Is the string '()()()' a valid parentheses sequence? Can you merge {'m': 13, 'n': 14} and {'n': 15, 'o': 16}?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"is_valid_parentheses\", \"arguments\": {\"s\": \"()()()\"}}, {\"name\": \"merge_dictionaries\", \"arguments\": {\"dict1\": {\"m\": 13, \"n\": 14}, \"dict2\": {\"n\": 15, \"o\": 16}}}]",
"style": "rule"
}
|
{
"index": 15,
"split": "train"
}
|
[{"name": "v1_ownersearch", "description": "Performs a search on the owner name or postcode and returns details about the trademarks found for that owner. Duplicate owner results can be returned by this endpoint, especially when an owner had an address change.", "parameters": {"search_keyword": {"description": "The search keyword (e.g., 'ferr' will return results for 'ferrari'). Defaults to 'netflix'. Use literal 'null' if you don't want to use this parameter.", "type": "str", "default": "netflix"}, "postcode": {"description": "The postcode to filter the search results (e.g., '95066'). Use literal 'null' if you don't want to use this parameter. Note that attorneys might omit postcodes from filings, so those results cannot be returned as they don't have postcode attached as metadata.", "type": "str", "default": ""}}}, {"name": "search", "description": "This function performs a vehicle license plate lookup for a given plate number in the Netherlands using the RapidAPI service.", "parameters": {"plate": {"description": "The vehicle license plate number to look up. Defaults to '3XKF30'.", "type": "str", "default": "3XKF30"}, "function": {"description": "The function to use for the lookup. Defaults to 'getktypefornumplatenetherlands'.", "type": "str", "default": "getktypefornumplatenetherlands"}}}, {"name": "auto_complete", "description": "Fetches auto-complete suggestions for a given search term using the Zoopla API.", "parameters": {"search_term": {"description": "The term or phrase for which to fetch auto-complete suggestions.", "type": "str", "default": "greenwich"}, "search_type": {"description": "The type of search to perform. Acceptable values are 'listings' or 'properties'. Defaults to 'listings'.", "type": "str, optional", "default": "listings"}}}, {"name": "get_data_entity_uid", "description": "Fetches an entity record from the OFAC service using a unique identifier (UID).", "parameters": {"uid": {"description": "The unique identifier of the entity to retrieve.", "type": "int", "default": "7178"}}}]
|
[
{
"from": "human",
"value": "Get auto-complete suggestions for 'London properties' and retrieve data for entity UID 12345."
}
] |
[{"name": "auto_complete", "arguments": {"search_term": "London properties", "search_type": "properties"}}, {"name": "get_data_entity_uid", "arguments": {"uid": 12345}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"v1_ownersearch\", \"description\": \"Performs a search on the owner name or postcode and returns details about the trademarks found for that owner. Duplicate owner results can be returned by this endpoint, especially when an owner had an address change.\", \"parameters\": {\"search_keyword\": {\"description\": \"The search keyword (e.g., 'ferr' will return results for 'ferrari'). Defaults to 'netflix'. Use literal 'null' if you don't want to use this parameter.\", \"type\": \"str\", \"default\": \"netflix\"}, \"postcode\": {\"description\": \"The postcode to filter the search results (e.g., '95066'). Use literal 'null' if you don't want to use this parameter. Note that attorneys might omit postcodes from filings, so those results cannot be returned as they don't have postcode attached as metadata.\", \"type\": \"str\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"search\", \"description\": \"This function performs a vehicle license plate lookup for a given plate number in the Netherlands using the RapidAPI service.\", \"parameters\": {\"plate\": {\"description\": \"The vehicle license plate number to look up. Defaults to '3XKF30'.\", \"type\": \"str\", \"default\": \"3XKF30\"}, \"function\": {\"description\": \"The function to use for the lookup. Defaults to 'getktypefornumplatenetherlands'.\", \"type\": \"str\", \"default\": \"getktypefornumplatenetherlands\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"auto_complete\", \"description\": \"Fetches auto-complete suggestions for a given search term using the Zoopla API.\", \"parameters\": {\"search_term\": {\"description\": \"The term or phrase for which to fetch auto-complete suggestions.\", \"type\": \"str\", \"default\": \"greenwich\"}, \"search_type\": {\"description\": \"The type of search to perform. Acceptable values are 'listings' or 'properties'. Defaults to 'listings'.\", \"type\": \"str, optional\", \"default\": \"listings\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_data_entity_uid\", \"description\": \"Fetches an entity record from the OFAC service using a unique identifier (UID).\", \"parameters\": {\"uid\": {\"description\": \"The unique identifier of the entity to retrieve.\", \"type\": \"int\", \"default\": \"7178\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Get auto-complete suggestions for 'London properties' and retrieve data for entity UID 12345.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"auto_complete\", \"arguments\": {\"search_term\": \"London properties\", \"search_type\": \"properties\"}}, {\"name\": \"get_data_entity_uid\", \"arguments\": {\"uid\": 12345}}]",
"style": "rule"
}
|
{
"index": 16,
"split": "train"
}
|
[{"name": "get_6_month_historical_daily_prices", "description": "Retrieves 6 months of historical daily stock prices for the given ticker, including adjusted Open, High, Low, and Close prices, as well as Daily Volume, Dividend, and Split information.", "parameters": {"ticker": {"description": "The stock ticker symbol for which to retrieve the historical prices.", "type": "str", "default": "AAPL"}}}]
|
[
{
"from": "human",
"value": "Provide the daily price history for Pfizer (PFE) from 6 months ago."
}
] |
[{"name": "get_6_month_historical_daily_prices", "arguments": {"ticker": "PFE"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_6_month_historical_daily_prices\", \"description\": \"Retrieves 6 months of historical daily stock prices for the given ticker, including adjusted Open, High, Low, and Close prices, as well as Daily Volume, Dividend, and Split information.\", \"parameters\": {\"ticker\": {\"description\": \"The stock ticker symbol for which to retrieve the historical prices.\", \"type\": \"str\", \"default\": \"AAPL\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Provide the daily price history for Pfizer (PFE) from 6 months ago.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_6_month_historical_daily_prices\", \"arguments\": {\"ticker\": \"PFE\"}}]",
"style": "rule"
}
|
{
"index": 17,
"split": "train"
}
|
[{"name": "bacterial_growth", "description": "Calculates the bacterial population after a given time based on the initial population and growth rate.", "parameters": {"initial_population": {"description": "The initial bacterial population.", "type": "int", "default": 20}, "growth_rate": {"description": "The growth rate per unit time.", "type": "float", "default": 20}, "time": {"description": "The time elapsed.", "type": "float"}, "doubling_time": {"description": "The doubling time of the bacteria in minutes. Defaults to 20.", "type": "float, optional"}}}]
|
[
{
"from": "human",
"value": "What will be the bacterial population after 60 minutes if the initial population is 100, the growth rate is 0.02 per minute, and the doubling time is 20 minutes? Also, what will be the population after 45 minutes with the same initial population and growth rate but a doubling time of 30 minutes?"
}
] |
[{"name": "bacterial_growth", "arguments": {"initial_population": 100, "growth_rate": 0.02, "time": 60, "doubling_time": 20}}, {"name": "bacterial_growth", "arguments": {"initial_population": 100, "growth_rate": 0.02, "time": 45, "doubling_time": 30}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"bacterial_growth\", \"description\": \"Calculates the bacterial population after a given time based on the initial population and growth rate.\", \"parameters\": {\"initial_population\": {\"description\": \"The initial bacterial population.\", \"type\": \"int\", \"default\": 20}, \"growth_rate\": {\"description\": \"The growth rate per unit time.\", \"type\": \"float\", \"default\": 20}, \"time\": {\"description\": \"The time elapsed.\", \"type\": \"float\"}, \"doubling_time\": {\"description\": \"The doubling time of the bacteria in minutes. Defaults to 20.\", \"type\": \"float, optional\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What will be the bacterial population after 60 minutes if the initial population is 100, the growth rate is 0.02 per minute, and the doubling time is 20 minutes? Also, what will be the population after 45 minutes with the same initial population and growth rate but a doubling time of 30 minutes?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"bacterial_growth\", \"arguments\": {\"initial_population\": 100, \"growth_rate\": 0.02, \"time\": 60, \"doubling_time\": 20}}, {\"name\": \"bacterial_growth\", \"arguments\": {\"initial_population\": 100, \"growth_rate\": 0.02, \"time\": 45, \"doubling_time\": 30}}]",
"style": "rule"
}
|
{
"index": 18,
"split": "train"
}
|
[{"name": "get_company_jobs_count", "description": "Retrieves the number of job openings a specified company has posted on LinkedIn.", "parameters": {"company_id": {"description": "The unique identifier of the company whose job openings count is to be retrieved.", "type": "str", "default": "162479"}}}]
|
[
{
"from": "human",
"value": "Hey, can you check how many jobs are currently open at the company I work for? Its ID is 33333"
}
] |
[{"name": "get_company_jobs_count", "arguments": {"company_id": "33333"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_company_jobs_count\", \"description\": \"Retrieves the number of job openings a specified company has posted on LinkedIn.\", \"parameters\": {\"company_id\": {\"description\": \"The unique identifier of the company whose job openings count is to be retrieved.\", \"type\": \"str\", \"default\": \"162479\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Hey, can you check how many jobs are currently open at the company I work for? Its ID is 33333",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_company_jobs_count\", \"arguments\": {\"company_id\": \"33333\"}}]",
"style": "rule"
}
|
{
"index": 19,
"split": "train"
}
|
[{"name": "mean_confidence_interval", "description": "Calculates the confidence interval for a sample mean.", "parameters": {"std_dev": {"description": "The standard deviation of the sample.", "type": "float", "default": 0.95}, "sample_size": {"description": "The size of the sample.", "type": "int", "default": 0.95}, "mean": {"description": "The mean of the sample.", "type": "float"}, "confidence": {"description": "The desired confidence level. Default is 0.95.", "type": "float, optional"}}}, {"name": "calculate_standard_deviation", "description": "Calculates the standard deviation of a list of numbers.", "parameters": {"numbers": {"description": "The list of numbers.", "type": "List[Union[int, float]]"}}}, {"name": "greatest_common_divisor", "description": "Computes the greatest common divisor (GCD) of two non-negative integers.", "parameters": {"a": {"description": "The first non-negative integer.", "type": "int"}, "b": {"description": "The second non-negative integer.", "type": "int"}}}, {"name": "euclidean_distance", "description": "Computes the Euclidean distance between two points in a 2D plane.", "parameters": {"point_a": {"description": "The coordinates of the first point (x, y).", "type": "Tuple[float, float]"}, "point_b": {"description": "The coordinates of the second point (x, y).", "type": "Tuple[float, float]"}}}]
|
[
{
"from": "human",
"value": "What is the confidence interval for a sample with a standard deviation of 5.2, a sample size of 100, and a mean of 23.7?"
}
] |
[{"name": "mean_confidence_interval", "arguments": {"std_dev": 5.2, "sample_size": 100, "mean": 23.7}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"mean_confidence_interval\", \"description\": \"Calculates the confidence interval for a sample mean.\", \"parameters\": {\"std_dev\": {\"description\": \"The standard deviation of the sample.\", \"type\": \"float\", \"default\": 0.95}, \"sample_size\": {\"description\": \"The size of the sample.\", \"type\": \"int\", \"default\": 0.95}, \"mean\": {\"description\": \"The mean of the sample.\", \"type\": \"float\"}, \"confidence\": {\"description\": \"The desired confidence level. Default is 0.95.\", \"type\": \"float, optional\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_standard_deviation\", \"description\": \"Calculates the standard deviation of a list of numbers.\", \"parameters\": {\"numbers\": {\"description\": \"The list of numbers.\", \"type\": \"List[Union[int, float]]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"greatest_common_divisor\", \"description\": \"Computes the greatest common divisor (GCD) of two non-negative integers.\", \"parameters\": {\"a\": {\"description\": \"The first non-negative integer.\", \"type\": \"int\"}, \"b\": {\"description\": \"The second non-negative integer.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"euclidean_distance\", \"description\": \"Computes the Euclidean distance between two points in a 2D plane.\", \"parameters\": {\"point_a\": {\"description\": \"The coordinates of the first point (x, y).\", \"type\": \"Tuple[float, float]\"}, \"point_b\": {\"description\": \"The coordinates of the second point (x, y).\", \"type\": \"Tuple[float, float]\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the confidence interval for a sample with a standard deviation of 5.2, a sample size of 100, and a mean of 23.7?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"mean_confidence_interval\", \"arguments\": {\"std_dev\": 5.2, \"sample_size\": 100, \"mean\": 23.7}}]",
"style": "rule"
}
|
{
"index": 20,
"split": "train"
}
|
[{"name": "fetch_movies", "description": "Fetch a list of movies from 2000 to 2019 based on the selected genre and year using the specified RapidAPI key.", "parameters": {"year": {"description": "The year for which to fetch movies. Should be between 2000 and 2019.", "type": "str", "default": "2018"}, "genre": {"description": "The genre of the movies to fetch.", "type": "str", "default": "Comedy"}}}, {"name": "ott_providers", "description": "Fetch information on OTT platforms supported in a given region.", "parameters": {"region": {"description": "The region to get OTT platform information for. Use 'US' for USA and 'IN' for India.", "type": "str", "default": "IN"}}}, {"name": "season_episodes", "description": "Fetch episodes for a given season from the Netflix RapidAPI.", "parameters": {"ids": {"description": "Season IDs (separated by commas) for which episodes are to be fetched.", "type": "str", "default": "80077209,80117715"}, "lang": {"description": "Language code for the episodes. Defaults to 'en'.", "type": "str, optional", "default": "en"}, "limit": {"description": "The maximum number of episodes to return. Defaults to 25.", "type": "int, optional", "default": "25"}, "offset": {"description": "The offset for pagination. Defaults to 0.", "type": "int, optional", "default": "0"}}}, {"name": "actors_random", "description": "Fetches a random list of actors from the Movies Database RapidAPI.", "parameters": {"limit": {"description": "The number of random actors to retrieve. Defaults to None, and the API will use its default value if not specified.", "type": "int, optional", "default": ""}}}]
|
[
{
"from": "human",
"value": "Fetch the episodes of the seasons with IDs 1234 and 5678 in German, limiting the results to 10 and starting from the 5th result, using the season_episodes function."
}
] |
[{"name": "season_episodes", "arguments": {"ids": "1234,5678", "lang": "de", "limit": 10, "offset": 5}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"fetch_movies\", \"description\": \"Fetch a list of movies from 2000 to 2019 based on the selected genre and year using the specified RapidAPI key.\", \"parameters\": {\"year\": {\"description\": \"The year for which to fetch movies. Should be between 2000 and 2019.\", \"type\": \"str\", \"default\": \"2018\"}, \"genre\": {\"description\": \"The genre of the movies to fetch.\", \"type\": \"str\", \"default\": \"Comedy\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"ott_providers\", \"description\": \"Fetch information on OTT platforms supported in a given region.\", \"parameters\": {\"region\": {\"description\": \"The region to get OTT platform information for. Use 'US' for USA and 'IN' for India.\", \"type\": \"str\", \"default\": \"IN\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"season_episodes\", \"description\": \"Fetch episodes for a given season from the Netflix RapidAPI.\", \"parameters\": {\"ids\": {\"description\": \"Season IDs (separated by commas) for which episodes are to be fetched.\", \"type\": \"str\", \"default\": \"80077209,80117715\"}, \"lang\": {\"description\": \"Language code for the episodes. Defaults to 'en'.\", \"type\": \"str, optional\", \"default\": \"en\"}, \"limit\": {\"description\": \"The maximum number of episodes to return. Defaults to 25.\", \"type\": \"int, optional\", \"default\": \"25\"}, \"offset\": {\"description\": \"The offset for pagination. Defaults to 0.\", \"type\": \"int, optional\", \"default\": \"0\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"actors_random\", \"description\": \"Fetches a random list of actors from the Movies Database RapidAPI.\", \"parameters\": {\"limit\": {\"description\": \"The number of random actors to retrieve. Defaults to None, and the API will use its default value if not specified.\", \"type\": \"int, optional\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch the episodes of the seasons with IDs 1234 and 5678 in German, limiting the results to 10 and starting from the 5th result, using the season_episodes function.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"season_episodes\", \"arguments\": {\"ids\": \"1234,5678\", \"lang\": \"de\", \"limit\": 10, \"offset\": 5}}]",
"style": "rule"
}
|
{
"index": 21,
"split": "train"
}
|
[{"name": "word_frequency", "description": "Calculates the frequency of each word in a text.", "parameters": {"text": {"description": "The input text.", "type": "str"}}}, {"name": "count_occurrences", "description": "Counts the occurrences of each element in a list and returns a dictionary with the counts.", "parameters": {"lst": {"description": "The input list.", "type": "List"}}}, {"name": "is_armstrong_number", "description": "Checks if a number is an Armstrong number.", "parameters": {"num": {"description": "The number to check.", "type": "int"}}}, {"name": "binary_search", "description": "Performs binary search on a sorted list to find the index of a target value.", "parameters": {"arr": {"description": "The sorted list of integers.", "type": "List[int]"}, "target": {"description": "The target value to search for.", "type": "int"}}}]
|
[
{
"from": "human",
"value": "Calculate word frequencies in the paragraph: 'The quick brown fox jumps over the lazy dog.'"
}
] |
[{"name": "word_frequency", "arguments": {"text": "The quick brown fox jumps over the lazy dog."}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"word_frequency\", \"description\": \"Calculates the frequency of each word in a text.\", \"parameters\": {\"text\": {\"description\": \"The input text.\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"count_occurrences\", \"description\": \"Counts the occurrences of each element in a list and returns a dictionary with the counts.\", \"parameters\": {\"lst\": {\"description\": \"The input list.\", \"type\": \"List\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"is_armstrong_number\", \"description\": \"Checks if a number is an Armstrong number.\", \"parameters\": {\"num\": {\"description\": \"The number to check.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"binary_search\", \"description\": \"Performs binary search on a sorted list to find the index of a target value.\", \"parameters\": {\"arr\": {\"description\": \"The sorted list of integers.\", \"type\": \"List[int]\"}, \"target\": {\"description\": \"The target value to search for.\", \"type\": \"int\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Calculate word frequencies in the paragraph: 'The quick brown fox jumps over the lazy dog.'",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"word_frequency\", \"arguments\": {\"text\": \"The quick brown fox jumps over the lazy dog.\"}}]",
"style": "rule"
}
|
{
"index": 22,
"split": "train"
}
|
[{"name": "hijos", "description": "Retrieves the list of children (hijos) from the Colegio Santa Ana API.", "parameters": {"authorization": {"description": "The authorization token required for accessing the API.", "type": "str", "default": "1234567890"}}}, {"name": "v1_babynames", "description": "Fetches a list of baby names from the API Ninjas Baby Names API endpoint.", "parameters": {"popular_only": {"description": "Whether to only return popular (top 10%) of names. Must be either 'true' or 'false'. Defaults to 'true' if not set.", "type": "str, optional", "default": ""}, "gender": {"description": "The gender for the baby names. Must be one of the following: 'boy', 'girl', or 'neutral'.", "type": "str, optional", "default": ""}}}, {"name": "topic", "description": "Fetches topics from the Quotes Diffusion API with optional pagination and search functionality.", "parameters": {"page": {"description": "Page number for pagination. Defaults to None.", "type": "int, optional", "default": ""}, "search": {"description": "Custom search term to filter topics. Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "mensajes", "description": "This function fetches messages from the Colegio Santa Ana API.", "parameters": {"authorization": {"description": "The authorization token required for the API request.", "type": "str", "default": "1234567890"}}}, {"name": "sign", "description": "Fetch horoscope information for a given astrological sign using the Horoscope Astrology API.", "parameters": {"s": {"description": "The astrological sign to fetch information for. Valid options include 'aries', 'taurus', 'gemini', 'cancer', 'leo', 'virgo', 'libra', 'scorpio', 'sagittarius', 'capricorn', 'aquarius', and 'pisces'.", "type": "str", "default": "libra"}}}, {"name": "tsv2", "description": "Fetches values from a specified data subset within a dataset using the ODAM RapidAPI.", "parameters": {"subset": {"description": "Identifier for the data subset.", "type": "str", "default": "samples"}, "dataset": {"description": "Identifier for the dataset.", "type": "str", "default": "frim1"}, "limit": {"description": "Limits the number of lines in the output table. Defaults to 10. A value of 0 means no limit.", "type": "int, optional", "default": 10}, "debug": {"description": "Debug status. When set to a non-zero value, debug mode is enabled. Defaults to 0.", "type": "int, optional", "default": 0}, "format": {"description": "Output format. Defaults to 'tsv'.", "type": "str, optional", "default": "tsv"}}}, {"name": "file_digest", "description": "Calculates the digest/checksum for a given file by making a request to the pragmavantapi via RapidAPI.", "parameters": {"source": {"description": "The URL of the file for which the digest/checksum is to be calculated.", "type": "str", "default": "http://google.com"}, "cache_key": {"description": "An optional cache key for quicker lookup. Defaults to None.", "type": "str, optional", "default": ""}}}]
|
[
{
"from": "human",
"value": "Fetch topics from the Quotes Diffusion API related to 'inspiration' on page 2."
}
] |
[{"name": "topic", "arguments": {"search": "inspiration", "page": 2}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"hijos\", \"description\": \"Retrieves the list of children (hijos) from the Colegio Santa Ana API.\", \"parameters\": {\"authorization\": {\"description\": \"The authorization token required for accessing the API.\", \"type\": \"str\", \"default\": \"1234567890\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"v1_babynames\", \"description\": \"Fetches a list of baby names from the API Ninjas Baby Names API endpoint.\", \"parameters\": {\"popular_only\": {\"description\": \"Whether to only return popular (top 10%) of names. Must be either 'true' or 'false'. Defaults to 'true' if not set.\", \"type\": \"str, optional\", \"default\": \"\"}, \"gender\": {\"description\": \"The gender for the baby names. Must be one of the following: 'boy', 'girl', or 'neutral'.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"topic\", \"description\": \"Fetches topics from the Quotes Diffusion API with optional pagination and search functionality.\", \"parameters\": {\"page\": {\"description\": \"Page number for pagination. Defaults to None.\", \"type\": \"int, optional\", \"default\": \"\"}, \"search\": {\"description\": \"Custom search term to filter topics. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"mensajes\", \"description\": \"This function fetches messages from the Colegio Santa Ana API.\", \"parameters\": {\"authorization\": {\"description\": \"The authorization token required for the API request.\", \"type\": \"str\", \"default\": \"1234567890\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"sign\", \"description\": \"Fetch horoscope information for a given astrological sign using the Horoscope Astrology API.\", \"parameters\": {\"s\": {\"description\": \"The astrological sign to fetch information for. Valid options include 'aries', 'taurus', 'gemini', 'cancer', 'leo', 'virgo', 'libra', 'scorpio', 'sagittarius', 'capricorn', 'aquarius', and 'pisces'.\", \"type\": \"str\", \"default\": \"libra\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"tsv2\", \"description\": \"Fetches values from a specified data subset within a dataset using the ODAM RapidAPI.\", \"parameters\": {\"subset\": {\"description\": \"Identifier for the data subset.\", \"type\": \"str\", \"default\": \"samples\"}, \"dataset\": {\"description\": \"Identifier for the dataset.\", \"type\": \"str\", \"default\": \"frim1\"}, \"limit\": {\"description\": \"Limits the number of lines in the output table. Defaults to 10. A value of 0 means no limit.\", \"type\": \"int, optional\", \"default\": 10}, \"debug\": {\"description\": \"Debug status. When set to a non-zero value, debug mode is enabled. Defaults to 0.\", \"type\": \"int, optional\", \"default\": 0}, \"format\": {\"description\": \"Output format. Defaults to 'tsv'.\", \"type\": \"str, optional\", \"default\": \"tsv\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"file_digest\", \"description\": \"Calculates the digest/checksum for a given file by making a request to the pragmavantapi via RapidAPI.\", \"parameters\": {\"source\": {\"description\": \"The URL of the file for which the digest/checksum is to be calculated.\", \"type\": \"str\", \"default\": \"http://google.com\"}, \"cache_key\": {\"description\": \"An optional cache key for quicker lookup. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch topics from the Quotes Diffusion API related to 'inspiration' on page 2.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"topic\", \"arguments\": {\"search\": \"inspiration\", \"page\": 2}}]",
"style": "rule"
}
|
{
"index": 23,
"split": "train"
}
|
[{"name": "get_products_in_category", "description": "Fetches products in a specified category from a remote catalog using the RapidAPI service.", "parameters": {"category": {"description": "The category from which to fetch products.", "type": "str", "default": ""}, "limit": {"description": "The number of products to retrieve.", "type": "int", "default": ""}, "skip": {"description": "The number of products to skip before starting to retrieve.", "type": "int", "default": ""}}}, {"name": "specificcolorset", "description": "Fetch a set of colors based on the input color name using the ColorMe API.", "parameters": {"colorname": {"description": "The name of the base color to generate a set of colors from (e.g., \"yellow\", \"red\").", "type": "str", "default": "yellow"}}}]
|
[
{
"from": "human",
"value": "Fetch 7 products from the books category, skipping the first 5 products, and generate a color set based on the color 'purple'."
}
] |
[{"name": "get_products_in_category", "arguments": {"category": "books", "limit": 7, "skip": 5}}, {"name": "specificcolorset", "arguments": {"colorname": "purple"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_products_in_category\", \"description\": \"Fetches products in a specified category from a remote catalog using the RapidAPI service.\", \"parameters\": {\"category\": {\"description\": \"The category from which to fetch products.\", \"type\": \"str\", \"default\": \"\"}, \"limit\": {\"description\": \"The number of products to retrieve.\", \"type\": \"int\", \"default\": \"\"}, \"skip\": {\"description\": \"The number of products to skip before starting to retrieve.\", \"type\": \"int\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"specificcolorset\", \"description\": \"Fetch a set of colors based on the input color name using the ColorMe API.\", \"parameters\": {\"colorname\": {\"description\": \"The name of the base color to generate a set of colors from (e.g., \\\"yellow\\\", \\\"red\\\").\", \"type\": \"str\", \"default\": \"yellow\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch 7 products from the books category, skipping the first 5 products, and generate a color set based on the color 'purple'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_products_in_category\", \"arguments\": {\"category\": \"books\", \"limit\": 7, \"skip\": 5}}, {\"name\": \"specificcolorset\", \"arguments\": {\"colorname\": \"purple\"}}]",
"style": "rule"
}
|
{
"index": 24,
"split": "train"
}
|
[{"name": "title_cast_crew", "description": "Fetches and returns the cast and crew information of a given title from the Watchmode API.", "parameters": {"is_id": {"description": "The ID of the title. This can be the Watchmode ID, IMDB ID, or a TMDB type and ID combination.", "type": "str", "default": "3173903"}}}]
|
[
{
"from": "human",
"value": "Fetch the cast and crew details for a movie with a custom API key 'abcdefghijklmnopqrstuvwxyz123456'."
}
] |
[{"name": "title_cast_crew", "arguments": {"is_id": "tt0111161"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"title_cast_crew\", \"description\": \"Fetches and returns the cast and crew information of a given title from the Watchmode API.\", \"parameters\": {\"is_id\": {\"description\": \"The ID of the title. This can be the Watchmode ID, IMDB ID, or a TMDB type and ID combination.\", \"type\": \"str\", \"default\": \"3173903\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch the cast and crew details for a movie with a custom API key 'abcdefghijklmnopqrstuvwxyz123456'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"title_cast_crew\", \"arguments\": {\"is_id\": \"tt0111161\"}}]",
"style": "rule"
}
|
{
"index": 25,
"split": "train"
}
|
[{"name": "software_assets", "description": "Fetch details of SaaS/Software tools based on specified feature tags or software name.", "parameters": {"q": {"description": "Query string representing the list of feature tags or the name of the software for which details are to be fetched.", "type": "str", "default": "email-marketing, landing-pages"}}}, {"name": "get_campaign_lead_from_id", "description": "Retrieve lead information from a campaign using its ID via the Fomo API.", "parameters": {"is_id": {"description": "The ID of the campaign to retrieve the lead information from.", "type": "str", "default": "Lead"}}}, {"name": "loginuser", "description": "Logs in a user by sending their credentials to a specified endpoint.", "parameters": {"username": {"description": "The user's username for login.", "type": "str", "default": ""}, "password": {"description": "The user's password for login in clear text.", "type": "str", "default": ""}}}, {"name": "loginuser", "description": "Logs in a user to the specified toolbench API by making a GET request to the login endpoint with the provided username and password.", "parameters": {"username": {"description": "The username for login.", "type": "str", "default": ""}, "password": {"description": "The password for login in clear text.", "type": "str", "default": ""}}}]
|
[
{
"from": "human",
"value": "Identify SaaS tools offering 'ticketing' and 'event management' features and gather lead information for campaigns with IDs 'ccccc' and 'ddddd' from Fomo API. Moreover, log in users 'johnthompson' and 'janethompson' to my_api_12345 and freeplanhardlimitexternal APIs using their password 'secr3tpa$$w'."
}
] |
[{"name": "software_assets", "arguments": {"q": "ticketing, event management"}}, {"name": "get_campaign_lead_from_id", "arguments": {"is_id": "ccccc"}}, {"name": "get_campaign_lead_from_id", "arguments": {"is_id": "ddddd"}}, {"name": "loginuser", "arguments": {"username": "johnthompson", "password": "secr3tpa$$w"}}, {"name": "loginuser", "arguments": {"username": "janethompson", "password": "secr3tpa$$w"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"software_assets\", \"description\": \"Fetch details of SaaS/Software tools based on specified feature tags or software name.\", \"parameters\": {\"q\": {\"description\": \"Query string representing the list of feature tags or the name of the software for which details are to be fetched.\", \"type\": \"str\", \"default\": \"email-marketing, landing-pages\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_campaign_lead_from_id\", \"description\": \"Retrieve lead information from a campaign using its ID via the Fomo API.\", \"parameters\": {\"is_id\": {\"description\": \"The ID of the campaign to retrieve the lead information from.\", \"type\": \"str\", \"default\": \"Lead\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"loginuser\", \"description\": \"Logs in a user by sending their credentials to a specified endpoint.\", \"parameters\": {\"username\": {\"description\": \"The user's username for login.\", \"type\": \"str\", \"default\": \"\"}, \"password\": {\"description\": \"The user's password for login in clear text.\", \"type\": \"str\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"loginuser\", \"description\": \"Logs in a user to the specified toolbench API by making a GET request to the login endpoint with the provided username and password.\", \"parameters\": {\"username\": {\"description\": \"The username for login.\", \"type\": \"str\", \"default\": \"\"}, \"password\": {\"description\": \"The password for login in clear text.\", \"type\": \"str\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Identify SaaS tools offering 'ticketing' and 'event management' features and gather lead information for campaigns with IDs 'ccccc' and 'ddddd' from Fomo API. Moreover, log in users 'johnthompson' and 'janethompson' to my_api_12345 and freeplanhardlimitexternal APIs using their password 'secr3tpa$$w'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"software_assets\", \"arguments\": {\"q\": \"ticketing, event management\"}}, {\"name\": \"get_campaign_lead_from_id\", \"arguments\": {\"is_id\": \"ccccc\"}}, {\"name\": \"get_campaign_lead_from_id\", \"arguments\": {\"is_id\": \"ddddd\"}}, {\"name\": \"loginuser\", \"arguments\": {\"username\": \"johnthompson\", \"password\": \"secr3tpa$$w\"}}, {\"name\": \"loginuser\", \"arguments\": {\"username\": \"janethompson\", \"password\": \"secr3tpa$$w\"}}]",
"style": "rule"
}
|
{
"index": 26,
"split": "train"
}
|
[{"name": "Quote of The Day", "description": "Returns a quote of the day, including the quote text and author.", "parameters": {"type": "dict", "properties": {"category": {"description": "Optional category filter for the quote (e.g., inspirational, humorous, etc.).", "type": "string"}}, "required": ["category"]}, "required": null}, {"name": "PL Car Averages", "description": "Retrieve average data for cars by year, make, and model", "parameters": {"type": "dict", "properties": {"year": {"description": "The year of the car", "type": "int"}, "make": {"description": "The make of the car", "type": "string"}, "model": {"description": "The model of the car", "type": "string"}}, "required": ["year", "make", "model"]}, "required": null}, {"name": "Get Glyph Information", "description": "Retrieve information about a specific Unicode codepoint, including the corresponding glyph.", "parameters": {"type": "dict", "properties": {"codepoint": {"description": "The hexadecimal codepoint of the Unicode character to retrieve information about.", "type": "string", "default": "0A2F"}}, "required": ["codepoint"]}, "required": null}, {"name": "Get Messages", "description": "Retrieve a list of messages based on the specified category", "parameters": {"type": "dict", "properties": {"category": {"description": "Select a category to get unlimited messages", "type": "string", "default": "love"}}, "required": ["category"]}, "required": null}, {"name": "Wayback Machine Captures", "description": "Captures a web page or snapshot using the Wayback Machine API", "parameters": {"type": "dict", "properties": {"url": {"description": "The URL of the web page to capture", "type": "string"}, "string": {"description": "The string to capture the web page (YYYY-MM-DD format)", "type": "string", "default": "2023-04-15"}}, "required": ["url"]}, "required": null}, {"name": "Get Brewery", "description": "Retrieve information about a specific brewery by its ID", "parameters": {"type": "dict", "properties": {"id": {"description": "ID of the brewery", "type": "int"}}, "required": ["id"]}, "required": null}]
|
[
{
"from": "human",
"value": "I am working on a report and need some specific information. Could you help me with the following:\n1. Get the average data for a 2018 Ford Mustang.\n2. Retrieve a quote of the day in the \"motivational\" category.\n3. Get messages in the \"friendship\" category.\n4. Capture the current state of the URL \"https://www.example.com\" using the Wayback Machine.\n5. Retrieve information about the Unicode codepoint \"1F600\"."
}
] |
[{"name": "PL Car Averages", "arguments": {"year": 2018, "make": "Ford", "model": "Mustang"}}, {"name": "Quote of The Day", "arguments": {"category": "motivational"}}, {"name": "Get Messages", "arguments": {"category": "friendship"}}, {"name": "Wayback Machine Captures", "arguments": {"url": "https://www.example.com"}}, {"name": "Get Glyph Information", "arguments": {"codepoint": "1F600"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out.
The current time is 2026-01-24 08:54:52.Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out.\nThe current time is 2026-01-24 08:54:52.Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"Quote of The Day\", \"description\": \"Returns a quote of the day, including the quote text and author.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"category\": {\"description\": \"Optional category filter for the quote (e.g., inspirational, humorous, etc.).\", \"type\": \"string\"}}, \"required\": [\"category\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"PL Car Averages\", \"description\": \"Retrieve average data for cars by year, make, and model\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"year\": {\"description\": \"The year of the car\", \"type\": \"int\"}, \"make\": {\"description\": \"The make of the car\", \"type\": \"string\"}, \"model\": {\"description\": \"The model of the car\", \"type\": \"string\"}}, \"required\": [\"year\", \"make\", \"model\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Get Glyph Information\", \"description\": \"Retrieve information about a specific Unicode codepoint, including the corresponding glyph.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"codepoint\": {\"description\": \"The hexadecimal codepoint of the Unicode character to retrieve information about.\", \"type\": \"string\", \"default\": \"0A2F\"}}, \"required\": [\"codepoint\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Get Messages\", \"description\": \"Retrieve a list of messages based on the specified category\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"category\": {\"description\": \"Select a category to get unlimited messages\", \"type\": \"string\", \"default\": \"love\"}}, \"required\": [\"category\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Wayback Machine Captures\", \"description\": \"Captures a web page or snapshot using the Wayback Machine API\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"url\": {\"description\": \"The URL of the web page to capture\", \"type\": \"string\"}, \"string\": {\"description\": \"The string to capture the web page (YYYY-MM-DD format)\", \"type\": \"string\", \"default\": \"2023-04-15\"}}, \"required\": [\"url\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Get Brewery\", \"description\": \"Retrieve information about a specific brewery by its ID\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"id\": {\"description\": \"ID of the brewery\", \"type\": \"int\"}}, \"required\": [\"id\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I am working on a report and need some specific information. Could you help me with the following:\n1. Get the average data for a 2018 Ford Mustang.\n2. Retrieve a quote of the day in the \"motivational\" category.\n3. Get messages in the \"friendship\" category.\n4. Capture the current state of the URL \"https://www.example.com\" using the Wayback Machine.\n5. Retrieve information about the Unicode codepoint \"1F600\".",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"PL Car Averages\", \"arguments\": {\"year\": 2018, \"make\": \"Ford\", \"model\": \"Mustang\"}}, {\"name\": \"Quote of The Day\", \"arguments\": {\"category\": \"motivational\"}}, {\"name\": \"Get Messages\", \"arguments\": {\"category\": \"friendship\"}}, {\"name\": \"Wayback Machine Captures\", \"arguments\": {\"url\": \"https://www.example.com\"}}, {\"name\": \"Get Glyph Information\", \"arguments\": {\"codepoint\": \"1F600\"}}]",
"style": "rule"
}
|
{
"index": 27,
"split": "train"
}
|
[{"name": "get_referral_domains", "description": "Retrieves a list of referral domains for a given domain using the Toolbench RapidAPI.", "parameters": {"domain": {"description": "The domain to retrieve referral domains for.", "type": "str", "default": "getecz.com"}}}]
|
[
{
"from": "human",
"value": "What are the referral domains for 'twitter.com'?"
}
] |
[{"name": "get_referral_domains", "arguments": {"domain": "twitter.com"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_referral_domains\", \"description\": \"Retrieves a list of referral domains for a given domain using the Toolbench RapidAPI.\", \"parameters\": {\"domain\": {\"description\": \"The domain to retrieve referral domains for.\", \"type\": \"str\", \"default\": \"getecz.com\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What are the referral domains for 'twitter.com'?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_referral_domains\", \"arguments\": {\"domain\": \"twitter.com\"}}]",
"style": "rule"
}
|
{
"index": 28,
"split": "train"
}
|
[{"name": "baseball_match_statistics", "description": "Fetches and returns statistics for a specified baseball match.", "parameters": {"match_id": {"description": "The unique identifier for the baseball match to retrieve statistics for.", "type": "str", "default": "9863520"}}}]
|
[
{
"from": "human",
"value": "Retrieve details for the baseball game with ID 'T778899'."
}
] |
[{"name": "baseball_match_statistics", "arguments": {"match_id": "T778899"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"baseball_match_statistics\", \"description\": \"Fetches and returns statistics for a specified baseball match.\", \"parameters\": {\"match_id\": {\"description\": \"The unique identifier for the baseball match to retrieve statistics for.\", \"type\": \"str\", \"default\": \"9863520\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Retrieve details for the baseball game with ID 'T778899'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"baseball_match_statistics\", \"arguments\": {\"match_id\": \"T778899\"}}]",
"style": "rule"
}
|
{
"index": 29,
"split": "train"
}
|
[{"name": "getmusiclenses", "description": "Fetches music lenses from the Snapchat API.", "parameters": {"cursor": {"description": "A string to navigate through paginated results. Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "gettrendinglenses", "description": "Fetches the trending lenses from Snapchat using the RapidAPI service.", "parameters": {"cursor": {"description": "A cursor for pagination. Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "sign_info", "description": "Fetches and returns the sign information from the OnlyFans API using the provided user agent and RapidAPI key.", "parameters": {"useragent": {"description": "The user agent string to be used in the API request.", "type": "str", "default": ""}}}]
|
[
{
"from": "human",
"value": "I'm interested in seeing the sign information for a user on OnlyFans. Their user agent is 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'. Can you help me with that?"
}
] |
[{"name": "sign_info", "arguments": {"useragent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"getmusiclenses\", \"description\": \"Fetches music lenses from the Snapchat API.\", \"parameters\": {\"cursor\": {\"description\": \"A string to navigate through paginated results. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"gettrendinglenses\", \"description\": \"Fetches the trending lenses from Snapchat using the RapidAPI service.\", \"parameters\": {\"cursor\": {\"description\": \"A cursor for pagination. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"sign_info\", \"description\": \"Fetches and returns the sign information from the OnlyFans API using the provided user agent and RapidAPI key.\", \"parameters\": {\"useragent\": {\"description\": \"The user agent string to be used in the API request.\", \"type\": \"str\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I'm interested in seeing the sign information for a user on OnlyFans. Their user agent is 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'. Can you help me with that?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"sign_info\", \"arguments\": {\"useragent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3\"}}]",
"style": "rule"
}
|
{
"index": 30,
"split": "train"
}
|
[{"name": "games_esports", "description": "Fetches information about esports games for a given event ID using the SofaSport API.", "parameters": {"event_id": {"description": "The ID of the event to retrieve esports games for.", "type": "int", "default": "10289011"}}}, {"name": "shotmap", "description": "Fetches the shotmap data for a given event from the SofaSport API.", "parameters": {"event_id": {"description": "The unique identifier for the event.", "type": "int", "default": "10230638"}}}, {"name": "getdivision", "description": "Retrieve information about a specific NHL division by its ID via the NHL Stats and Live Data API.", "parameters": {"is_id": {"description": "The ID of the division to retrieve information for.", "type": "int", "default": 15}}}, {"name": "results", "description": "Fetch soccer match results for a specified date from the Msport API.", "parameters": {"date": {"description": "The date of the soccer matches to retrieve results for (format: 'YYYY-MM-DD').", "type": "str", "default": "2023-01-30"}, "page": {"description": "The page number of results to retrieve. Defaults to 1.", "type": "int, optional", "default": "1"}}}]
|
[
{
"from": "human",
"value": "Get the shotmap data for event ID 11223 and the esports games for event ID 44556."
}
] |
[{"name": "shotmap", "arguments": {"event_id": 11223}}, {"name": "games_esports", "arguments": {"event_id": 44556}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"games_esports\", \"description\": \"Fetches information about esports games for a given event ID using the SofaSport API.\", \"parameters\": {\"event_id\": {\"description\": \"The ID of the event to retrieve esports games for.\", \"type\": \"int\", \"default\": \"10289011\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"shotmap\", \"description\": \"Fetches the shotmap data for a given event from the SofaSport API.\", \"parameters\": {\"event_id\": {\"description\": \"The unique identifier for the event.\", \"type\": \"int\", \"default\": \"10230638\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"getdivision\", \"description\": \"Retrieve information about a specific NHL division by its ID via the NHL Stats and Live Data API.\", \"parameters\": {\"is_id\": {\"description\": \"The ID of the division to retrieve information for.\", \"type\": \"int\", \"default\": 15}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"results\", \"description\": \"Fetch soccer match results for a specified date from the Msport API.\", \"parameters\": {\"date\": {\"description\": \"The date of the soccer matches to retrieve results for (format: 'YYYY-MM-DD').\", \"type\": \"str\", \"default\": \"2023-01-30\"}, \"page\": {\"description\": \"The page number of results to retrieve. Defaults to 1.\", \"type\": \"int, optional\", \"default\": \"1\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Get the shotmap data for event ID 11223 and the esports games for event ID 44556.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"shotmap\", \"arguments\": {\"event_id\": 11223}}, {\"name\": \"games_esports\", \"arguments\": {\"event_id\": 44556}}]",
"style": "rule"
}
|
{
"index": 31,
"split": "train"
}
|
[{"name": "calculate_distance", "description": "Calculates the Euclidean distance between two points in n-dimensional space.", "parameters": {"point1": {"description": "The coordinates of the first point.", "type": "List[float]"}, "point2": {"description": "The coordinates of the second point.", "type": "List[float]"}}}]
|
[
{
"from": "human",
"value": "Calculate the Euclidean distance between the points (0, 0, 0, 0, 0) and (1, 1, 1, 1, 1), and also between the points (2, 2, 2, 2, 2) and (3, 3, 3, 3, 3) using the 'calculate_distance' function."
}
] |
[{"name": "calculate_distance", "arguments": {"point1": [0, 0, 0, 0, 0], "point2": [1, 1, 1, 1, 1]}}, {"name": "calculate_distance", "arguments": {"point1": [2, 2, 2, 2, 2], "point2": [3, 3, 3, 3, 3]}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_distance\", \"description\": \"Calculates the Euclidean distance between two points in n-dimensional space.\", \"parameters\": {\"point1\": {\"description\": \"The coordinates of the first point.\", \"type\": \"List[float]\"}, \"point2\": {\"description\": \"The coordinates of the second point.\", \"type\": \"List[float]\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Calculate the Euclidean distance between the points (0, 0, 0, 0, 0) and (1, 1, 1, 1, 1), and also between the points (2, 2, 2, 2, 2) and (3, 3, 3, 3, 3) using the 'calculate_distance' function.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"calculate_distance\", \"arguments\": {\"point1\": [0, 0, 0, 0, 0], \"point2\": [1, 1, 1, 1, 1]}}, {\"name\": \"calculate_distance\", \"arguments\": {\"point1\": [2, 2, 2, 2, 2], \"point2\": [3, 3, 3, 3, 3]}}]",
"style": "rule"
}
|
{
"index": 32,
"split": "train"
}
|
[{"name": "polygon_area_shoelace", "description": "Calculates the area of a polygon using the shoelace formula.", "parameters": {"vertices": {"description": "A list of polygon vertices represented as tuples (x, y).", "type": "List[Tuple[float, float]]"}}}, {"name": "euclidean_distance", "description": "Computes the Euclidean distance between two points in a 2D plane.", "parameters": {"point_a": {"description": "The coordinates of the first point (x, y).", "type": "Tuple[float, float]"}, "point_b": {"description": "The coordinates of the second point (x, y).", "type": "Tuple[float, float]"}}}]
|
[
{
"from": "human",
"value": "Determine the distance between the points (-1,-1) and (1,1)."
}
] |
[{"name": "euclidean_distance", "arguments": {"point_a": [-1, -1], "point_b": [1, 1]}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"polygon_area_shoelace\", \"description\": \"Calculates the area of a polygon using the shoelace formula.\", \"parameters\": {\"vertices\": {\"description\": \"A list of polygon vertices represented as tuples (x, y).\", \"type\": \"List[Tuple[float, float]]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"euclidean_distance\", \"description\": \"Computes the Euclidean distance between two points in a 2D plane.\", \"parameters\": {\"point_a\": {\"description\": \"The coordinates of the first point (x, y).\", \"type\": \"Tuple[float, float]\"}, \"point_b\": {\"description\": \"The coordinates of the second point (x, y).\", \"type\": \"Tuple[float, float]\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Determine the distance between the points (-1,-1) and (1,1).",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"euclidean_distance\", \"arguments\": {\"point_a\": [-1, -1], \"point_b\": [1, 1]}}]",
"style": "rule"
}
|
{
"index": 33,
"split": "train"
}
|
[{"name": "runner_up", "description": "Fetches the runner-up team data for the given identifying parameter from the NCAA Final Four API.", "parameters": {"identifier": {"description": "The identifier (e.g., year) to fetch the runner-up team data for.", "type": "str", "default": "1959"}}}, {"name": "basketball_search", "description": "Search for basketball players, teams, and tournaments using the provided term.", "parameters": {"term": {"description": "The search term used to look for players, teams, and tournaments.", "type": "str", "default": "kevin"}}}]
|
[
{
"from": "human",
"value": "Who were the runner-up teams in the NCAA Final Four in the years 2000, 2005, and 2010? Also, search for basketball players named 'LeBron James'."
}
] |
[{"name": "runner_up", "arguments": {"identifier": "2000"}}, {"name": "runner_up", "arguments": {"identifier": "2005"}}, {"name": "runner_up", "arguments": {"identifier": "2010"}}, {"name": "basketball_search", "arguments": {"term": "LeBron James"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"runner_up\", \"description\": \"Fetches the runner-up team data for the given identifying parameter from the NCAA Final Four API.\", \"parameters\": {\"identifier\": {\"description\": \"The identifier (e.g., year) to fetch the runner-up team data for.\", \"type\": \"str\", \"default\": \"1959\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"basketball_search\", \"description\": \"Search for basketball players, teams, and tournaments using the provided term.\", \"parameters\": {\"term\": {\"description\": \"The search term used to look for players, teams, and tournaments.\", \"type\": \"str\", \"default\": \"kevin\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Who were the runner-up teams in the NCAA Final Four in the years 2000, 2005, and 2010? Also, search for basketball players named 'LeBron James'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"runner_up\", \"arguments\": {\"identifier\": \"2000\"}}, {\"name\": \"runner_up\", \"arguments\": {\"identifier\": \"2005\"}}, {\"name\": \"runner_up\", \"arguments\": {\"identifier\": \"2010\"}}, {\"name\": \"basketball_search\", \"arguments\": {\"term\": \"LeBron James\"}}]",
"style": "rule"
}
|
{
"index": 34,
"split": "train"
}
|
[{"name": "match_scorecard", "description": "Fetches the full scorecard (updated live) for a given match ID using the RapidAPI service.", "parameters": {"match_id": {"description": "The ID of the cricket match for which to retrieve the live scorecard.", "type": "int", "default": "2432999"}}}, {"name": "player_latest_media", "description": "Fetch the latest media for a given player using their player ID.", "parameters": {"player_id": {"description": "The unique identifier of the player for whom the latest media is to be fetched.", "type": "int", "default": "12994"}}}]
|
[
{
"from": "human",
"value": "I'd like to know the score of match 85296 and the latest media from player 74135."
}
] |
[{"name": "match_scorecard", "arguments": {"match_id": 85296}}, {"name": "player_latest_media", "arguments": {"player_id": 74135}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"match_scorecard\", \"description\": \"Fetches the full scorecard (updated live) for a given match ID using the RapidAPI service.\", \"parameters\": {\"match_id\": {\"description\": \"The ID of the cricket match for which to retrieve the live scorecard.\", \"type\": \"int\", \"default\": \"2432999\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"player_latest_media\", \"description\": \"Fetch the latest media for a given player using their player ID.\", \"parameters\": {\"player_id\": {\"description\": \"The unique identifier of the player for whom the latest media is to be fetched.\", \"type\": \"int\", \"default\": \"12994\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I'd like to know the score of match 85296 and the latest media from player 74135.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"match_scorecard\", \"arguments\": {\"match_id\": 85296}}, {\"name\": \"player_latest_media\", \"arguments\": {\"player_id\": 74135}}]",
"style": "rule"
}
|
{
"index": 35,
"split": "train"
}
|
[{"name": "getprojects", "description": "Fetches artificial intelligence projects from the specified page using the provided RapidAPI key.", "parameters": {"page": {"description": "The page number of the projects to retrieve.", "type": "int", "default": "1"}}}, {"name": "tirto_search", "description": "Searches Tirto news data using the RapidAPI interface.", "parameters": {"limit": {"description": "The maximum number of search results to return.", "type": "str", "default": "10"}, "q": {"description": "The query string to search for in Tirto news articles.", "type": "str", "default": "banjir"}, "page": {"description": "The page number for paginated results.", "type": "str", "default": "1"}}}, {"name": "get_individual_news_from_source", "description": "Fetch LGBTQ+ related news from a specific newspaper using the newspaper's ID.", "parameters": {"newspaperid": {"description": "The unique identifier of the newspaper from which to retrieve news.", "type": "str", "default": "gaytimes"}}}]
|
[
{
"from": "human",
"value": "Get the latest AI projects from the first page and search Tirto for 'digital transformation' from page 1 with a limit of 5."
}
] |
[{"name": "getprojects", "arguments": {"page": 1}}, {"name": "tirto_search", "arguments": {"limit": "5", "q": "digital transformation", "page": "1"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"getprojects\", \"description\": \"Fetches artificial intelligence projects from the specified page using the provided RapidAPI key.\", \"parameters\": {\"page\": {\"description\": \"The page number of the projects to retrieve.\", \"type\": \"int\", \"default\": \"1\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"tirto_search\", \"description\": \"Searches Tirto news data using the RapidAPI interface.\", \"parameters\": {\"limit\": {\"description\": \"The maximum number of search results to return.\", \"type\": \"str\", \"default\": \"10\"}, \"q\": {\"description\": \"The query string to search for in Tirto news articles.\", \"type\": \"str\", \"default\": \"banjir\"}, \"page\": {\"description\": \"The page number for paginated results.\", \"type\": \"str\", \"default\": \"1\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_individual_news_from_source\", \"description\": \"Fetch LGBTQ+ related news from a specific newspaper using the newspaper's ID.\", \"parameters\": {\"newspaperid\": {\"description\": \"The unique identifier of the newspaper from which to retrieve news.\", \"type\": \"str\", \"default\": \"gaytimes\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Get the latest AI projects from the first page and search Tirto for 'digital transformation' from page 1 with a limit of 5.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"getprojects\", \"arguments\": {\"page\": 1}}, {\"name\": \"tirto_search\", \"arguments\": {\"limit\": \"5\", \"q\": \"digital transformation\", \"page\": \"1\"}}]",
"style": "rule"
}
|
{
"index": 36,
"split": "train"
}
|
[{"name": "future_investment_value", "description": "Calculates the future value of an investment based on the present value, annual interest rate, and number of years.", "parameters": {"present_value": {"description": "The present value of the investment.", "type": "float"}, "annual_interest_rate": {"description": "The annual interest rate as a decimal (e.g., 0.05 for 5%).", "type": "float"}, "years": {"description": "The number of years the investment will grow.", "type": "int"}}}, {"name": "displacement", "description": "Calculates the displacement of an object given its initial velocity, acceleration, and time.", "parameters": {"initial_velocity": {"description": "The initial velocity of the object.", "type": "float"}, "acceleration": {"description": "The acceleration of the object.", "type": "float"}, "time": {"description": "The time elapsed.", "type": "float"}}}, {"name": "binomial_probability", "description": "Calculates the probability of getting exactly k successes in n independent trials,", "parameters": {"n": {"description": "The total number of trials.", "type": "int"}, "k": {"description": "The number of successes.", "type": "int"}, "p": {"description": "The probability of success in each trial.", "type": "float"}}}, {"name": "light_travel_time", "description": "Calculate the time taken for light to travel from one celestial body to another.", "parameters": {"distance_in_light_years": {"description": "The distance between the two celestial bodies in light years.", "type": "int", "default": 299792458}, "speed_of_light": {"description": "The speed of light in vacuum, in m/s. Default value is 299792458 m/s.", "type": "int", "default": 299792458}}}]
|
[
{
"from": "human",
"value": "What is the probability of getting exactly 5 successes in 15 trials where the success probability is 0.6? Also, how long does it take for light to travel from our galaxy to the Andromeda galaxy, which is about 2.537 million light years away?"
}
] |
[{"name": "binomial_probability", "arguments": {"n": 15, "k": 5, "p": 0.6}}, {"name": "light_travel_time", "arguments": {"distance_in_light_years": 2537000}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"future_investment_value\", \"description\": \"Calculates the future value of an investment based on the present value, annual interest rate, and number of years.\", \"parameters\": {\"present_value\": {\"description\": \"The present value of the investment.\", \"type\": \"float\"}, \"annual_interest_rate\": {\"description\": \"The annual interest rate as a decimal (e.g., 0.05 for 5%).\", \"type\": \"float\"}, \"years\": {\"description\": \"The number of years the investment will grow.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"displacement\", \"description\": \"Calculates the displacement of an object given its initial velocity, acceleration, and time.\", \"parameters\": {\"initial_velocity\": {\"description\": \"The initial velocity of the object.\", \"type\": \"float\"}, \"acceleration\": {\"description\": \"The acceleration of the object.\", \"type\": \"float\"}, \"time\": {\"description\": \"The time elapsed.\", \"type\": \"float\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"binomial_probability\", \"description\": \"Calculates the probability of getting exactly k successes in n independent trials,\", \"parameters\": {\"n\": {\"description\": \"The total number of trials.\", \"type\": \"int\"}, \"k\": {\"description\": \"The number of successes.\", \"type\": \"int\"}, \"p\": {\"description\": \"The probability of success in each trial.\", \"type\": \"float\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"light_travel_time\", \"description\": \"Calculate the time taken for light to travel from one celestial body to another.\", \"parameters\": {\"distance_in_light_years\": {\"description\": \"The distance between the two celestial bodies in light years.\", \"type\": \"int\", \"default\": 299792458}, \"speed_of_light\": {\"description\": \"The speed of light in vacuum, in m/s. Default value is 299792458 m/s.\", \"type\": \"int\", \"default\": 299792458}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the probability of getting exactly 5 successes in 15 trials where the success probability is 0.6? Also, how long does it take for light to travel from our galaxy to the Andromeda galaxy, which is about 2.537 million light years away?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"binomial_probability\", \"arguments\": {\"n\": 15, \"k\": 5, \"p\": 0.6}}, {\"name\": \"light_travel_time\", \"arguments\": {\"distance_in_light_years\": 2537000}}]",
"style": "rule"
}
|
{
"index": 37,
"split": "train"
}
|
[{"name": "top_paid_ios_apps", "description": "Fetches a list of the top paid iOS apps from the App Store.", "parameters": {"lang": {"description": "Language code for the results. Defaults to 'en'.", "type": "str", "default": "en"}, "category": {"description": "Category ID to filter results by. Defaults to '6016'.", "type": "str", "default": "6016"}, "country": {"description": "Country code for the App Store to search in. Defaults to 'us'.", "type": "str", "default": "us"}, "num": {"description": "Number of results to return. Defaults to 100. Maximum is 200.", "type": "int", "default": "100"}}}, {"name": "skill_child", "description": "Fetches child skill data from an external API using provided identifiers.", "parameters": {"is_id": {"description": "The unique identifier for the desired child skill data. Defaults to 'files/198956'.", "type": "str, optional", "default": "files/198956"}}}, {"name": "pluses_and_minuses_of_the_car", "description": "Fetches the list of pluses and minuses for a specific car model using the ToolBench RapidAPI.", "parameters": {"year": {"description": "The year of manufacture of the car.", "type": "str", "default": "2012"}, "make": {"description": "The make (manufacturer) of the car.", "type": "str", "default": "bmw"}, "model": {"description": "The model of the car.", "type": "str", "default": "5 series"}}}]
|
[
{
"from": "human",
"value": "Could you provide me with the pros and cons of a 2010 Honda Civic?"
}
] |
[{"name": "pluses_and_minuses_of_the_car", "arguments": {"year": "2010", "make": "Honda", "model": "Civic"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"top_paid_ios_apps\", \"description\": \"Fetches a list of the top paid iOS apps from the App Store.\", \"parameters\": {\"lang\": {\"description\": \"Language code for the results. Defaults to 'en'.\", \"type\": \"str\", \"default\": \"en\"}, \"category\": {\"description\": \"Category ID to filter results by. Defaults to '6016'.\", \"type\": \"str\", \"default\": \"6016\"}, \"country\": {\"description\": \"Country code for the App Store to search in. Defaults to 'us'.\", \"type\": \"str\", \"default\": \"us\"}, \"num\": {\"description\": \"Number of results to return. Defaults to 100. Maximum is 200.\", \"type\": \"int\", \"default\": \"100\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"skill_child\", \"description\": \"Fetches child skill data from an external API using provided identifiers.\", \"parameters\": {\"is_id\": {\"description\": \"The unique identifier for the desired child skill data. Defaults to 'files/198956'.\", \"type\": \"str, optional\", \"default\": \"files/198956\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"pluses_and_minuses_of_the_car\", \"description\": \"Fetches the list of pluses and minuses for a specific car model using the ToolBench RapidAPI.\", \"parameters\": {\"year\": {\"description\": \"The year of manufacture of the car.\", \"type\": \"str\", \"default\": \"2012\"}, \"make\": {\"description\": \"The make (manufacturer) of the car.\", \"type\": \"str\", \"default\": \"bmw\"}, \"model\": {\"description\": \"The model of the car.\", \"type\": \"str\", \"default\": \"5 series\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Could you provide me with the pros and cons of a 2010 Honda Civic?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"pluses_and_minuses_of_the_car\", \"arguments\": {\"year\": \"2010\", \"make\": \"Honda\", \"model\": \"Civic\"}}]",
"style": "rule"
}
|
{
"index": 38,
"split": "train"
}
|
[{"name": "get_call", "description": "Fetches the API result using the given request ID.", "parameters": {"request_id": {"description": "The unique identifier for the API request.", "type": "str", "default": "76d1c748-51ed-435b-bcd8-3d9c9d3eb68a"}}}, {"name": "getproductbyname", "description": "Fetches product information for a specific brand from the products database via the Cartify API.", "parameters": {"brand": {"description": "The name of the brand to filter products by.", "type": "str", "default": "iPhone"}}}]
|
[
{
"from": "human",
"value": "Could you get the response for request '97531' and also provide details about products from 'Vans'?"
}
] |
[{"name": "get_call", "arguments": {"request_id": "97531"}}, {"name": "getproductbyname", "arguments": {"brand": "Vans"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_call\", \"description\": \"Fetches the API result using the given request ID.\", \"parameters\": {\"request_id\": {\"description\": \"The unique identifier for the API request.\", \"type\": \"str\", \"default\": \"76d1c748-51ed-435b-bcd8-3d9c9d3eb68a\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"getproductbyname\", \"description\": \"Fetches product information for a specific brand from the products database via the Cartify API.\", \"parameters\": {\"brand\": {\"description\": \"The name of the brand to filter products by.\", \"type\": \"str\", \"default\": \"iPhone\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Could you get the response for request '97531' and also provide details about products from 'Vans'?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_call\", \"arguments\": {\"request_id\": \"97531\"}}, {\"name\": \"getproductbyname\", \"arguments\": {\"brand\": \"Vans\"}}]",
"style": "rule"
}
|
{
"index": 39,
"split": "train"
}
|
[{"name": "get_company_ads_count", "description": "Fetch the number of ads a specific company has posted on LinkedIn using the Toolbench RapidAPI.", "parameters": {"company_id": {"description": "The unique identifier of the company whose ad count is to be fetched.", "type": "str", "default": "162479"}}}, {"name": "search_agents", "description": "Search for real estate agents based on various criteria such as location, price range, language, etc.", "parameters": {"location": {"description": "The city or zip code to search for agents.", "type": "str", "default": "santa monica"}, "page": {"description": "The page number of the results to retrieve. Defaults to 1.", "type": "int, optional", "default": "1"}, "price": {"description": "The price range of properties the agent deals with, formatted as 'minPrice_maxPrice'. Defaults to None.", "type": "str, optional", "default": ""}, "agentname": {"description": "The name of the agent to search for. Defaults to None.", "type": "str, optional", "default": ""}, "lang": {"description": "The language spoken by the agent. Defaults to None.", "type": "str, optional", "default": ""}, "photo": {"description": "Whether to only show agents with a photo. 1 for yes, 0 for no. Defaults to None.", "type": "bool, optional", "default": "1"}, "rating": {"description": "The rating of the agent, between 1 and 5. Defaults to None.", "type": "int, optional", "default": ""}}}]
|
[
{
"from": "human",
"value": "What is the ad count for the company '67890' on LinkedIn? Additionally, list agents in Los Angeles dealing with properties priced between $500,000 and $1,000,000."
}
] |
[{"name": "get_company_ads_count", "arguments": {"company_id": "67890"}}, {"name": "search_agents", "arguments": {"location": "Los Angeles", "price": "500000_1000000"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_company_ads_count\", \"description\": \"Fetch the number of ads a specific company has posted on LinkedIn using the Toolbench RapidAPI.\", \"parameters\": {\"company_id\": {\"description\": \"The unique identifier of the company whose ad count is to be fetched.\", \"type\": \"str\", \"default\": \"162479\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"search_agents\", \"description\": \"Search for real estate agents based on various criteria such as location, price range, language, etc.\", \"parameters\": {\"location\": {\"description\": \"The city or zip code to search for agents.\", \"type\": \"str\", \"default\": \"santa monica\"}, \"page\": {\"description\": \"The page number of the results to retrieve. Defaults to 1.\", \"type\": \"int, optional\", \"default\": \"1\"}, \"price\": {\"description\": \"The price range of properties the agent deals with, formatted as 'minPrice_maxPrice'. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}, \"agentname\": {\"description\": \"The name of the agent to search for. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}, \"lang\": {\"description\": \"The language spoken by the agent. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}, \"photo\": {\"description\": \"Whether to only show agents with a photo. 1 for yes, 0 for no. Defaults to None.\", \"type\": \"bool, optional\", \"default\": \"1\"}, \"rating\": {\"description\": \"The rating of the agent, between 1 and 5. Defaults to None.\", \"type\": \"int, optional\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the ad count for the company '67890' on LinkedIn? Additionally, list agents in Los Angeles dealing with properties priced between $500,000 and $1,000,000.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_company_ads_count\", \"arguments\": {\"company_id\": \"67890\"}}, {\"name\": \"search_agents\", \"arguments\": {\"location\": \"Los Angeles\", \"price\": \"500000_1000000\"}}]",
"style": "rule"
}
|
{
"index": 40,
"split": "train"
}
|
[{"name": "protocol", "description": "Fetch protocol details using a given protocol ID.", "parameters": {"is_id": {"description": "The ID of the protocol to retrieve details for.", "type": "str", "default": "curve"}}}]
|
[
{
"from": "human",
"value": "Can you fetch details for protocols with IDs 'ETH2' and 'BTC'? Also, what about 'LTC' and 'XRP'?"
}
] |
[{"name": "protocol", "arguments": {"is_id": "ETH2"}}, {"name": "protocol", "arguments": {"is_id": "BTC"}}, {"name": "protocol", "arguments": {"is_id": "LTC"}}, {"name": "protocol", "arguments": {"is_id": "XRP"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"protocol\", \"description\": \"Fetch protocol details using a given protocol ID.\", \"parameters\": {\"is_id\": {\"description\": \"The ID of the protocol to retrieve details for.\", \"type\": \"str\", \"default\": \"curve\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Can you fetch details for protocols with IDs 'ETH2' and 'BTC'? Also, what about 'LTC' and 'XRP'?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"protocol\", \"arguments\": {\"is_id\": \"ETH2\"}}, {\"name\": \"protocol\", \"arguments\": {\"is_id\": \"BTC\"}}, {\"name\": \"protocol\", \"arguments\": {\"is_id\": \"LTC\"}}, {\"name\": \"protocol\", \"arguments\": {\"is_id\": \"XRP\"}}]",
"style": "rule"
}
|
{
"index": 41,
"split": "train"
}
|
[{"name": "spellout", "description": "Spells out a given number in the specified language using the provided rule set.", "parameters": {"data": {"description": "The number to be spelled out.", "type": "int", "default": 123}, "lang": {"description": "The 2-letter ISO 639 language code specifying the language in which the number will be spelled out. Use the `/v1/languages` endpoint to list all supported languages.", "type": "str", "default": "en"}, "ruleset": {"description": "The name of the rule set to use for spelling out the number. Use the `/v1/rulesets` endpoint to list all supported rule sets for any given language.", "type": "str", "default": "spellout-cardinal"}}}, {"name": "classify", "description": "Classifies input text using the IAB taxonomy via RapidAPI and returns the confidence score and IAB classification.", "parameters": {"text": {"description": "The input text to be classified.", "type": "str", "default": "Bank of Americate all your financial and banking requirements satisfied here."}}}, {"name": "extract_entities", "description": "Extracts named entities from the provided text using the specified model and RapidAPI key.", "parameters": {"text": {"description": "The text from which to extract named entities.", "type": "str", "default": "U.S. stocks rallied Thursday, with the Dow Jones Industrial Average up 2.9% in a tempestuous first half of the year."}, "model": {"description": "The model to use for named entity recognition. Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "generate", "description": "Generate a rewritten version of a given article using the Article Rewriter Pro API.", "parameters": {"lang": {"description": "Language code of the article to be rewritten.", "type": "str", "default": "en"}, "article": {"description": "The article text to be rewritten.", "type": "str", "default": "Dedicated servers or bare metal servers are a server in itself with no server resources sharing with other hosting account users. These servers offer a higher power and flexibility, but usually comes at a premium cost. In such cases, you must have to research well about the dedicated hosting service providers."}}}]
|
[
{
"from": "human",
"value": "Spell out the number 1234 in French using the standard ruleset."
}
] |
[{"name": "spellout", "arguments": {"data": 1234, "lang": "fr", "ruleset": "standard"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"spellout\", \"description\": \"Spells out a given number in the specified language using the provided rule set.\", \"parameters\": {\"data\": {\"description\": \"The number to be spelled out.\", \"type\": \"int\", \"default\": 123}, \"lang\": {\"description\": \"The 2-letter ISO 639 language code specifying the language in which the number will be spelled out. Use the `/v1/languages` endpoint to list all supported languages.\", \"type\": \"str\", \"default\": \"en\"}, \"ruleset\": {\"description\": \"The name of the rule set to use for spelling out the number. Use the `/v1/rulesets` endpoint to list all supported rule sets for any given language.\", \"type\": \"str\", \"default\": \"spellout-cardinal\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"classify\", \"description\": \"Classifies input text using the IAB taxonomy via RapidAPI and returns the confidence score and IAB classification.\", \"parameters\": {\"text\": {\"description\": \"The input text to be classified.\", \"type\": \"str\", \"default\": \"Bank of Americate all your financial and banking requirements satisfied here.\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"extract_entities\", \"description\": \"Extracts named entities from the provided text using the specified model and RapidAPI key.\", \"parameters\": {\"text\": {\"description\": \"The text from which to extract named entities.\", \"type\": \"str\", \"default\": \"U.S. stocks rallied Thursday, with the Dow Jones Industrial Average up 2.9% in a tempestuous first half of the year.\"}, \"model\": {\"description\": \"The model to use for named entity recognition. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"generate\", \"description\": \"Generate a rewritten version of a given article using the Article Rewriter Pro API.\", \"parameters\": {\"lang\": {\"description\": \"Language code of the article to be rewritten.\", \"type\": \"str\", \"default\": \"en\"}, \"article\": {\"description\": \"The article text to be rewritten.\", \"type\": \"str\", \"default\": \"Dedicated servers or bare metal servers are a server in itself with no server resources sharing with other hosting account users. These servers offer a higher power and flexibility, but usually comes at a premium cost. In such cases, you must have to research well about the dedicated hosting service providers.\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Spell out the number 1234 in French using the standard ruleset.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"spellout\", \"arguments\": {\"data\": 1234, \"lang\": \"fr\", \"ruleset\": \"standard\"}}]",
"style": "rule"
}
|
{
"index": 42,
"split": "train"
}
|
[{"name": "predict_forest_area", "description": "Predicts the change in forest area over a specified number of years.", "parameters": {"location": {"description": "The geographic location for the prediction.", "type": "str"}, "num_years": {"description": "The number of years into the future to make the prediction.", "type": "int"}, "include_humans": {"description": "Whether to include the impact of human activities in the prediction. Defaults to False.", "type": "bool, optional"}}}, {"name": "get_holidays_by_year", "description": "Retrieves the list of public holidays for a given year and country using the Nager.Date API.", "parameters": {"year": {"description": "The year for which to retrieve the holidays.", "type": "int"}, "country_code": {"description": "The two-letter ISO 3166-1 alpha-2 country code.", "type": "str"}}}, {"name": "simulate_query_database", "description": "Simulates querying a database based on certain conditions.", "parameters": {"table": {"description": "Name of the table to query.", "type": "str"}, "conditions": {"description": "Conditions for the query, each condition is a dictionary.", "type": "list"}}}, {"name": "project_investment_growth", "description": "Projects the growth of an investment over a specified number of years.", "parameters": {"principal": {"description": "The initial investment amount.", "type": "float", "default": true}, "annual_addition": {"description": "The amount added to the investment annually.", "type": "float", "default": true}, "years": {"description": "The number of years to project the investment growth.", "type": "int"}, "return_rate": {"description": "The annual return rate as a decimal (e.g., 0.07 for 7%).", "type": "float"}, "inflation": {"description": "A list of annual inflation rates as decimals.", "type": "List[float]"}, "inflation_adjusted": {"description": "Whether to adjust the final value for inflation. Defaults to True.", "type": "bool, optional"}}}, {"name": "get_dna_sequence", "description": "Retrieves the DNA sequence for a given sequence ID from the NCBI Nucleotide database.", "parameters": {"sequence_id": {"description": "The unique identifier for the DNA sequence.", "type": "str", "default": "fasta"}, "file_format": {"description": "The format of the returned sequence. Allowed values: \"fasta\" (default) or \"gb\".", "type": "str, optional"}, "upstream_bases": {"description": "The number of bases upstream of the sequence to include. Defaults to 0.", "type": "int, optional", "default": "fasta"}}}, {"name": "reserve_hotel_room", "description": "Reserves a hotel room with the specified details.", "parameters": {"room_type": {"description": "The type of room to reserve.", "type": "str"}, "nightly_rate": {"description": "The nightly rate for the room.", "type": "float"}, "checkin_date": {"description": "The check-in date in the format 'YYYY-MM-DD'.", "type": "str"}, "checkout_date": {"description": "The check-out date in the format 'YYYY-MM-DD'.", "type": "str"}, "guest_id": {"description": "The unique identifier for the guest.", "type": "str"}, "promo_code": {"description": "A promotional code for a discount. Defaults to None.", "type": "str, optional"}}}]
|
[
{
"from": "human",
"value": "Predict the change in forest area in the Amazon for the next 10 years considering human impact. Also, retrieve the public holidays for the year 2023 in the UK."
}
] |
[{"name": "predict_forest_area", "arguments": {"location": "Amazon", "num_years": 10, "include_humans": true}}, {"name": "get_holidays_by_year", "arguments": {"year": 2023, "country_code": "GB"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"predict_forest_area\", \"description\": \"Predicts the change in forest area over a specified number of years.\", \"parameters\": {\"location\": {\"description\": \"The geographic location for the prediction.\", \"type\": \"str\"}, \"num_years\": {\"description\": \"The number of years into the future to make the prediction.\", \"type\": \"int\"}, \"include_humans\": {\"description\": \"Whether to include the impact of human activities in the prediction. Defaults to False.\", \"type\": \"bool, optional\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_holidays_by_year\", \"description\": \"Retrieves the list of public holidays for a given year and country using the Nager.Date API.\", \"parameters\": {\"year\": {\"description\": \"The year for which to retrieve the holidays.\", \"type\": \"int\"}, \"country_code\": {\"description\": \"The two-letter ISO 3166-1 alpha-2 country code.\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"simulate_query_database\", \"description\": \"Simulates querying a database based on certain conditions.\", \"parameters\": {\"table\": {\"description\": \"Name of the table to query.\", \"type\": \"str\"}, \"conditions\": {\"description\": \"Conditions for the query, each condition is a dictionary.\", \"type\": \"list\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"project_investment_growth\", \"description\": \"Projects the growth of an investment over a specified number of years.\", \"parameters\": {\"principal\": {\"description\": \"The initial investment amount.\", \"type\": \"float\", \"default\": true}, \"annual_addition\": {\"description\": \"The amount added to the investment annually.\", \"type\": \"float\", \"default\": true}, \"years\": {\"description\": \"The number of years to project the investment growth.\", \"type\": \"int\"}, \"return_rate\": {\"description\": \"The annual return rate as a decimal (e.g., 0.07 for 7%).\", \"type\": \"float\"}, \"inflation\": {\"description\": \"A list of annual inflation rates as decimals.\", \"type\": \"List[float]\"}, \"inflation_adjusted\": {\"description\": \"Whether to adjust the final value for inflation. Defaults to True.\", \"type\": \"bool, optional\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_dna_sequence\", \"description\": \"Retrieves the DNA sequence for a given sequence ID from the NCBI Nucleotide database.\", \"parameters\": {\"sequence_id\": {\"description\": \"The unique identifier for the DNA sequence.\", \"type\": \"str\", \"default\": \"fasta\"}, \"file_format\": {\"description\": \"The format of the returned sequence. Allowed values: \\\"fasta\\\" (default) or \\\"gb\\\".\", \"type\": \"str, optional\"}, \"upstream_bases\": {\"description\": \"The number of bases upstream of the sequence to include. Defaults to 0.\", \"type\": \"int, optional\", \"default\": \"fasta\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"reserve_hotel_room\", \"description\": \"Reserves a hotel room with the specified details.\", \"parameters\": {\"room_type\": {\"description\": \"The type of room to reserve.\", \"type\": \"str\"}, \"nightly_rate\": {\"description\": \"The nightly rate for the room.\", \"type\": \"float\"}, \"checkin_date\": {\"description\": \"The check-in date in the format 'YYYY-MM-DD'.\", \"type\": \"str\"}, \"checkout_date\": {\"description\": \"The check-out date in the format 'YYYY-MM-DD'.\", \"type\": \"str\"}, \"guest_id\": {\"description\": \"The unique identifier for the guest.\", \"type\": \"str\"}, \"promo_code\": {\"description\": \"A promotional code for a discount. Defaults to None.\", \"type\": \"str, optional\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Predict the change in forest area in the Amazon for the next 10 years considering human impact. Also, retrieve the public holidays for the year 2023 in the UK.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"predict_forest_area\", \"arguments\": {\"location\": \"Amazon\", \"num_years\": 10, \"include_humans\": true}}, {\"name\": \"get_holidays_by_year\", \"arguments\": {\"year\": 2023, \"country_code\": \"GB\"}}]",
"style": "rule"
}
|
{
"index": 43,
"split": "train"
}
|
[{"name": "study_list_macquarie", "description": "Fetches kanji information based on a given list using the Kanjialive API.", "parameters": {"list": {"description": "A string representing the specific chapters of Kanji to be queried (e.g., \"12-22\").", "type": "str", "default": "mac:c12"}}}, {"name": "get_trivia_fact", "description": "Fetches a trivia fact about a given number from the Numbers API.", "parameters": {"number": {"description": "The number for which to retrieve the trivia fact.", "type": "str", "default": "42"}, "fragment": {"description": "Whether to return the fact as a sentence fragment. Defaults to 'True'.", "type": "str, optional", "default": true}, "notfound": {"description": "Determines the behavior when a fact is not found for the specified number. Options are 'default', 'floor', or 'ceil'. Defaults to 'floor'.", "type": "str, optional", "default": "floor"}, "json": {"description": "Whether to return the result as JSON. Defaults to 'True'.", "type": "str, optional", "default": true}}}]
|
[
{
"from": "human",
"value": "Retrieve a trivia fact about the number 42 as a sentence fragment from the Numbers API."
}
] |
[{"name": "get_trivia_fact", "arguments": {"number": "42", "fragment": "True"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"study_list_macquarie\", \"description\": \"Fetches kanji information based on a given list using the Kanjialive API.\", \"parameters\": {\"list\": {\"description\": \"A string representing the specific chapters of Kanji to be queried (e.g., \\\"12-22\\\").\", \"type\": \"str\", \"default\": \"mac:c12\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_trivia_fact\", \"description\": \"Fetches a trivia fact about a given number from the Numbers API.\", \"parameters\": {\"number\": {\"description\": \"The number for which to retrieve the trivia fact.\", \"type\": \"str\", \"default\": \"42\"}, \"fragment\": {\"description\": \"Whether to return the fact as a sentence fragment. Defaults to 'True'.\", \"type\": \"str, optional\", \"default\": true}, \"notfound\": {\"description\": \"Determines the behavior when a fact is not found for the specified number. Options are 'default', 'floor', or 'ceil'. Defaults to 'floor'.\", \"type\": \"str, optional\", \"default\": \"floor\"}, \"json\": {\"description\": \"Whether to return the result as JSON. Defaults to 'True'.\", \"type\": \"str, optional\", \"default\": true}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Retrieve a trivia fact about the number 42 as a sentence fragment from the Numbers API.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_trivia_fact\", \"arguments\": {\"number\": \"42\", \"fragment\": \"True\"}}]",
"style": "rule"
}
|
{
"index": 44,
"split": "train"
}
|
[{"name": "user_info", "description": "Retrieve TikTok user information by username using the Toolbench RapidAPI.", "parameters": {"username": {"description": "The TikTok username of the user whose information is to be retrieved.", "type": "str", "default": "therock"}}}, {"name": "channel_videos", "description": "Fetch the latest videos published by a YouTube channel using the provided RapidAPI key.", "parameters": {"channel_id": {"description": "The ID of the YouTube channel for which to fetch the latest videos.", "type": "str", "default": "UCg6gPGh8HU2U01vaFCAsvmQ"}}}]
|
[
{
"from": "human",
"value": "Get the TikTok user information for @alexander, @isabella, and @jack, as well as the latest videos from YouTube channels UCXpLkz8PWgS4w2Rz4hXNzJA and UCJkMlO-RhEijQcneB2cemqw."
}
] |
[{"name": "user_info", "arguments": {"username": "alexander"}}, {"name": "user_info", "arguments": {"username": "isabella"}}, {"name": "user_info", "arguments": {"username": "jack"}}, {"name": "channel_videos", "arguments": {"channel_id": "UCXpLkz8PWgS4w2Rz4hXNzJA"}}, {"name": "channel_videos", "arguments": {"channel_id": "UCJkMlO-RhEijQcneB2cemqw"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"user_info\", \"description\": \"Retrieve TikTok user information by username using the Toolbench RapidAPI.\", \"parameters\": {\"username\": {\"description\": \"The TikTok username of the user whose information is to be retrieved.\", \"type\": \"str\", \"default\": \"therock\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"channel_videos\", \"description\": \"Fetch the latest videos published by a YouTube channel using the provided RapidAPI key.\", \"parameters\": {\"channel_id\": {\"description\": \"The ID of the YouTube channel for which to fetch the latest videos.\", \"type\": \"str\", \"default\": \"UCg6gPGh8HU2U01vaFCAsvmQ\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Get the TikTok user information for @alexander, @isabella, and @jack, as well as the latest videos from YouTube channels UCXpLkz8PWgS4w2Rz4hXNzJA and UCJkMlO-RhEijQcneB2cemqw.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"user_info\", \"arguments\": {\"username\": \"alexander\"}}, {\"name\": \"user_info\", \"arguments\": {\"username\": \"isabella\"}}, {\"name\": \"user_info\", \"arguments\": {\"username\": \"jack\"}}, {\"name\": \"channel_videos\", \"arguments\": {\"channel_id\": \"UCXpLkz8PWgS4w2Rz4hXNzJA\"}}, {\"name\": \"channel_videos\", \"arguments\": {\"channel_id\": \"UCJkMlO-RhEijQcneB2cemqw\"}}]",
"style": "rule"
}
|
{
"index": 45,
"split": "train"
}
|
[{"name": "get_last_5_news", "description": "Fetches the last 5 news articles from the financial section.", "parameters": {"content_type": {"description": "The type of content to retrieve (e.g., 'application/json').", "type": "str", "default": "application/json"}}}, {"name": "exchange", "description": "Converts an amount of money from one currency to another using a currency conversion API.", "parameters": {"base": {"description": "The currency code to convert from (e.g., 'USD', 'EUR').", "type": "str", "default": "USD"}, "to": {"description": "The target currency code to convert to.", "type": "str", "default": "EUR"}, "int": {"description": "The amount of money to convert, default is '1'.", "type": "str, optional", "default": "1"}}}, {"name": "esg", "description": "Retrieves the Environmental, Social, and Governance (ESG) score for a given company symbol using the Yahoo Finance API.", "parameters": {"symb": {"description": "The stock symbol of the company for which the ESG score is requested.", "type": "str", "default": "tsla"}}}]
|
[
{
"from": "human",
"value": "Could you find the ESG score for Microsoft?"
}
] |
[{"name": "esg", "arguments": {"symb": "MSFT"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_last_5_news\", \"description\": \"Fetches the last 5 news articles from the financial section.\", \"parameters\": {\"content_type\": {\"description\": \"The type of content to retrieve (e.g., 'application/json').\", \"type\": \"str\", \"default\": \"application/json\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"exchange\", \"description\": \"Converts an amount of money from one currency to another using a currency conversion API.\", \"parameters\": {\"base\": {\"description\": \"The currency code to convert from (e.g., 'USD', 'EUR').\", \"type\": \"str\", \"default\": \"USD\"}, \"to\": {\"description\": \"The target currency code to convert to.\", \"type\": \"str\", \"default\": \"EUR\"}, \"int\": {\"description\": \"The amount of money to convert, default is '1'.\", \"type\": \"str, optional\", \"default\": \"1\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"esg\", \"description\": \"Retrieves the Environmental, Social, and Governance (ESG) score for a given company symbol using the Yahoo Finance API.\", \"parameters\": {\"symb\": {\"description\": \"The stock symbol of the company for which the ESG score is requested.\", \"type\": \"str\", \"default\": \"tsla\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Could you find the ESG score for Microsoft?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"esg\", \"arguments\": {\"symb\": \"MSFT\"}}]",
"style": "rule"
}
|
{
"index": 46,
"split": "train"
}
|
[{"name": "stock_cashflow_statement", "description": "Fetches the cash flow statement for a given stock symbol from Yahoo Finance using RapidAPI.", "parameters": {"symbol": {"description": "The stock symbol for which to fetch the cash flow statement.", "type": "str", "default": "AAPL"}}}]
|
[
{
"from": "human",
"value": "I need the cash flow data for Tesla and Google, please."
}
] |
[{"name": "stock_cashflow_statement", "arguments": {"symbol": "TSLA"}}, {"name": "stock_cashflow_statement", "arguments": {"symbol": "GOOGL"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"stock_cashflow_statement\", \"description\": \"Fetches the cash flow statement for a given stock symbol from Yahoo Finance using RapidAPI.\", \"parameters\": {\"symbol\": {\"description\": \"The stock symbol for which to fetch the cash flow statement.\", \"type\": \"str\", \"default\": \"AAPL\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I need the cash flow data for Tesla and Google, please.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"stock_cashflow_statement\", \"arguments\": {\"symbol\": \"TSLA\"}}, {\"name\": \"stock_cashflow_statement\", \"arguments\": {\"symbol\": \"GOOGL\"}}]",
"style": "rule"
}
|
{
"index": 47,
"split": "train"
}
|
[{"name": "calculate_angle", "description": "Calculates the angle between the hour and minute hands of a clock.", "parameters": {"hour": {"description": "The hour value (1-12).", "type": "int"}, "minute": {"description": "The minute value (0-59).", "type": "int"}}}, {"name": "sort_numbers", "description": "Sorts a list of numbers in ascending or descending order.", "parameters": {"numbers": {"description": "The list of numbers to be sorted.", "type": "List[float]"}, "descending": {"description": "If True, sorts the numbers in descending order. Defaults to False.", "type": "bool, optional"}}}, {"name": "find_pairs_with_sum", "description": "Finds all pairs of integers in a list that sum up to a target value.", "parameters": {"nums": {"description": "The list of integers.", "type": "List[int]"}, "target": {"description": "The target sum value.", "type": "int"}}}]
|
[
{
"from": "human",
"value": "Sort the following numbers [4.2, 1.5, 3.7, 2.1] in ascending order and then in descending order."
}
] |
[{"name": "sort_numbers", "arguments": {"numbers": [4.2, 1.5, 3.7, 2.1]}}, {"name": "sort_numbers", "arguments": {"numbers": [4.2, 1.5, 3.7, 2.1], "descending": true}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_angle\", \"description\": \"Calculates the angle between the hour and minute hands of a clock.\", \"parameters\": {\"hour\": {\"description\": \"The hour value (1-12).\", \"type\": \"int\"}, \"minute\": {\"description\": \"The minute value (0-59).\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"sort_numbers\", \"description\": \"Sorts a list of numbers in ascending or descending order.\", \"parameters\": {\"numbers\": {\"description\": \"The list of numbers to be sorted.\", \"type\": \"List[float]\"}, \"descending\": {\"description\": \"If True, sorts the numbers in descending order. Defaults to False.\", \"type\": \"bool, optional\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"find_pairs_with_sum\", \"description\": \"Finds all pairs of integers in a list that sum up to a target value.\", \"parameters\": {\"nums\": {\"description\": \"The list of integers.\", \"type\": \"List[int]\"}, \"target\": {\"description\": \"The target sum value.\", \"type\": \"int\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Sort the following numbers [4.2, 1.5, 3.7, 2.1] in ascending order and then in descending order.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"sort_numbers\", \"arguments\": {\"numbers\": [4.2, 1.5, 3.7, 2.1]}}, {\"name\": \"sort_numbers\", \"arguments\": {\"numbers\": [4.2, 1.5, 3.7, 2.1], \"descending\": true}}]",
"style": "rule"
}
|
{
"index": 48,
"split": "train"
}
|
[{"name": "rgb to hex", "description": "Converts RGB color codes to hex color codes", "parameters": {"type": "dict", "properties": {"r": {"description": "The red component of the RGB color code", "type": "float"}, "g": {"description": "The green component of the RGB color code", "type": "float"}, "b": {"description": "The blue component of the RGB color code", "type": "float"}}, "required": ["r", "g", "b"]}, "required": null}, {"name": "Generate QR Code", "description": "Generate a QR code based on the provided URL or text.", "parameters": {"type": "dict", "properties": {"url": {"description": "The URL or text to be encoded in the QR code.", "type": "string"}}, "required": ["url"]}, "required": null}, {"name": "Is Prime", "description": "Checks if a given number is prime or not", "parameters": {"type": "dict", "properties": {"number": {"description": "The number to check for primality", "type": "int"}}, "required": ["number"]}, "required": null}, {"name": "Data Analyst Jobs API", "description": "Retrieve data analyst job listings in the USA", "parameters": {"type": "dict", "properties": {"location": {"description": "Location for job search (e.g., city, state, or zip code)", "type": "string"}, "industry": {"description": "Industry for job search (e.g., finance, healthcare, technology)", "type": "string"}, "job_type": {"description": "Job type for search (e.g., full-time, part-time, internship)", "type": "string"}}, "required": ["location"]}, "required": null}]
|
[
{
"from": "human",
"value": "I need to convert the RGB color 102, 205, 170 to a hex code for my design project. Can you help?"
}
] |
[{"name": "rgb to hex", "arguments": {"r": 102, "g": 205, "b": 170}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out.
Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out.\nHere is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"rgb to hex\", \"description\": \"Converts RGB color codes to hex color codes\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"r\": {\"description\": \"The red component of the RGB color code\", \"type\": \"float\"}, \"g\": {\"description\": \"The green component of the RGB color code\", \"type\": \"float\"}, \"b\": {\"description\": \"The blue component of the RGB color code\", \"type\": \"float\"}}, \"required\": [\"r\", \"g\", \"b\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Generate QR Code\", \"description\": \"Generate a QR code based on the provided URL or text.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"url\": {\"description\": \"The URL or text to be encoded in the QR code.\", \"type\": \"string\"}}, \"required\": [\"url\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Is Prime\", \"description\": \"Checks if a given number is prime or not\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"number\": {\"description\": \"The number to check for primality\", \"type\": \"int\"}}, \"required\": [\"number\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Data Analyst Jobs API\", \"description\": \"Retrieve data analyst job listings in the USA\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"location\": {\"description\": \"Location for job search (e.g., city, state, or zip code)\", \"type\": \"string\"}, \"industry\": {\"description\": \"Industry for job search (e.g., finance, healthcare, technology)\", \"type\": \"string\"}, \"job_type\": {\"description\": \"Job type for search (e.g., full-time, part-time, internship)\", \"type\": \"string\"}}, \"required\": [\"location\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I need to convert the RGB color 102, 205, 170 to a hex code for my design project. Can you help?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"rgb to hex\", \"arguments\": {\"r\": 102, \"g\": 205, \"b\": 170}}]",
"style": "rule"
}
|
{
"index": 49,
"split": "train"
}
|
[{"name": "is_valid_parentheses", "description": "Checks if a string contains valid parentheses.", "parameters": {"s": {"description": "The input string.", "type": "str"}}}]
|
[
{
"from": "human",
"value": "Is the arithmetic expression '(1 + (2 * 3)) / 4' valid?"
}
] |
[{"name": "is_valid_parentheses", "arguments": {"s": "(1 + (2 * 3)) / 4"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"is_valid_parentheses\", \"description\": \"Checks if a string contains valid parentheses.\", \"parameters\": {\"s\": {\"description\": \"The input string.\", \"type\": \"str\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Is the arithmetic expression '(1 + (2 * 3)) / 4' valid?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"is_valid_parentheses\", \"arguments\": {\"s\": \"(1 + (2 * 3)) / 4\"}}]",
"style": "rule"
}
|
{
"index": 50,
"split": "train"
}
|
[{"name": "calculate_standard_deviation", "description": "Calculates the standard deviation of a list of numbers.", "parameters": {"numbers": {"description": "The list of numbers.", "type": "List[Union[int, float]]"}}}]
|
[
{
"from": "human",
"value": "Calculate the standard deviation of a list containing the numbers 10, 20, 30, 40, 50."
}
] |
[{"name": "calculate_standard_deviation", "arguments": {"numbers": [10, 20, 30, 40, 50]}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_standard_deviation\", \"description\": \"Calculates the standard deviation of a list of numbers.\", \"parameters\": {\"numbers\": {\"description\": \"The list of numbers.\", \"type\": \"List[Union[int, float]]\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Calculate the standard deviation of a list containing the numbers 10, 20, 30, 40, 50.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"calculate_standard_deviation\", \"arguments\": {\"numbers\": [10, 20, 30, 40, 50]}}]",
"style": "rule"
}
|
{
"index": 51,
"split": "train"
}
|
[{"name": "Reverse Geocoding API", "description": "This API performs reverse geocoding, converting a coordinate or location (latitude, longitude) to a readable address or place name.", "parameters": {"type": "dict", "properties": {"normalizecity": {"description": "Normalizes village to city level data to city", "type": "float", "default": 1}, "lat": {"description": "Latitude of the location to generate an address for.", "type": "float", "default": 40.7487727}, "format": {"description": "Format to geocode. Only JSON supported for SDKs", "type": "string", "default": "json"}, "lon": {"description": "Longitude of the location to generate an address for.", "type": "float", "default": -73.9849336}}, "required": ["normalizecity", "lat", "format", "lon"]}, "required": null}, {"name": "Query for City Boundary by City Name", "description": "Retrieve the boundary information of a city based on its name.", "parameters": {"type": "dict", "properties": {"name": {"description": "The name of the city to retrieve boundary information for.", "type": "string"}}, "required": ["name"]}, "required": null}, {"name": "getCountryList", "description": "This API returns a list of all countries, including their ISO code, ISO3 code, and phone code.", "parameters": {"type": "dict", "properties": {}, "required": []}, "required": null}, {"name": "Zip Code Information", "description": "Retrieves detailed information about a specific zip code in Mexico, including its location, city, state, and other relevant details.", "parameters": {"type": "dict", "properties": {"zip_code": {"description": "A valid zip code in Mexico", "type": "string"}}, "required": ["zip_code"]}, "required": null}, {"name": "GetLargestCities", "description": "Returns the 5 largest cities within a given radial range with name, population, country, and distance from a specified location.", "parameters": {"type": "dict", "properties": {"latitude": {"description": "Latitude in decimal degrees (WGS84)", "type": "float"}, "longitude": {"description": "Longitude in decimal degrees (WGS84)", "type": "float"}, "range": {"description": "Radial lookup range in meters (max 100,000)", "type": "float"}}, "required": ["latitude", "longitude", "range"]}, "required": null}]
|
[
{
"from": "human",
"value": "Role definition:\n Inquirer: A user who raises an inquiry.\n Response assistant: Communicates with the inquirer and provides answers and solutions.\n\n Historical dialog data is as follows:\nInquirer: Can you help me find out where exactly I am currently?\nResponse assistant: Could you please provide your current location's latitude and longitude?\nInquirer: My current coordinates are 40.7487727, -73.9849336.\n\n Please continue your answer given the historical dialog. Your role is the Response assistant."
}
] |
[{"name": "Reverse Geocoding API", "arguments": {"normalizecity": 1, "lat": 40.7487727, "format": "json", "lon": -73.9849336}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out.
Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out.\nHere is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"Reverse Geocoding API\", \"description\": \"This API performs reverse geocoding, converting a coordinate or location (latitude, longitude) to a readable address or place name.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"normalizecity\": {\"description\": \"Normalizes village to city level data to city\", \"type\": \"float\", \"default\": 1}, \"lat\": {\"description\": \"Latitude of the location to generate an address for.\", \"type\": \"float\", \"default\": 40.7487727}, \"format\": {\"description\": \"Format to geocode. Only JSON supported for SDKs\", \"type\": \"string\", \"default\": \"json\"}, \"lon\": {\"description\": \"Longitude of the location to generate an address for.\", \"type\": \"float\", \"default\": -73.9849336}}, \"required\": [\"normalizecity\", \"lat\", \"format\", \"lon\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Query for City Boundary by City Name\", \"description\": \"Retrieve the boundary information of a city based on its name.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"name\": {\"description\": \"The name of the city to retrieve boundary information for.\", \"type\": \"string\"}}, \"required\": [\"name\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"getCountryList\", \"description\": \"This API returns a list of all countries, including their ISO code, ISO3 code, and phone code.\", \"parameters\": {\"type\": \"dict\", \"properties\": {}, \"required\": []}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Zip Code Information\", \"description\": \"Retrieves detailed information about a specific zip code in Mexico, including its location, city, state, and other relevant details.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"zip_code\": {\"description\": \"A valid zip code in Mexico\", \"type\": \"string\"}}, \"required\": [\"zip_code\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"GetLargestCities\", \"description\": \"Returns the 5 largest cities within a given radial range with name, population, country, and distance from a specified location.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"latitude\": {\"description\": \"Latitude in decimal degrees (WGS84)\", \"type\": \"float\"}, \"longitude\": {\"description\": \"Longitude in decimal degrees (WGS84)\", \"type\": \"float\"}, \"range\": {\"description\": \"Radial lookup range in meters (max 100,000)\", \"type\": \"float\"}}, \"required\": [\"latitude\", \"longitude\", \"range\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Role definition:\n Inquirer: A user who raises an inquiry.\n Response assistant: Communicates with the inquirer and provides answers and solutions.\n\n Historical dialog data is as follows:\nInquirer: Can you help me find out where exactly I am currently?\nResponse assistant: Could you please provide your current location's latitude and longitude?\nInquirer: My current coordinates are 40.7487727, -73.9849336.\n\n Please continue your answer given the historical dialog. Your role is the Response assistant.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"Reverse Geocoding API\", \"arguments\": {\"normalizecity\": 1, \"lat\": 40.7487727, \"format\": \"json\", \"lon\": -73.9849336}}]",
"style": "rule"
}
|
{
"index": 52,
"split": "train"
}
|
[{"name": "list_all_bot_category_groups", "description": "Get a list of category groups that are linked to user-owned bots (not locked bots).", "parameters": {"category_group": {"description": "Category group slug of the category group in the bot category group.", "type": "str, optional", "default": ""}, "dir": {"description": "Direction of the ordering. Default is 'asc'.", "type": "str, optional", "default": "asc"}, "limit": {"description": "The number of records to return. Default is 20.", "type": "int, optional", "default": 20}, "order": {"description": "The search field to order by. Default is 'id'.", "type": "str, optional", "default": "id"}, "is_id": {"description": "The ID of the bot category group.", "type": "int, optional", "default": ""}, "bot": {"description": "Bot slug of the bot in the bot category group.", "type": "str, optional", "default": ""}, "category_group_id": {"description": "The ID of the category group.", "type": "int, optional", "default": ""}, "bot_id": {"description": "The ID of the bot category group.", "type": "int, optional", "default": ""}, "page": {"description": "The page number of results to start from. Default is 1.", "type": "int, optional", "default": 1}}}, {"name": "get_models", "description": "Retrieves a list of models from the specified API endpoint.", "parameters": {"type": {"description": "The type of models to retrieve. Defaults to 'checkpoint'.", "type": "str", "default": "checkpoint"}}}]
|
[
{
"from": "human",
"value": "List all bot category groups with an ID of 500, and also provide a list of all model types available from the API."
}
] |
[{"name": "list_all_bot_category_groups", "arguments": {"is_id": 500}}, {"name": "get_models", "arguments": {}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"list_all_bot_category_groups\", \"description\": \"Get a list of category groups that are linked to user-owned bots (not locked bots).\", \"parameters\": {\"category_group\": {\"description\": \"Category group slug of the category group in the bot category group.\", \"type\": \"str, optional\", \"default\": \"\"}, \"dir\": {\"description\": \"Direction of the ordering. Default is 'asc'.\", \"type\": \"str, optional\", \"default\": \"asc\"}, \"limit\": {\"description\": \"The number of records to return. Default is 20.\", \"type\": \"int, optional\", \"default\": 20}, \"order\": {\"description\": \"The search field to order by. Default is 'id'.\", \"type\": \"str, optional\", \"default\": \"id\"}, \"is_id\": {\"description\": \"The ID of the bot category group.\", \"type\": \"int, optional\", \"default\": \"\"}, \"bot\": {\"description\": \"Bot slug of the bot in the bot category group.\", \"type\": \"str, optional\", \"default\": \"\"}, \"category_group_id\": {\"description\": \"The ID of the category group.\", \"type\": \"int, optional\", \"default\": \"\"}, \"bot_id\": {\"description\": \"The ID of the bot category group.\", \"type\": \"int, optional\", \"default\": \"\"}, \"page\": {\"description\": \"The page number of results to start from. Default is 1.\", \"type\": \"int, optional\", \"default\": 1}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_models\", \"description\": \"Retrieves a list of models from the specified API endpoint.\", \"parameters\": {\"type\": {\"description\": \"The type of models to retrieve. Defaults to 'checkpoint'.\", \"type\": \"str\", \"default\": \"checkpoint\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "List all bot category groups with an ID of 500, and also provide a list of all model types available from the API.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"list_all_bot_category_groups\", \"arguments\": {\"is_id\": 500}}, {\"name\": \"get_models\", \"arguments\": {}}]",
"style": "rule"
}
|
{
"index": 53,
"split": "train"
}
|
[{"name": "image_search", "description": "Searches for images using the specified query parameters and returns the results.", "parameters": {"q": {"description": "The search query.", "type": "str", "default": "Word Cup"}, "start": {"description": "The index of the first result to return. Defaults to '0'.", "type": "str", "default": "0"}, "num": {"description": "The number of search results to return. Valid values are integers between 1 and 20, inclusive. Defaults to 10.", "type": "int", "default": "10"}, "gl": {"description": "A two-letter country code to boost search results from that country. Defaults to 'us'.", "type": "str", "default": "us"}, "lr": {"description": "Restricts the search to documents written in a particular language. Defaults to 'lang_en'.", "type": "str", "default": "lang_en"}}}, {"name": "autocomplete", "description": "This function sends a request to the Place Autocomplete API to get place suggestions based on the input text and specified radius.", "parameters": {"radius": {"description": "The radius within which to search for place suggestions.", "type": "str", "default": "500"}, "input": {"description": "The input text for which to find place matches.", "type": "str", "default": "new"}}}]
|
[
{
"from": "human",
"value": "Find images of the Eiffel Tower in Paris, France."
}
] |
[{"name": "image_search", "arguments": {"q": "Eiffel Tower", "gl": "fr"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"image_search\", \"description\": \"Searches for images using the specified query parameters and returns the results.\", \"parameters\": {\"q\": {\"description\": \"The search query.\", \"type\": \"str\", \"default\": \"Word Cup\"}, \"start\": {\"description\": \"The index of the first result to return. Defaults to '0'.\", \"type\": \"str\", \"default\": \"0\"}, \"num\": {\"description\": \"The number of search results to return. Valid values are integers between 1 and 20, inclusive. Defaults to 10.\", \"type\": \"int\", \"default\": \"10\"}, \"gl\": {\"description\": \"A two-letter country code to boost search results from that country. Defaults to 'us'.\", \"type\": \"str\", \"default\": \"us\"}, \"lr\": {\"description\": \"Restricts the search to documents written in a particular language. Defaults to 'lang_en'.\", \"type\": \"str\", \"default\": \"lang_en\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"autocomplete\", \"description\": \"This function sends a request to the Place Autocomplete API to get place suggestions based on the input text and specified radius.\", \"parameters\": {\"radius\": {\"description\": \"The radius within which to search for place suggestions.\", \"type\": \"str\", \"default\": \"500\"}, \"input\": {\"description\": \"The input text for which to find place matches.\", \"type\": \"str\", \"default\": \"new\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Find images of the Eiffel Tower in Paris, France.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"image_search\", \"arguments\": {\"q\": \"Eiffel Tower\", \"gl\": \"fr\"}}]",
"style": "rule"
}
|
{
"index": 54,
"split": "train"
}
|
[{"name": "find_pairs_with_sum", "description": "Finds all pairs of integers in a list that sum up to a target value.", "parameters": {"nums": {"description": "The list of integers.", "type": "List[int]"}, "target": {"description": "The target sum value.", "type": "int"}}}, {"name": "numerical_derivative", "description": "Estimates the derivative of a function at a given point using the central difference formula.", "parameters": {"function": {"description": "The function to calculate the derivative of.", "type": "Callable[[float], float]"}, "x": {"description": "The point at which to estimate the derivative.", "type": "float"}}}, {"name": "can_attend_all_meetings", "description": "Determines if a person can attend all meetings given a list of meeting time intervals.", "parameters": {"intervals": {"description": "A list of meeting time intervals, where each interval is represented as [start_time, end_time].", "type": "List[List[int]]"}}}, {"name": "draw_cards", "description": "Shuffles a standard deck of 52 cards and draws a specified number of cards from the top.", "parameters": {"num_draw": {"description": "The number of cards to be drawn. Defaults to 1.", "type": "int, optional", "default": 1}}}, {"name": "fibonacci_numbers", "description": "Generates the first n Fibonacci numbers.", "parameters": {"n": {"description": "The number of Fibonacci numbers to generate.", "type": "int"}}}, {"name": "cell_density", "description": "Calculates the cell density based on the optical density (OD) and dilution factor.", "parameters": {"od": {"description": "The optical density of the sample.", "type": "float", "default": 1000000000.0}, "dilution": {"description": "The dilution factor applied to the sample.", "type": "int", "default": 1000000000.0}, "factor": {"description": "The calibration factor for converting OD to cell density. Defaults to 1e9.", "type": "float, optional"}}}, {"name": "create_histogram", "description": "Create a histogram based on provided data.", "parameters": {"data": {"description": "The data for which histogram needs to be plotted.", "type": "list", "default": 10}, "bins": {"description": "The number of equal-width bins in the range. Default is 10.", "type": "int", "default": 10}}}, {"name": "find_next_greater_element", "description": "Finds the next greater element for each element in a list.", "parameters": {"nums": {"description": "The list of numbers.", "type": "List[int]"}}}]
|
[
{
"from": "human",
"value": "Determine if a person can attend all meetings with time intervals [[1, 3], [2, 4], [5, 6]] and calculate the numerical derivative of the function f(x) = x^2 at x = 3."
}
] |
[{"name": "can_attend_all_meetings", "arguments": {"intervals": [[1, 3], [2, 4], [5, 6]]}}, {"name": "numerical_derivative", "arguments": {"function": "lambda x: x ** 2", "x": 3}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"find_pairs_with_sum\", \"description\": \"Finds all pairs of integers in a list that sum up to a target value.\", \"parameters\": {\"nums\": {\"description\": \"The list of integers.\", \"type\": \"List[int]\"}, \"target\": {\"description\": \"The target sum value.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"numerical_derivative\", \"description\": \"Estimates the derivative of a function at a given point using the central difference formula.\", \"parameters\": {\"function\": {\"description\": \"The function to calculate the derivative of.\", \"type\": \"Callable[[float], float]\"}, \"x\": {\"description\": \"The point at which to estimate the derivative.\", \"type\": \"float\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"can_attend_all_meetings\", \"description\": \"Determines if a person can attend all meetings given a list of meeting time intervals.\", \"parameters\": {\"intervals\": {\"description\": \"A list of meeting time intervals, where each interval is represented as [start_time, end_time].\", \"type\": \"List[List[int]]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"draw_cards\", \"description\": \"Shuffles a standard deck of 52 cards and draws a specified number of cards from the top.\", \"parameters\": {\"num_draw\": {\"description\": \"The number of cards to be drawn. Defaults to 1.\", \"type\": \"int, optional\", \"default\": 1}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"fibonacci_numbers\", \"description\": \"Generates the first n Fibonacci numbers.\", \"parameters\": {\"n\": {\"description\": \"The number of Fibonacci numbers to generate.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"cell_density\", \"description\": \"Calculates the cell density based on the optical density (OD) and dilution factor.\", \"parameters\": {\"od\": {\"description\": \"The optical density of the sample.\", \"type\": \"float\", \"default\": 1000000000.0}, \"dilution\": {\"description\": \"The dilution factor applied to the sample.\", \"type\": \"int\", \"default\": 1000000000.0}, \"factor\": {\"description\": \"The calibration factor for converting OD to cell density. Defaults to 1e9.\", \"type\": \"float, optional\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"create_histogram\", \"description\": \"Create a histogram based on provided data.\", \"parameters\": {\"data\": {\"description\": \"The data for which histogram needs to be plotted.\", \"type\": \"list\", \"default\": 10}, \"bins\": {\"description\": \"The number of equal-width bins in the range. Default is 10.\", \"type\": \"int\", \"default\": 10}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"find_next_greater_element\", \"description\": \"Finds the next greater element for each element in a list.\", \"parameters\": {\"nums\": {\"description\": \"The list of numbers.\", \"type\": \"List[int]\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Determine if a person can attend all meetings with time intervals [[1, 3], [2, 4], [5, 6]] and calculate the numerical derivative of the function f(x) = x^2 at x = 3.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"can_attend_all_meetings\", \"arguments\": {\"intervals\": [[1, 3], [2, 4], [5, 6]]}}, {\"name\": \"numerical_derivative\", \"arguments\": {\"function\": \"lambda x: x ** 2\", \"x\": 3}}]",
"style": "rule"
}
|
{
"index": 55,
"split": "train"
}
|
[{"name": "whole_foods_order", "description": "Places an order at Whole Foods.", "parameters": {"store_location": {"description": "The location of the Whole Foods store.", "type": "str"}, "item_list": {"description": "A list of items to order.", "type": "list"}, "order_size": {"description": "The size of the order. Allowed values: \"small\", \"medium\", or \"large\".", "type": "str"}}}, {"name": "simulate_query_database", "description": "Simulates querying a database based on certain conditions.", "parameters": {"table": {"description": "Name of the table to query.", "type": "str"}, "conditions": {"description": "Conditions for the query, each condition is a dictionary.", "type": "list"}}}, {"name": "calculate_calorie_intake", "description": "Calculates the recommended daily calorie intake and macronutrient distribution based on personal characteristics and goals.", "parameters": {"weight_kg": {"description": "Body weight in kilograms.", "type": "float"}, "height_cm": {"description": "Height in centimeters.", "type": "float"}, "age": {"description": "Age in years.", "type": "int"}, "sex": {"description": "Biological sex, either 'male' or 'female'.", "type": "str"}, "activity_level": {"description": "Activity level on a scale of 1 to 5 (1 = sedentary, 5 = extremely active).", "type": "int"}, "goal": {"description": "Fitness goal, either 'lose', 'maintain', or 'gain'.", "type": "str"}}}]
|
[
{
"from": "human",
"value": "What is the recommended daily calorie intake for a 25-year-old female, weighing 60kg, 165cm tall, with a highly active lifestyle and a goal to maintain weight?"
}
] |
[{"name": "calculate_calorie_intake", "arguments": {"weight_kg": 60, "height_cm": 165, "age": 25, "sex": "female", "activity_level": 5, "goal": "maintain"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"whole_foods_order\", \"description\": \"Places an order at Whole Foods.\", \"parameters\": {\"store_location\": {\"description\": \"The location of the Whole Foods store.\", \"type\": \"str\"}, \"item_list\": {\"description\": \"A list of items to order.\", \"type\": \"list\"}, \"order_size\": {\"description\": \"The size of the order. Allowed values: \\\"small\\\", \\\"medium\\\", or \\\"large\\\".\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"simulate_query_database\", \"description\": \"Simulates querying a database based on certain conditions.\", \"parameters\": {\"table\": {\"description\": \"Name of the table to query.\", \"type\": \"str\"}, \"conditions\": {\"description\": \"Conditions for the query, each condition is a dictionary.\", \"type\": \"list\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_calorie_intake\", \"description\": \"Calculates the recommended daily calorie intake and macronutrient distribution based on personal characteristics and goals.\", \"parameters\": {\"weight_kg\": {\"description\": \"Body weight in kilograms.\", \"type\": \"float\"}, \"height_cm\": {\"description\": \"Height in centimeters.\", \"type\": \"float\"}, \"age\": {\"description\": \"Age in years.\", \"type\": \"int\"}, \"sex\": {\"description\": \"Biological sex, either 'male' or 'female'.\", \"type\": \"str\"}, \"activity_level\": {\"description\": \"Activity level on a scale of 1 to 5 (1 = sedentary, 5 = extremely active).\", \"type\": \"int\"}, \"goal\": {\"description\": \"Fitness goal, either 'lose', 'maintain', or 'gain'.\", \"type\": \"str\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the recommended daily calorie intake for a 25-year-old female, weighing 60kg, 165cm tall, with a highly active lifestyle and a goal to maintain weight?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"calculate_calorie_intake\", \"arguments\": {\"weight_kg\": 60, \"height_cm\": 165, \"age\": 25, \"sex\": \"female\", \"activity_level\": 5, \"goal\": \"maintain\"}}]",
"style": "rule"
}
|
{
"index": 56,
"split": "train"
}
|
[{"name": "contacts", "description": "Fetches the contacts list from a specified WhatsApp instance using the Maytapi API.", "parameters": {"phone_id": {"description": "The unique identifier for the phone instance in the Maytapi WhatsApp service.", "type": "str", "default": ""}}}, {"name": "get_an_answer", "description": "Fetches an answer based on the given query parameters from a specific API endpoint.", "parameters": {"page": {"description": "The page number to fetch. Default is '1'.", "type": "str, optional", "default": "1"}, "limit": {"description": "The number of items per page. Default is '10'.", "type": "str, optional", "default": "10"}, "status": {"description": "The status of the dialogue (e.g., 'approved' or 'analyzing'). Default is 'approved'.", "type": "str, optional", "default": "approved"}, "answer": {"description": "The pre-defined response for the initial speech of the dialogue. Default is 'Hi, how are you?'.", "type": "str, optional", "default": "Hi, how are you?"}, "is_id": {"description": "The unique identifier of the dialogue. Default is '5ec47b3d8958430d6a6d5898'.", "type": "str, optional", "default": "5ec47b3d8958430d6a6d5898"}, "speech": {"description": "The initial speech input for which an answer is sought. Default is 'Hi'.", "type": "str, optional", "default": "Hi"}, "user": {"description": "The unique identifier of the user who created the dialogue. Default is '5ec479048958430d6a6d5895'.", "type": "str, optional", "default": "5ec479048958430d6a6d5895"}}}]
|
[
{
"from": "human",
"value": "Fetch contacts from a WhatsApp instance with phone ID '9876543210' and retrieve the second page of answers from the English Talking API with a limit of 15 items."
}
] |
[{"name": "contacts", "arguments": {"phone_id": "9876543210"}}, {"name": "get_an_answer", "arguments": {"page": "2", "limit": "15"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"contacts\", \"description\": \"Fetches the contacts list from a specified WhatsApp instance using the Maytapi API.\", \"parameters\": {\"phone_id\": {\"description\": \"The unique identifier for the phone instance in the Maytapi WhatsApp service.\", \"type\": \"str\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_an_answer\", \"description\": \"Fetches an answer based on the given query parameters from a specific API endpoint.\", \"parameters\": {\"page\": {\"description\": \"The page number to fetch. Default is '1'.\", \"type\": \"str, optional\", \"default\": \"1\"}, \"limit\": {\"description\": \"The number of items per page. Default is '10'.\", \"type\": \"str, optional\", \"default\": \"10\"}, \"status\": {\"description\": \"The status of the dialogue (e.g., 'approved' or 'analyzing'). Default is 'approved'.\", \"type\": \"str, optional\", \"default\": \"approved\"}, \"answer\": {\"description\": \"The pre-defined response for the initial speech of the dialogue. Default is 'Hi, how are you?'.\", \"type\": \"str, optional\", \"default\": \"Hi, how are you?\"}, \"is_id\": {\"description\": \"The unique identifier of the dialogue. Default is '5ec47b3d8958430d6a6d5898'.\", \"type\": \"str, optional\", \"default\": \"5ec47b3d8958430d6a6d5898\"}, \"speech\": {\"description\": \"The initial speech input for which an answer is sought. Default is 'Hi'.\", \"type\": \"str, optional\", \"default\": \"Hi\"}, \"user\": {\"description\": \"The unique identifier of the user who created the dialogue. Default is '5ec479048958430d6a6d5895'.\", \"type\": \"str, optional\", \"default\": \"5ec479048958430d6a6d5895\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch contacts from a WhatsApp instance with phone ID '9876543210' and retrieve the second page of answers from the English Talking API with a limit of 15 items.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"contacts\", \"arguments\": {\"phone_id\": \"9876543210\"}}, {\"name\": \"get_an_answer\", \"arguments\": {\"page\": \"2\", \"limit\": \"15\"}}]",
"style": "rule"
}
|
{
"index": 57,
"split": "train"
}
|
[{"name": "Get Channel Videos", "description": "Returns a list of videos from a specified Twitch channel.", "parameters": {"type": "dict", "properties": {"channel": {"description": "The name of the Twitch channel to retrieve videos from.", "type": "string"}}, "required": ["channel"]}, "required": null}, {"name": "Collection", "description": "Retrieves a collection of artworks from the Rijksmuseum website, with optional filtering by search terms and language.", "parameters": {"type": "dict", "properties": {"q": {"description": "The search terms that need to occur in one of the fields of the artwork data", "type": "string"}, "culture": {"description": "The language to search in (and of the results)", "type": "string", "default": ""}}, "required": ["q"]}, "required": null}, {"name": "Get Random Colors", "description": "Returns an array of objects containing information about random colors from the sRGB color space. The color-object contains the color codes in RGB, CMYK, HEX, HSL, and HSV (HSB). In addition, the property \"safe\" specifies whether the color is [web-safe](https://en.wikipedia.org/wiki/Web_colors#Web-safe_colors) or not. If the color has a name that can be used in CSS, the name(s) will also be included. The nearest color(s) will also be included.", "parameters": {"type": "dict", "properties": {"quantity": {"description": "The number of colors to return. Max is 50. If no quantity is specified, returns only one color-object. Any quantities above 50 will default to 50.", "type": "int"}}, "required": ["quantity"]}, "required": null}]
|
[
{
"from": "human",
"value": "Can you fetch the recent videos for my favorite Twitch channel 'Ninja'? I would love to catch up with his game streams."
}
] |
[{"name": "Get Channel Videos", "arguments": {"channel": "Ninja"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out.
Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out.\nHere is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"Get Channel Videos\", \"description\": \"Returns a list of videos from a specified Twitch channel.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"channel\": {\"description\": \"The name of the Twitch channel to retrieve videos from.\", \"type\": \"string\"}}, \"required\": [\"channel\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Collection\", \"description\": \"Retrieves a collection of artworks from the Rijksmuseum website, with optional filtering by search terms and language.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"q\": {\"description\": \"The search terms that need to occur in one of the fields of the artwork data\", \"type\": \"string\"}, \"culture\": {\"description\": \"The language to search in (and of the results)\", \"type\": \"string\", \"default\": \"\"}}, \"required\": [\"q\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Get Random Colors\", \"description\": \"Returns an array of objects containing information about random colors from the sRGB color space. The color-object contains the color codes in RGB, CMYK, HEX, HSL, and HSV (HSB). In addition, the property \\\"safe\\\" specifies whether the color is [web-safe](https://en.wikipedia.org/wiki/Web_colors#Web-safe_colors) or not. If the color has a name that can be used in CSS, the name(s) will also be included. The nearest color(s) will also be included.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"quantity\": {\"description\": \"The number of colors to return. Max is 50. If no quantity is specified, returns only one color-object. Any quantities above 50 will default to 50.\", \"type\": \"int\"}}, \"required\": [\"quantity\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Can you fetch the recent videos for my favorite Twitch channel 'Ninja'? I would love to catch up with his game streams.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"Get Channel Videos\", \"arguments\": {\"channel\": \"Ninja\"}}]",
"style": "rule"
}
|
{
"index": 58,
"split": "train"
}
|
[{"name": "weather_dataset", "description": "Fetches weather data from the Weather Dataset API using provided parameters.", "parameters": {"data": {"description": "The specific weather data to query from the API. Defaults to '1'.", "type": "str", "default": "1"}}}, {"name": "time", "description": "Retrieves the current time token from the PubNub Network.", "parameters": {"callback": {"description": "JSONP callback function name.", "type": "str", "default": "0"}}}, {"name": "message_send", "description": "Sends an SMS message using the SensSMS API.", "parameters": {"password": {"description": "Your SensSMS API key.", "type": "str", "default": ""}, "to": {"description": "Destination phone number.", "type": "int", "default": ""}, "text": {"description": "Content of the SMS message.", "type": "str", "default": ""}, "action": {"description": "The action type for the API call.", "type": "str", "default": "message_send"}, "username": {"description": "Your SensSMS username.", "type": "str", "default": ""}, "is_from": {"description": "The sender of the message. Defaults to None.", "type": "str, optional", "default": ""}, "report_mask": {"description": "The report mask for SMS status updates. Defaults to 19.", "type": "int, optional", "default": "19"}, "report_url": {"description": "URL for receiving SMS status reports. Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "regions", "description": "Returns a collection of supported regions for the specified IETF BCP 47 language tag.", "parameters": {"language": {"description": "Language code in BCP 47 format.", "type": "str", "default": "us"}}}, {"name": "queue", "description": "Retrieve the queue information of a phone using the specified phone ID.", "parameters": {"phone_id": {"description": "The ID of the phone for which queue information is to be retrieved.", "type": "str", "default": ""}}}]
|
[
{
"from": "human",
"value": "Fetch the weather data for location '2' using the weather dataset API. Also, retrieve the current time token from the PubNub Network using a callback function named 'cb2'."
}
] |
[{"name": "weather_dataset", "arguments": {"data": "2"}}, {"name": "time", "arguments": {"callback": "cb2"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"weather_dataset\", \"description\": \"Fetches weather data from the Weather Dataset API using provided parameters.\", \"parameters\": {\"data\": {\"description\": \"The specific weather data to query from the API. Defaults to '1'.\", \"type\": \"str\", \"default\": \"1\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"time\", \"description\": \"Retrieves the current time token from the PubNub Network.\", \"parameters\": {\"callback\": {\"description\": \"JSONP callback function name.\", \"type\": \"str\", \"default\": \"0\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"message_send\", \"description\": \"Sends an SMS message using the SensSMS API.\", \"parameters\": {\"password\": {\"description\": \"Your SensSMS API key.\", \"type\": \"str\", \"default\": \"\"}, \"to\": {\"description\": \"Destination phone number.\", \"type\": \"int\", \"default\": \"\"}, \"text\": {\"description\": \"Content of the SMS message.\", \"type\": \"str\", \"default\": \"\"}, \"action\": {\"description\": \"The action type for the API call.\", \"type\": \"str\", \"default\": \"message_send\"}, \"username\": {\"description\": \"Your SensSMS username.\", \"type\": \"str\", \"default\": \"\"}, \"is_from\": {\"description\": \"The sender of the message. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}, \"report_mask\": {\"description\": \"The report mask for SMS status updates. Defaults to 19.\", \"type\": \"int, optional\", \"default\": \"19\"}, \"report_url\": {\"description\": \"URL for receiving SMS status reports. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"regions\", \"description\": \"Returns a collection of supported regions for the specified IETF BCP 47 language tag.\", \"parameters\": {\"language\": {\"description\": \"Language code in BCP 47 format.\", \"type\": \"str\", \"default\": \"us\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"queue\", \"description\": \"Retrieve the queue information of a phone using the specified phone ID.\", \"parameters\": {\"phone_id\": {\"description\": \"The ID of the phone for which queue information is to be retrieved.\", \"type\": \"str\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch the weather data for location '2' using the weather dataset API. Also, retrieve the current time token from the PubNub Network using a callback function named 'cb2'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"weather_dataset\", \"arguments\": {\"data\": \"2\"}}, {\"name\": \"time\", \"arguments\": {\"callback\": \"cb2\"}}]",
"style": "rule"
}
|
{
"index": 59,
"split": "train"
}
|
[{"name": "get_manga_by_id", "description": "Fetches Manga information by its ID from the Anime, Manga, and Novels API.", "parameters": {"is_id": {"description": "The ID of the Manga to fetch information for.", "type": "int", "default": "3674"}}}, {"name": "get_by_trakt_tv_id", "description": "Fetches movie or TV show information from the RapidAPI MDB List service based on a given Trakt.tv ID.", "parameters": {"t": {"description": "A valid Trakt.tv ID representing the movie or TV show.", "type": "str", "default": "457"}, "m": {"description": "The media type, either 'movie' or 'show'. Defaults to 'movie' if not specified.", "type": "str, optional", "default": ""}}}, {"name": "songs", "description": "Fetches a list of songs from JSR/JSRF using the specified parameters.", "parameters": {"limit": {"description": "The maximum number of items to return in the response. Default is '5'.", "type": "str", "default": "5"}, "sortby": {"description": "The field by which to sort the results. Possible values include fields on the document, e.g., 'name', 'stats'. Default is 'name'.", "type": "str", "default": "name"}, "orderby": {"description": "The order in which to sort the results. Possible values are 'asc' for ascending and 'desc' for descending. The `sortby` parameter must be present for this to take effect. Default is 'asc'.", "type": "str", "default": "asc"}}}, {"name": "query_joke_using_id", "description": "Fetches an anime joke using the provided joke ID from the RapidAPI service.", "parameters": {"is_id": {"description": "The ID of the joke to be fetched.", "type": "int", "default": "4"}}}]
|
[
{
"from": "human",
"value": "What is the TV show with Trakt.tv ID 'tt98765' and the joke with ID 12345?"
}
] |
[{"name": "get_by_trakt_tv_id", "arguments": {"t": "tt98765", "m": "show"}}, {"name": "query_joke_using_id", "arguments": {"is_id": 12345}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_manga_by_id\", \"description\": \"Fetches Manga information by its ID from the Anime, Manga, and Novels API.\", \"parameters\": {\"is_id\": {\"description\": \"The ID of the Manga to fetch information for.\", \"type\": \"int\", \"default\": \"3674\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_by_trakt_tv_id\", \"description\": \"Fetches movie or TV show information from the RapidAPI MDB List service based on a given Trakt.tv ID.\", \"parameters\": {\"t\": {\"description\": \"A valid Trakt.tv ID representing the movie or TV show.\", \"type\": \"str\", \"default\": \"457\"}, \"m\": {\"description\": \"The media type, either 'movie' or 'show'. Defaults to 'movie' if not specified.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"songs\", \"description\": \"Fetches a list of songs from JSR/JSRF using the specified parameters.\", \"parameters\": {\"limit\": {\"description\": \"The maximum number of items to return in the response. Default is '5'.\", \"type\": \"str\", \"default\": \"5\"}, \"sortby\": {\"description\": \"The field by which to sort the results. Possible values include fields on the document, e.g., 'name', 'stats'. Default is 'name'.\", \"type\": \"str\", \"default\": \"name\"}, \"orderby\": {\"description\": \"The order in which to sort the results. Possible values are 'asc' for ascending and 'desc' for descending. The `sortby` parameter must be present for this to take effect. Default is 'asc'.\", \"type\": \"str\", \"default\": \"asc\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"query_joke_using_id\", \"description\": \"Fetches an anime joke using the provided joke ID from the RapidAPI service.\", \"parameters\": {\"is_id\": {\"description\": \"The ID of the joke to be fetched.\", \"type\": \"int\", \"default\": \"4\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the TV show with Trakt.tv ID 'tt98765' and the joke with ID 12345?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_by_trakt_tv_id\", \"arguments\": {\"t\": \"tt98765\", \"m\": \"show\"}}, {\"name\": \"query_joke_using_id\", \"arguments\": {\"is_id\": 12345}}]",
"style": "rule"
}
|
{
"index": 60,
"split": "train"
}
|
[{"name": "drink_by_id", "description": "Fetches a specific drink recipe by its ID using the Ghana Food Recipe API.", "parameters": {"is_id": {"description": "The unique identifier for the drink recipe.", "type": "str", "default": "63c67c9db06a3ed9f92b2367"}}}, {"name": "go", "description": "Retrieves creative recipes based on a search query using the Recipe64 RapidAPI.", "parameters": {"q": {"description": "Search query for the recipes.", "type": "str", "default": "taco"}}}]
|
[
{
"from": "human",
"value": "Get the drink recipe with ID '151617' from the Ghana Food Recipe API. Also, search for 'low-carb breakfast' recipes using the Recipe64 RapidAPI."
}
] |
[{"name": "drink_by_id", "arguments": {"is_id": "151617"}}, {"name": "go", "arguments": {"q": "low-carb breakfast"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"drink_by_id\", \"description\": \"Fetches a specific drink recipe by its ID using the Ghana Food Recipe API.\", \"parameters\": {\"is_id\": {\"description\": \"The unique identifier for the drink recipe.\", \"type\": \"str\", \"default\": \"63c67c9db06a3ed9f92b2367\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"go\", \"description\": \"Retrieves creative recipes based on a search query using the Recipe64 RapidAPI.\", \"parameters\": {\"q\": {\"description\": \"Search query for the recipes.\", \"type\": \"str\", \"default\": \"taco\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Get the drink recipe with ID '151617' from the Ghana Food Recipe API. Also, search for 'low-carb breakfast' recipes using the Recipe64 RapidAPI.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"drink_by_id\", \"arguments\": {\"is_id\": \"151617\"}}, {\"name\": \"go\", \"arguments\": {\"q\": \"low-carb breakfast\"}}]",
"style": "rule"
}
|
{
"index": 61,
"split": "train"
}
|
[{"name": "conversion", "description": "Performs cryptocurrency conversion from a given cryptocurrency symbol to another and retrieves conversion data.", "parameters": {"tsym": {"description": "The target cryptocurrency symbol to convert to.", "type": "str", "default": "USDT"}, "fsyms": {"description": "The source cryptocurrency symbol to convert from.", "type": "str", "default": "ETH"}}}, {"name": "get_realtime_volume", "description": "Fetches the real-time trading volume of a cryptocurrency in US Dollars.", "parameters": {"symbol": {"description": "The ticker symbol of the cryptocurrency (e.g., 'BTC' for Bitcoin).", "type": "str", "default": "BTC"}}}, {"name": "quote", "description": "Retrieve the latest quote for the specified financial instrument.", "parameters": {"symbol": {"description": "The symbol of the financial instrument (e.g., 'AAPL', 'EUR/USD', 'ETH/BTC').", "type": "str", "default": "AMZN"}, "interval": {"description": "Time interval between data points. Supported values are `1min`, `5min`, `15min`, `30min`, `45min`, `1h`, `2h`, `4h`, `1day`, `1week`, `1month`.", "type": "str", "default": "1day"}, "outputsize": {"description": "The number of data points to retrieve. Defaults to 30.", "type": "int, optional", "default": 30}, "format": {"description": "The format of the response. Can be 'csv' or 'json'. Defaults to 'json'.", "type": "str, optional", "default": "json"}}}, {"name": "recent_trades_list", "description": "Fetches the recent trades for a given cryptocurrency symbol from the RapidAPI crypto markets service.", "parameters": {"symbol": {"description": "The cryptocurrency symbol (e.g., 'BTC' for Bitcoin) for which recent trades are to be fetched.", "type": "str", "default": "BTCUSDT"}, "limit": {"description": "The number of recent trades to retrieve. Default is 500; maximum is 1000.", "type": "int, optional", "default": "500"}}}]
|
[
{
"from": "human",
"value": "Convert 10 Litecoins to Bitcoin and 2 Bitcoins to Litecoin. Also, what are their real-time trading volumes?"
}
] |
[{"name": "conversion", "arguments": {"tsym": "BTC", "fsyms": "LTC"}}, {"name": "conversion", "arguments": {"tsym": "LTC", "fsyms": "BTC"}}, {"name": "get_realtime_volume", "arguments": {"symbol": "BTC"}}, {"name": "get_realtime_volume", "arguments": {"symbol": "LTC"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"conversion\", \"description\": \"Performs cryptocurrency conversion from a given cryptocurrency symbol to another and retrieves conversion data.\", \"parameters\": {\"tsym\": {\"description\": \"The target cryptocurrency symbol to convert to.\", \"type\": \"str\", \"default\": \"USDT\"}, \"fsyms\": {\"description\": \"The source cryptocurrency symbol to convert from.\", \"type\": \"str\", \"default\": \"ETH\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_realtime_volume\", \"description\": \"Fetches the real-time trading volume of a cryptocurrency in US Dollars.\", \"parameters\": {\"symbol\": {\"description\": \"The ticker symbol of the cryptocurrency (e.g., 'BTC' for Bitcoin).\", \"type\": \"str\", \"default\": \"BTC\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"quote\", \"description\": \"Retrieve the latest quote for the specified financial instrument.\", \"parameters\": {\"symbol\": {\"description\": \"The symbol of the financial instrument (e.g., 'AAPL', 'EUR/USD', 'ETH/BTC').\", \"type\": \"str\", \"default\": \"AMZN\"}, \"interval\": {\"description\": \"Time interval between data points. Supported values are `1min`, `5min`, `15min`, `30min`, `45min`, `1h`, `2h`, `4h`, `1day`, `1week`, `1month`.\", \"type\": \"str\", \"default\": \"1day\"}, \"outputsize\": {\"description\": \"The number of data points to retrieve. Defaults to 30.\", \"type\": \"int, optional\", \"default\": 30}, \"format\": {\"description\": \"The format of the response. Can be 'csv' or 'json'. Defaults to 'json'.\", \"type\": \"str, optional\", \"default\": \"json\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"recent_trades_list\", \"description\": \"Fetches the recent trades for a given cryptocurrency symbol from the RapidAPI crypto markets service.\", \"parameters\": {\"symbol\": {\"description\": \"The cryptocurrency symbol (e.g., 'BTC' for Bitcoin) for which recent trades are to be fetched.\", \"type\": \"str\", \"default\": \"BTCUSDT\"}, \"limit\": {\"description\": \"The number of recent trades to retrieve. Default is 500; maximum is 1000.\", \"type\": \"int, optional\", \"default\": \"500\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Convert 10 Litecoins to Bitcoin and 2 Bitcoins to Litecoin. Also, what are their real-time trading volumes?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"conversion\", \"arguments\": {\"tsym\": \"BTC\", \"fsyms\": \"LTC\"}}, {\"name\": \"conversion\", \"arguments\": {\"tsym\": \"LTC\", \"fsyms\": \"BTC\"}}, {\"name\": \"get_realtime_volume\", \"arguments\": {\"symbol\": \"BTC\"}}, {\"name\": \"get_realtime_volume\", \"arguments\": {\"symbol\": \"LTC\"}}]",
"style": "rule"
}
|
{
"index": 62,
"split": "train"
}
|
[{"name": "EvolutionaryBiology.FitnessCalculator", "description": "Calculates the fitness of an organism based on its phenotype and the current environmental conditions.", "parameters": {"type": "dict", "properties": {"phenotype": {"description": "The phenotype of the organism, represented as a list of traits.", "type": "array", "items": {"type": "string"}}, "environment": {"description": "The current environmental conditions, represented as a list of factors.", "type": "array", "items": {"type": "string"}}}, "required": ["phenotype", "environment"]}, "required": null}, {"name": "EvolutionaryBiology.GeneticDrift", "description": "Simulates the effect of genetic drift on a population over a number of generations.", "parameters": {"type": "dict", "properties": {"initialPopulation": {"description": "The initial size of the population.", "type": "int", "minimum": 2}, "generations": {"description": "The number of generations to simulate.", "type": "int", "minimum": 1}, "alleleFrequency": {"description": "The initial frequency of a particular allele in the population, represented as a percentage.", "type": "float", "minimum": 0, "maximum": 100}}, "required": ["initialPopulation", "generations", "alleleFrequency"]}, "required": null}]
|
[
{
"from": "human",
"value": "I am working on a research project that explores the adaptability of certain species in changing environments. I need to calculate the fitness scores of three different species in a forest environment undergoing changes due to deforestation. The species are \"Arctic Fox\", \"Red Fox\", and \"Grey Wolf\", facing challenges like \"reduced prey\", \"increased competition\", and \"habitat loss\". Can you help me calculate their fitness scores?"
}
] |
[{"name": "EvolutionaryBiology.FitnessCalculator", "arguments": {"phenotype": ["Arctic Fox"], "environment": ["reduced prey", "increased competition", "habitat loss"]}}, {"name": "EvolutionaryBiology.FitnessCalculator", "arguments": {"phenotype": ["Red Fox"], "environment": ["reduced prey", "increased competition", "habitat loss"]}}, {"name": "EvolutionaryBiology.FitnessCalculator", "arguments": {"phenotype": ["Grey Wolf"], "environment": ["reduced prey", "increased competition", "habitat loss"]}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out.
Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out.\nHere is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"EvolutionaryBiology.FitnessCalculator\", \"description\": \"Calculates the fitness of an organism based on its phenotype and the current environmental conditions.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"phenotype\": {\"description\": \"The phenotype of the organism, represented as a list of traits.\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"environment\": {\"description\": \"The current environmental conditions, represented as a list of factors.\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"phenotype\", \"environment\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"EvolutionaryBiology.GeneticDrift\", \"description\": \"Simulates the effect of genetic drift on a population over a number of generations.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"initialPopulation\": {\"description\": \"The initial size of the population.\", \"type\": \"int\", \"minimum\": 2}, \"generations\": {\"description\": \"The number of generations to simulate.\", \"type\": \"int\", \"minimum\": 1}, \"alleleFrequency\": {\"description\": \"The initial frequency of a particular allele in the population, represented as a percentage.\", \"type\": \"float\", \"minimum\": 0, \"maximum\": 100}}, \"required\": [\"initialPopulation\", \"generations\", \"alleleFrequency\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I am working on a research project that explores the adaptability of certain species in changing environments. I need to calculate the fitness scores of three different species in a forest environment undergoing changes due to deforestation. The species are \"Arctic Fox\", \"Red Fox\", and \"Grey Wolf\", facing challenges like \"reduced prey\", \"increased competition\", and \"habitat loss\". Can you help me calculate their fitness scores?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"EvolutionaryBiology.FitnessCalculator\", \"arguments\": {\"phenotype\": [\"Arctic Fox\"], \"environment\": [\"reduced prey\", \"increased competition\", \"habitat loss\"]}}, {\"name\": \"EvolutionaryBiology.FitnessCalculator\", \"arguments\": {\"phenotype\": [\"Red Fox\"], \"environment\": [\"reduced prey\", \"increased competition\", \"habitat loss\"]}}, {\"name\": \"EvolutionaryBiology.FitnessCalculator\", \"arguments\": {\"phenotype\": [\"Grey Wolf\"], \"environment\": [\"reduced prey\", \"increased competition\", \"habitat loss\"]}}]",
"style": "rule"
}
|
{
"index": 63,
"split": "train"
}
|
[{"name": "get_index_price_kline", "description": "Fetches the index price kline data for a specified symbol and category within a given time range.", "parameters": {"symbol": {"description": "The symbol for which the kline data is to be fetched.", "type": "str", "default": "BTCUSDT"}, "category": {"description": "The derivatives products category. Possible values are 'linear' and 'inverse', including inverse futures.", "type": "str", "default": "linear"}, "interval": {"description": "The interval for the kline data. Possible values are '1', '3', '5', '15', '30', '60', '120', '240', '360', '720', 'D', 'M', and 'W'.", "type": "str", "default": "D"}, "end": {"description": "The end timestamp point for the query results, in milliseconds.", "type": "int", "default": "1652544000000"}, "start": {"description": "The start timestamp point for the query results, in milliseconds.", "type": "int", "default": "1652112000000"}, "limit": {"description": "The limit for the data size per page, with a maximum size of 200. Defaults to None.", "type": "int, optional", "default": ""}}}, {"name": "balance", "description": "Retrieves the balance sheet statements of a specified stock company.", "parameters": {"symbol": {"description": "The stock symbol of the company (e.g., 'AAPL' for Apple Inc.).", "type": "str", "default": "MSFT"}, "period": {"description": "The reporting period for the balance sheet, which can be 'annual' or 'quarterly'.", "type": "str", "default": "quarter"}}}]
|
[
{
"from": "human",
"value": "Retrieve the annual balance sheet for 'GOOGL'."
}
] |
[{"name": "balance", "arguments": {"symbol": "GOOGL", "period": "annual"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_index_price_kline\", \"description\": \"Fetches the index price kline data for a specified symbol and category within a given time range.\", \"parameters\": {\"symbol\": {\"description\": \"The symbol for which the kline data is to be fetched.\", \"type\": \"str\", \"default\": \"BTCUSDT\"}, \"category\": {\"description\": \"The derivatives products category. Possible values are 'linear' and 'inverse', including inverse futures.\", \"type\": \"str\", \"default\": \"linear\"}, \"interval\": {\"description\": \"The interval for the kline data. Possible values are '1', '3', '5', '15', '30', '60', '120', '240', '360', '720', 'D', 'M', and 'W'.\", \"type\": \"str\", \"default\": \"D\"}, \"end\": {\"description\": \"The end timestamp point for the query results, in milliseconds.\", \"type\": \"int\", \"default\": \"1652544000000\"}, \"start\": {\"description\": \"The start timestamp point for the query results, in milliseconds.\", \"type\": \"int\", \"default\": \"1652112000000\"}, \"limit\": {\"description\": \"The limit for the data size per page, with a maximum size of 200. Defaults to None.\", \"type\": \"int, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"balance\", \"description\": \"Retrieves the balance sheet statements of a specified stock company.\", \"parameters\": {\"symbol\": {\"description\": \"The stock symbol of the company (e.g., 'AAPL' for Apple Inc.).\", \"type\": \"str\", \"default\": \"MSFT\"}, \"period\": {\"description\": \"The reporting period for the balance sheet, which can be 'annual' or 'quarterly'.\", \"type\": \"str\", \"default\": \"quarter\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Retrieve the annual balance sheet for 'GOOGL'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"balance\", \"arguments\": {\"symbol\": \"GOOGL\", \"period\": \"annual\"}}]",
"style": "rule"
}
|
{
"index": 64,
"split": "train"
}
|
[{"name": "stock_recommendation_trend", "description": "Fetches stock recommendation trends using the Yahoo Finance API.", "parameters": {"symbol": {"description": "The stock symbol for which to fetch recommendation trends.", "type": "str", "default": "AAPL"}}}, {"name": "stock_get_financial_stmts", "description": "Fetch financial statements for a given stock symbol.", "parameters": {"frequency": {"description": "The frequency of the financial statements. It can be either 'annual' or 'quarterly'.", "type": "str", "default": "quarterly"}, "symbol": {"description": "The ticker symbol of the stock (e.g., \"AAPL\" for Apple Inc.).", "type": "str", "default": "AAPL"}, "statement_type": {"description": "The type of financial statement to retrieve. It can be 'income', 'balance', 'cash', or a list containing these types.", "type": "str", "default": "income"}, "region": {"description": "The region of the stock market. Defaults to 'US'. Allowed values are 'US', 'BR', 'AU', 'CA', 'FR', 'DE', 'HK', 'IN', 'IT', 'ES', 'GB', 'S'.", "type": "str, optional", "default": "US"}}}, {"name": "stock_splits", "description": "Fetch the list of all stock splits for a given stock symbol.", "parameters": {"symbol": {"description": "The stock symbol for which to fetch stock splits.", "type": "str", "default": "MSFT"}, "orderby": {"description": "The order in which to sort the stock splits. Defaults to 'Ascending'.", "type": "str, optional", "default": "Ascending"}}}]
|
[
{
"from": "human",
"value": "Can you provide the recommendation trend for Tesla and the latest financial statements for Apple Inc. in the US?"
}
] |
[{"name": "stock_recommendation_trend", "arguments": {"symbol": "TSLA"}}, {"name": "stock_get_financial_stmts", "arguments": {"frequency": "annual", "symbol": "AAPL", "statement_type": "income", "region": "US"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"stock_recommendation_trend\", \"description\": \"Fetches stock recommendation trends using the Yahoo Finance API.\", \"parameters\": {\"symbol\": {\"description\": \"The stock symbol for which to fetch recommendation trends.\", \"type\": \"str\", \"default\": \"AAPL\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"stock_get_financial_stmts\", \"description\": \"Fetch financial statements for a given stock symbol.\", \"parameters\": {\"frequency\": {\"description\": \"The frequency of the financial statements. It can be either 'annual' or 'quarterly'.\", \"type\": \"str\", \"default\": \"quarterly\"}, \"symbol\": {\"description\": \"The ticker symbol of the stock (e.g., \\\"AAPL\\\" for Apple Inc.).\", \"type\": \"str\", \"default\": \"AAPL\"}, \"statement_type\": {\"description\": \"The type of financial statement to retrieve. It can be 'income', 'balance', 'cash', or a list containing these types.\", \"type\": \"str\", \"default\": \"income\"}, \"region\": {\"description\": \"The region of the stock market. Defaults to 'US'. Allowed values are 'US', 'BR', 'AU', 'CA', 'FR', 'DE', 'HK', 'IN', 'IT', 'ES', 'GB', 'S'.\", \"type\": \"str, optional\", \"default\": \"US\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"stock_splits\", \"description\": \"Fetch the list of all stock splits for a given stock symbol.\", \"parameters\": {\"symbol\": {\"description\": \"The stock symbol for which to fetch stock splits.\", \"type\": \"str\", \"default\": \"MSFT\"}, \"orderby\": {\"description\": \"The order in which to sort the stock splits. Defaults to 'Ascending'.\", \"type\": \"str, optional\", \"default\": \"Ascending\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Can you provide the recommendation trend for Tesla and the latest financial statements for Apple Inc. in the US?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"stock_recommendation_trend\", \"arguments\": {\"symbol\": \"TSLA\"}}, {\"name\": \"stock_get_financial_stmts\", \"arguments\": {\"frequency\": \"annual\", \"symbol\": \"AAPL\", \"statement_type\": \"income\", \"region\": \"US\"}}]",
"style": "rule"
}
|
{
"index": 65,
"split": "train"
}
|
[{"name": "calculate_electric_field", "description": "Calculate the electric field produced by a charge at a certain distance.", "parameters": {"charge": {"description": "Charge in coulombs producing the electric field.", "type": "int", "default": 8.854e-12}, "distance": {"description": "Distance from the charge in meters where the field is being measured.", "type": "int", "default": 8.854e-12}, "permitivity": {"description": "Permitivity of the space where field is being calculated, default is 8.854e-12.", "type": "float"}}}]
|
[
{
"from": "human",
"value": "What is the electric field at 45 meters from a charge of 50 Coulombs, and then at 90 meters from a charge of 100 Coulombs?"
}
] |
[{"name": "calculate_electric_field", "arguments": {"charge": 50, "distance": 45}}, {"name": "calculate_electric_field", "arguments": {"charge": 100, "distance": 90}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_electric_field\", \"description\": \"Calculate the electric field produced by a charge at a certain distance.\", \"parameters\": {\"charge\": {\"description\": \"Charge in coulombs producing the electric field.\", \"type\": \"int\", \"default\": 8.854e-12}, \"distance\": {\"description\": \"Distance from the charge in meters where the field is being measured.\", \"type\": \"int\", \"default\": 8.854e-12}, \"permitivity\": {\"description\": \"Permitivity of the space where field is being calculated, default is 8.854e-12.\", \"type\": \"float\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the electric field at 45 meters from a charge of 50 Coulombs, and then at 90 meters from a charge of 100 Coulombs?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"calculate_electric_field\", \"arguments\": {\"charge\": 50, \"distance\": 45}}, {\"name\": \"calculate_electric_field\", \"arguments\": {\"charge\": 100, \"distance\": 90}}]",
"style": "rule"
}
|
{
"index": 66,
"split": "train"
}
|
[{"name": "bilingual_dictionary", "description": "Queries a powerful multi-language bilingual neural translation dictionary, supporting 80+ languages, to get translations.", "parameters": {"q": {"description": "The word or comma-separated words (up to 10 words per request) to seek bilingual translations for.", "type": "str", "default": "merci, poisson, beaucoup"}, "is_from": {"description": "The ISO 639-1 language code of the source language. Supported languages include 'ar', 'az', 'be', 'bg', 'ca', 'ce', 'cs', 'cy', 'da', 'de', 'el', 'en', 'eo', 'es', 'et', 'eu', 'fa', 'fi', 'fr', 'gl', 'he', 'hi', 'hr', 'hu', 'hy', 'id', 'it', 'ja', 'ka', 'kk', 'ko', 'la', 'lt', 'lv', 'mk', 'ms', 'nl', 'nn', 'no', 'pl', 'pt', 'ro', 'ru', 'sh', 'sk', 'sl', 'sr', 'sv', 'ta', 'tg', 'th', 'tr', 'tt', 'uk', 'ur', 'uz', 'vi', 'vo', 'zh'.", "type": "str", "default": "fr"}, "to": {"description": "The ISO 639-1 language code of the target language. The same set of supported languages as `is_from`.", "type": "str", "default": "en"}}}, {"name": "translate", "description": "Translates the given text to the specified target language using the Joj Translate API.", "parameters": {"text": {"description": "The text to be translated.", "type": "str", "default": "article"}, "target": {"description": "The language to translate the text into.", "type": "str", "default": "es"}, "source": {"description": "The source language of the text. Defaults to 'auto', which automatically detects the source language.", "type": "str, optional", "default": "auto"}}}, {"name": "get_voice", "description": "Generates a voice response from the given text using the Anime Voice Waifu AI via RapidAPI.", "parameters": {"text": {"description": "The text to be converted into voice.", "type": "str", "default": ""}, "speaker": {"description": "The speaker's voice to use for conversion. Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "translate", "description": "Translates the given text from the source language to the destination language using the RapidAPI translation service.", "parameters": {"text": {"description": "The text to be translated.", "type": "str", "default": "this is accurate and it can improve if it's longer"}, "dest": {"description": "The target language code (e.g., 'en' for English, 'es' for Spanish).", "type": "str", "default": "es"}, "src": {"description": "The source language code. Defaults to 'auto', which will auto-detect the source language.", "type": "str, optional", "default": "auto"}}}]
|
[
{
"from": "human",
"value": "Convert the text 'I love anime' into a voice clip using the voice of Hatsune Miku from the Anime Voice Waifu AI API."
}
] |
[{"name": "get_voice", "arguments": {"text": "I love anime", "speaker": "Hatsune Miku"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"bilingual_dictionary\", \"description\": \"Queries a powerful multi-language bilingual neural translation dictionary, supporting 80+ languages, to get translations.\", \"parameters\": {\"q\": {\"description\": \"The word or comma-separated words (up to 10 words per request) to seek bilingual translations for.\", \"type\": \"str\", \"default\": \"merci, poisson, beaucoup\"}, \"is_from\": {\"description\": \"The ISO 639-1 language code of the source language. Supported languages include 'ar', 'az', 'be', 'bg', 'ca', 'ce', 'cs', 'cy', 'da', 'de', 'el', 'en', 'eo', 'es', 'et', 'eu', 'fa', 'fi', 'fr', 'gl', 'he', 'hi', 'hr', 'hu', 'hy', 'id', 'it', 'ja', 'ka', 'kk', 'ko', 'la', 'lt', 'lv', 'mk', 'ms', 'nl', 'nn', 'no', 'pl', 'pt', 'ro', 'ru', 'sh', 'sk', 'sl', 'sr', 'sv', 'ta', 'tg', 'th', 'tr', 'tt', 'uk', 'ur', 'uz', 'vi', 'vo', 'zh'.\", \"type\": \"str\", \"default\": \"fr\"}, \"to\": {\"description\": \"The ISO 639-1 language code of the target language. The same set of supported languages as `is_from`.\", \"type\": \"str\", \"default\": \"en\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"translate\", \"description\": \"Translates the given text to the specified target language using the Joj Translate API.\", \"parameters\": {\"text\": {\"description\": \"The text to be translated.\", \"type\": \"str\", \"default\": \"article\"}, \"target\": {\"description\": \"The language to translate the text into.\", \"type\": \"str\", \"default\": \"es\"}, \"source\": {\"description\": \"The source language of the text. Defaults to 'auto', which automatically detects the source language.\", \"type\": \"str, optional\", \"default\": \"auto\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_voice\", \"description\": \"Generates a voice response from the given text using the Anime Voice Waifu AI via RapidAPI.\", \"parameters\": {\"text\": {\"description\": \"The text to be converted into voice.\", \"type\": \"str\", \"default\": \"\"}, \"speaker\": {\"description\": \"The speaker's voice to use for conversion. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"translate\", \"description\": \"Translates the given text from the source language to the destination language using the RapidAPI translation service.\", \"parameters\": {\"text\": {\"description\": \"The text to be translated.\", \"type\": \"str\", \"default\": \"this is accurate and it can improve if it's longer\"}, \"dest\": {\"description\": \"The target language code (e.g., 'en' for English, 'es' for Spanish).\", \"type\": \"str\", \"default\": \"es\"}, \"src\": {\"description\": \"The source language code. Defaults to 'auto', which will auto-detect the source language.\", \"type\": \"str, optional\", \"default\": \"auto\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Convert the text 'I love anime' into a voice clip using the voice of Hatsune Miku from the Anime Voice Waifu AI API.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_voice\", \"arguments\": {\"text\": \"I love anime\", \"speaker\": \"Hatsune Miku\"}}]",
"style": "rule"
}
|
{
"index": 67,
"split": "train"
}
|
[{"name": "getDateTimeByCoOrdinates", "description": "Get the string and time for a pair of given coordinates.", "parameters": {"type": "dict", "properties": {"latitude": {"description": "The latitude of the location", "type": "float"}, "longitude": {"description": "The longitude of the location", "type": "float"}}, "required": ["latitude", "longitude"]}, "required": null}, {"name": "getFeedVersions", "description": "Retrieve a list of feed versions for a given transit feed, with optional filtering and pagination.", "parameters": {"type": "dict", "properties": {"feed": {"description": "The ID of the transit feed to retrieve versions for.", "type": "string", "default": "sfmta/60"}, "page": {"description": "The page of results to return.", "type": "string", "default": ""}}, "required": ["feed"]}, "required": null}, {"name": "Get Time Zones", "description": "Retrieves a list of time zones along with their corresponding information.", "parameters": {"type": "dict", "properties": {"offset": {"description": "The zero-based offset index into the results", "type": "string"}, "hateoasMode": {"description": "Include HATEOAS-style links in results", "type": "boolean"}, "limit": {"description": "The maximum number of results to retrieve", "type": "float"}}, "required": []}, "required": null}, {"name": "discover", "description": "Retrieve a list of strings discovered by FilePursuit, with optional filtering and pagination", "parameters": {"type": "dict", "properties": {"start": {"description": "Start results from this count (for pagination)", "type": "int"}, "type": {"description": "Type of result (Accepted values: stringlinks, all)", "type": "string"}, "link": {"description": "Link to discover strings from", "type": "string"}}, "required": ["link"]}, "required": null}]
|
[
{
"from": "human",
"value": "Can you tell me the current time and weather conditions for my current GPS coordinates? Assume my latitude is 37.7749 and longitude is -122.4194."
},
{
"from": "function_call",
"value": "[{\"name\": \"getDateTimeByCoOrdinates\", \"arguments\": {\"latitude\": 37.7749, \"longitude\": -122.4194}}]"
},
{
"from": "observation",
"value": "[{\"name\": \"getDateTimeByCoOrdinates\", \"results\": {\"string\": \"San Francisco, California, USA\", \"time\": \"2023-04-20T12:09:45\"}}]"
},
{
"from": "gpt",
"value": "Based on the output from the tool, the current time for your coordinates in San Francisco, California, USA, is 12:09:45 on April 20th, 2023. Please note that this is the time at the moment of your inquiry and it may have changed since then. If you require the exact current time now, please let me know to provide an updated response. \n\nAs for the weather conditions, as mentioned earlier, I currently do not have the tools to provide that information. You may check a local weather service or a weather website for the most up-to-date weather conditions."
},
{
"from": "human",
"value": "This brings a curious thought to my mind. How are time zones actually determined? It seems like an intricate system."
},
{
"from": "gpt",
"value": "Indeed, the system of time zones is quite fascinating!\n\nTime zones are regions of the Earth that have the same standard time. They follow the lines of longitude, which run from the North Pole to the South Pole. The concept was proposed by Sir Sandford Fleming in the late 1800s and was later adopted in 1884 at the International Meridian Conference.\n\nThe entire world is divided into 24 time zones, approximately following lines of longitude. The starting point is the prime meridian (0 degrees longitude), which runs through the Royal Observatory in Greenwich, London, UK, hence known as Greenwich Mean Time (GMT). Each time zone is about 15 degrees of longitude wide and represents one hour of time.\n\nAs you move east from the prime meridian, the local time increases by one hour for each time zone, and vice versa as you move west. However, actual time zone boundaries are determined by political or geographical factors and may not strictly adhere to the 15-degree rule. For example, China, despite spanning five geographical time zones, uses a single standard time throughout the country.\n\nAdditionally, some countries utilize Daylight Saving Time, when clocks are adjusted forward by one hour near the start of spring to extend evening daylight and are then set back by an hour in the fall.\n\nIt's an intricate system indeed, designed to standardize time across the globe and facilitate communication and coordination."
},
{
"from": "human",
"value": "It's like a global game of tag with time! Keeping that in mind, can you retrieve a list of time zones, including their offsets, ids, and a brief description? I’m curious to know more specifics!"
}
] |
[{"name": "Get Time Zones", "arguments": {}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections.
Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections.\nHere is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"getDateTimeByCoOrdinates\", \"description\": \"Get the string and time for a pair of given coordinates.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"latitude\": {\"description\": \"The latitude of the location\", \"type\": \"float\"}, \"longitude\": {\"description\": \"The longitude of the location\", \"type\": \"float\"}}, \"required\": [\"latitude\", \"longitude\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"getFeedVersions\", \"description\": \"Retrieve a list of feed versions for a given transit feed, with optional filtering and pagination.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"feed\": {\"description\": \"The ID of the transit feed to retrieve versions for.\", \"type\": \"string\", \"default\": \"sfmta/60\"}, \"page\": {\"description\": \"The page of results to return.\", \"type\": \"string\", \"default\": \"\"}}, \"required\": [\"feed\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Get Time Zones\", \"description\": \"Retrieves a list of time zones along with their corresponding information.\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"offset\": {\"description\": \"The zero-based offset index into the results\", \"type\": \"string\"}, \"hateoasMode\": {\"description\": \"Include HATEOAS-style links in results\", \"type\": \"boolean\"}, \"limit\": {\"description\": \"The maximum number of results to retrieve\", \"type\": \"float\"}}, \"required\": []}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"discover\", \"description\": \"Retrieve a list of strings discovered by FilePursuit, with optional filtering and pagination\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"start\": {\"description\": \"Start results from this count (for pagination)\", \"type\": \"int\"}, \"type\": {\"description\": \"Type of result (Accepted values: stringlinks, all)\", \"type\": \"string\"}, \"link\": {\"description\": \"Link to discover strings from\", \"type\": \"string\"}}, \"required\": [\"link\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Can you tell me the current time and weather conditions for my current GPS coordinates? Assume my latitude is 37.7749 and longitude is -122.4194.",
"role": "user"
},
{
"content": "\"[{\\\"name\\\": \\\"getDateTimeByCoOrdinates\\\", \\\"arguments\\\": {\\\"latitude\\\": 37.7749, \\\"longitude\\\": -122.4194}}]\"",
"role": "assistant"
},
{
"content": "[{\"name\": \"getDateTimeByCoOrdinates\", \"results\": {\"string\": \"San Francisco, California, USA\", \"time\": \"2023-04-20T12:09:45\"}}]",
"role": "tool"
},
{
"content": "Based on the output from the tool, the current time for your coordinates in San Francisco, California, USA, is 12:09:45 on April 20th, 2023. Please note that this is the time at the moment of your inquiry and it may have changed since then. If you require the exact current time now, please let me know to provide an updated response. \n\nAs for the weather conditions, as mentioned earlier, I currently do not have the tools to provide that information. You may check a local weather service or a weather website for the most up-to-date weather conditions.",
"role": "assistant"
},
{
"content": "This brings a curious thought to my mind. How are time zones actually determined? It seems like an intricate system.",
"role": "user"
},
{
"content": "Indeed, the system of time zones is quite fascinating!\n\nTime zones are regions of the Earth that have the same standard time. They follow the lines of longitude, which run from the North Pole to the South Pole. The concept was proposed by Sir Sandford Fleming in the late 1800s and was later adopted in 1884 at the International Meridian Conference.\n\nThe entire world is divided into 24 time zones, approximately following lines of longitude. The starting point is the prime meridian (0 degrees longitude), which runs through the Royal Observatory in Greenwich, London, UK, hence known as Greenwich Mean Time (GMT). Each time zone is about 15 degrees of longitude wide and represents one hour of time.\n\nAs you move east from the prime meridian, the local time increases by one hour for each time zone, and vice versa as you move west. However, actual time zone boundaries are determined by political or geographical factors and may not strictly adhere to the 15-degree rule. For example, China, despite spanning five geographical time zones, uses a single standard time throughout the country.\n\nAdditionally, some countries utilize Daylight Saving Time, when clocks are adjusted forward by one hour near the start of spring to extend evening daylight and are then set back by an hour in the fall.\n\nIt's an intricate system indeed, designed to standardize time across the globe and facilitate communication and coordination.",
"role": "assistant"
},
{
"content": "It's like a global game of tag with time! Keeping that in mind, can you retrieve a list of time zones, including their offsets, ids, and a brief description? I’m curious to know more specifics!",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"Get Time Zones\", \"arguments\": {}}]",
"style": "rule"
}
|
{
"index": 68,
"split": "train"
}
|
[{"name": "calculate_median", "description": "Calculates the median of a list of numbers.", "parameters": {"numbers": {"description": "The list of numbers.", "type": "List[Union[int, float]]"}}}, {"name": "final_velocity", "description": "Calculates the final velocity of an object given its initial velocity, acceleration, and time.", "parameters": {"initial_velocity": {"description": "The initial velocity of the object.", "type": "float"}, "acceleration": {"description": "The acceleration of the object.", "type": "float"}, "time": {"description": "The time elapsed.", "type": "float"}}}, {"name": "note_duration", "description": "Calculates the duration between two musical notes based on their frequencies and the tempo.", "parameters": {"freq1": {"description": "The frequency of the first note in Hz.", "type": "int", "default": 120}, "freq2": {"description": "The frequency of the second note in Hz.", "type": "int", "default": 120}, "bpm": {"description": "The tempo of the music in beats per minute. Defaults to 120.", "type": "int, optional"}}}, {"name": "is_power", "description": "Checks if a number is a power of a given base.", "parameters": {"num": {"description": "The number to check.", "type": "int"}, "base": {"description": "The base to check against.", "type": "int"}}}, {"name": "calculate_electric_field", "description": "Calculate the electric field produced by a charge at a certain distance.", "parameters": {"charge": {"description": "Charge in coulombs producing the electric field.", "type": "int", "default": 8.854e-12}, "distance": {"description": "Distance from the charge in meters where the field is being measured.", "type": "int", "default": 8.854e-12}, "permitivity": {"description": "Permitivity of the space where field is being calculated, default is 8.854e-12.", "type": "float"}}}, {"name": "bacterial_growth", "description": "Calculates the bacterial population after a given time based on the initial population and growth rate.", "parameters": {"initial_population": {"description": "The initial bacterial population.", "type": "int", "default": 20}, "growth_rate": {"description": "The growth rate per unit time.", "type": "float", "default": 20}, "time": {"description": "The time elapsed.", "type": "float"}, "doubling_time": {"description": "The doubling time of the bacteria in minutes. Defaults to 20.", "type": "float, optional"}}}]
|
[
{
"from": "human",
"value": "What is the median of the numbers 1, 2, 3, 4, and 5? Also, I want to find the final velocity of an object that starts with an initial velocity of 30 m/s, accelerates at 10 m/s^2 for 5 seconds."
}
] |
[{"name": "calculate_median", "arguments": {"numbers": [1, 2, 3, 4, 5]}}, {"name": "final_velocity", "arguments": {"initial_velocity": 30, "acceleration": 10, "time": 5}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_median\", \"description\": \"Calculates the median of a list of numbers.\", \"parameters\": {\"numbers\": {\"description\": \"The list of numbers.\", \"type\": \"List[Union[int, float]]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"final_velocity\", \"description\": \"Calculates the final velocity of an object given its initial velocity, acceleration, and time.\", \"parameters\": {\"initial_velocity\": {\"description\": \"The initial velocity of the object.\", \"type\": \"float\"}, \"acceleration\": {\"description\": \"The acceleration of the object.\", \"type\": \"float\"}, \"time\": {\"description\": \"The time elapsed.\", \"type\": \"float\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"note_duration\", \"description\": \"Calculates the duration between two musical notes based on their frequencies and the tempo.\", \"parameters\": {\"freq1\": {\"description\": \"The frequency of the first note in Hz.\", \"type\": \"int\", \"default\": 120}, \"freq2\": {\"description\": \"The frequency of the second note in Hz.\", \"type\": \"int\", \"default\": 120}, \"bpm\": {\"description\": \"The tempo of the music in beats per minute. Defaults to 120.\", \"type\": \"int, optional\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"is_power\", \"description\": \"Checks if a number is a power of a given base.\", \"parameters\": {\"num\": {\"description\": \"The number to check.\", \"type\": \"int\"}, \"base\": {\"description\": \"The base to check against.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_electric_field\", \"description\": \"Calculate the electric field produced by a charge at a certain distance.\", \"parameters\": {\"charge\": {\"description\": \"Charge in coulombs producing the electric field.\", \"type\": \"int\", \"default\": 8.854e-12}, \"distance\": {\"description\": \"Distance from the charge in meters where the field is being measured.\", \"type\": \"int\", \"default\": 8.854e-12}, \"permitivity\": {\"description\": \"Permitivity of the space where field is being calculated, default is 8.854e-12.\", \"type\": \"float\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"bacterial_growth\", \"description\": \"Calculates the bacterial population after a given time based on the initial population and growth rate.\", \"parameters\": {\"initial_population\": {\"description\": \"The initial bacterial population.\", \"type\": \"int\", \"default\": 20}, \"growth_rate\": {\"description\": \"The growth rate per unit time.\", \"type\": \"float\", \"default\": 20}, \"time\": {\"description\": \"The time elapsed.\", \"type\": \"float\"}, \"doubling_time\": {\"description\": \"The doubling time of the bacteria in minutes. Defaults to 20.\", \"type\": \"float, optional\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the median of the numbers 1, 2, 3, 4, and 5? Also, I want to find the final velocity of an object that starts with an initial velocity of 30 m/s, accelerates at 10 m/s^2 for 5 seconds.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"calculate_median\", \"arguments\": {\"numbers\": [1, 2, 3, 4, 5]}}, {\"name\": \"final_velocity\", \"arguments\": {\"initial_velocity\": 30, \"acceleration\": 10, \"time\": 5}}]",
"style": "rule"
}
|
{
"index": 69,
"split": "train"
}
|
[{"name": "predict_forest_area", "description": "Predicts the change in forest area over a specified number of years.", "parameters": {"location": {"description": "The geographic location for the prediction.", "type": "str"}, "num_years": {"description": "The number of years into the future to make the prediction.", "type": "int"}, "include_humans": {"description": "Whether to include the impact of human activities in the prediction. Defaults to False.", "type": "bool, optional"}}}, {"name": "is_leap_year", "description": "Checks if a year is a leap year.", "parameters": {"year": {"description": "The year to check.", "type": "int"}}}, {"name": "is_valid_email", "description": "Checks if an email address is valid.", "parameters": {"email": {"description": "The email address to validate.", "type": "str"}}}]
|
[
{
"from": "human",
"value": "I want to know the forest area change for the Arctic over the next 30 years and check if the year 2028 is a leap year."
}
] |
[{"name": "predict_forest_area", "arguments": {"location": "Arctic", "num_years": 30, "include_humans": false}}, {"name": "is_leap_year", "arguments": {"year": 2028}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"predict_forest_area\", \"description\": \"Predicts the change in forest area over a specified number of years.\", \"parameters\": {\"location\": {\"description\": \"The geographic location for the prediction.\", \"type\": \"str\"}, \"num_years\": {\"description\": \"The number of years into the future to make the prediction.\", \"type\": \"int\"}, \"include_humans\": {\"description\": \"Whether to include the impact of human activities in the prediction. Defaults to False.\", \"type\": \"bool, optional\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"is_leap_year\", \"description\": \"Checks if a year is a leap year.\", \"parameters\": {\"year\": {\"description\": \"The year to check.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"is_valid_email\", \"description\": \"Checks if an email address is valid.\", \"parameters\": {\"email\": {\"description\": \"The email address to validate.\", \"type\": \"str\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I want to know the forest area change for the Arctic over the next 30 years and check if the year 2028 is a leap year.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"predict_forest_area\", \"arguments\": {\"location\": \"Arctic\", \"num_years\": 30, \"include_humans\": false}}, {\"name\": \"is_leap_year\", \"arguments\": {\"year\": 2028}}]",
"style": "rule"
}
|
{
"index": 70,
"split": "train"
}
|
[{"name": "getmessage", "description": "Retrieves message details based on the provided message ID using the Toolbench RapidAPI service.", "parameters": {"message_id": {"description": "The unique identifier of the message to retrieve.", "type": "int", "default": ""}}}, {"name": "get_contacts", "description": "Retrieves all contacts using the provided API key and returns the response in either JSON or CSV format.", "parameters": {"p": {"description": "API Key from Sms77.io.", "type": "str", "default": ""}, "json": {"description": "Specifies whether to return the response in JSON format. If not provided, the response will be in CSV format.", "type": "str, optional", "default": ""}}}, {"name": "settag", "description": "Sets a new tag for the SMS receive service using the provided RapidAPI key.", "parameters": {"tag": {"description": "The value of the new tag, with a maximum length of 16 characters.", "type": "str", "default": ""}}}, {"name": "validatetest", "description": "Validate any phone number from any country using the given RapidAPI key.", "parameters": {"number": {"description": "Phone number to be validated. This can be provided in two formats:", "type": "str", "default": "+59894887766"}, "country": {"description": "ISO 3166-1 alpha-2 code of the country in capital letters. This is optional if the number parameter starts with the + symbol. Defaults to None.", "type": "str, optional", "default": ""}}}]
|
[
{
"from": "human",
"value": "Set a new tag 'promotion' for the SMS receive service and validate the phone number '+5678901234' from Canada."
}
] |
[{"name": "settag", "arguments": {"tag": "promotion"}}, {"name": "validatetest", "arguments": {"number": "+5678901234", "country": "CA"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"getmessage\", \"description\": \"Retrieves message details based on the provided message ID using the Toolbench RapidAPI service.\", \"parameters\": {\"message_id\": {\"description\": \"The unique identifier of the message to retrieve.\", \"type\": \"int\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_contacts\", \"description\": \"Retrieves all contacts using the provided API key and returns the response in either JSON or CSV format.\", \"parameters\": {\"p\": {\"description\": \"API Key from Sms77.io.\", \"type\": \"str\", \"default\": \"\"}, \"json\": {\"description\": \"Specifies whether to return the response in JSON format. If not provided, the response will be in CSV format.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"settag\", \"description\": \"Sets a new tag for the SMS receive service using the provided RapidAPI key.\", \"parameters\": {\"tag\": {\"description\": \"The value of the new tag, with a maximum length of 16 characters.\", \"type\": \"str\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"validatetest\", \"description\": \"Validate any phone number from any country using the given RapidAPI key.\", \"parameters\": {\"number\": {\"description\": \"Phone number to be validated. This can be provided in two formats:\", \"type\": \"str\", \"default\": \"+59894887766\"}, \"country\": {\"description\": \"ISO 3166-1 alpha-2 code of the country in capital letters. This is optional if the number parameter starts with the + symbol. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Set a new tag 'promotion' for the SMS receive service and validate the phone number '+5678901234' from Canada.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"settag\", \"arguments\": {\"tag\": \"promotion\"}}, {\"name\": \"validatetest\", \"arguments\": {\"number\": \"+5678901234\", \"country\": \"CA\"}}]",
"style": "rule"
}
|
{
"index": 71,
"split": "train"
}
|
[{"name": "market_get_compact", "description": "Fetch the most informative fields about indices, commodities, currencies, rates, and other market data.", "parameters": {"is_id": {"description": "A comma-separated string of market IDs returned from the `/market/auto-complete` endpoint.", "type": "str", "default": "adsmi:ind,aex:ind,co1:com,gc1:com"}}}, {"name": "transaction", "description": "Fetches full data for a specific transaction on the Optimism blockchain.", "parameters": {"hash": {"description": "The hash of the transaction to scan.", "type": "str", "default": "0xc3f239bae81d78c344f475955801bf2a491430009f171c34a4937dc89ad88d9f"}, "network": {"description": "The network to use (mainnet or testnet). Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "currency_options", "description": "Fetches currency options data for a specified stock using the Investing Financial Stocks API.", "parameters": {"slug": {"description": "The stock identifier slug to specify the stock for which currency options are to be retrieved.", "type": "str", "default": "usd-jpy"}}}]
|
[
{
"from": "human",
"value": "Fetch currency options for the stock identified by the slug 'TSLA'."
}
] |
[{"name": "currency_options", "arguments": {"slug": "TSLA"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"market_get_compact\", \"description\": \"Fetch the most informative fields about indices, commodities, currencies, rates, and other market data.\", \"parameters\": {\"is_id\": {\"description\": \"A comma-separated string of market IDs returned from the `/market/auto-complete` endpoint.\", \"type\": \"str\", \"default\": \"adsmi:ind,aex:ind,co1:com,gc1:com\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"transaction\", \"description\": \"Fetches full data for a specific transaction on the Optimism blockchain.\", \"parameters\": {\"hash\": {\"description\": \"The hash of the transaction to scan.\", \"type\": \"str\", \"default\": \"0xc3f239bae81d78c344f475955801bf2a491430009f171c34a4937dc89ad88d9f\"}, \"network\": {\"description\": \"The network to use (mainnet or testnet). Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"currency_options\", \"description\": \"Fetches currency options data for a specified stock using the Investing Financial Stocks API.\", \"parameters\": {\"slug\": {\"description\": \"The stock identifier slug to specify the stock for which currency options are to be retrieved.\", \"type\": \"str\", \"default\": \"usd-jpy\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch currency options for the stock identified by the slug 'TSLA'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"currency_options\", \"arguments\": {\"slug\": \"TSLA\"}}]",
"style": "rule"
}
|
{
"index": 72,
"split": "train"
}
|
[{"name": "get_signals", "description": "Fetches trading signals and trends for a specified cryptocurrency pair from the given exchange and market type.", "parameters": {"coin": {"description": "The cryptocurrency pair to get signals for (e.g., BTC, ETH, TRX).", "type": "str", "default": "BTC"}, "exchange": {"description": "The exchange to get signals from (e.g., Binance, Bybit, Huobi, Kucoin, Coinex, MXC, Gate).", "type": "str", "default": "Bybit"}, "market_type": {"description": "The market type to get signals for (e.g., SPOT, FUTURES).", "type": "str", "default": "SPOT"}}}, {"name": "get_bank_info", "description": "Fetches information about a bank using the provided routing number.", "parameters": {"routingnumber": {"description": "The routing number of the bank to lookup.", "type": "str", "default": "121000248"}, "format": {"description": "Defines the format of the response. Default value is 'json'. Possible values are 'xml' and 'json'.", "type": "str, optional", "default": "json"}, "paymenttype": {"description": "Specifies the type of payment information to retrieve. Default value is 'ach'. Possible values are 'ach' and 'wire'.", "type": "str, optional", "default": "ach"}}}, {"name": "get_the_next_dividend_payout_date", "description": "Fetches the next dividend payout date for a given stock ticker using the Sunday Finance API.", "parameters": {"ticker": {"description": "The stock ticker symbol to lookup for the next dividend payout date.", "type": "str", "default": "aapl"}}}, {"name": "history_prices", "description": "Fetches historical stock prices including Date, Open, High, Low, Close, Adj Close, and Volume for a given stock symbol over a specified range.", "parameters": {"range": {"description": "The time period for which to fetch stock prices. Choices are ['1y', '5y', 'max']. Defaults to '1y'.", "type": "str", "default": "1y"}, "symbol": {"description": "The ticker symbol of the company. Defaults to 'TSLA'.", "type": "str", "default": "TSLA"}}}]
|
[
{
"from": "human",
"value": "What are the trading signals and trends for BTC and ETH on Binance for both SPOT and FUTURES markets?"
}
] |
[{"name": "get_signals", "arguments": {"coin": "BTC", "exchange": "Binance", "market_type": "SPOT"}}, {"name": "get_signals", "arguments": {"coin": "BTC", "exchange": "Binance", "market_type": "FUTURES"}}, {"name": "get_signals", "arguments": {"coin": "ETH", "exchange": "Binance", "market_type": "SPOT"}}, {"name": "get_signals", "arguments": {"coin": "ETH", "exchange": "Binance", "market_type": "FUTURES"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_signals\", \"description\": \"Fetches trading signals and trends for a specified cryptocurrency pair from the given exchange and market type.\", \"parameters\": {\"coin\": {\"description\": \"The cryptocurrency pair to get signals for (e.g., BTC, ETH, TRX).\", \"type\": \"str\", \"default\": \"BTC\"}, \"exchange\": {\"description\": \"The exchange to get signals from (e.g., Binance, Bybit, Huobi, Kucoin, Coinex, MXC, Gate).\", \"type\": \"str\", \"default\": \"Bybit\"}, \"market_type\": {\"description\": \"The market type to get signals for (e.g., SPOT, FUTURES).\", \"type\": \"str\", \"default\": \"SPOT\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_bank_info\", \"description\": \"Fetches information about a bank using the provided routing number.\", \"parameters\": {\"routingnumber\": {\"description\": \"The routing number of the bank to lookup.\", \"type\": \"str\", \"default\": \"121000248\"}, \"format\": {\"description\": \"Defines the format of the response. Default value is 'json'. Possible values are 'xml' and 'json'.\", \"type\": \"str, optional\", \"default\": \"json\"}, \"paymenttype\": {\"description\": \"Specifies the type of payment information to retrieve. Default value is 'ach'. Possible values are 'ach' and 'wire'.\", \"type\": \"str, optional\", \"default\": \"ach\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_the_next_dividend_payout_date\", \"description\": \"Fetches the next dividend payout date for a given stock ticker using the Sunday Finance API.\", \"parameters\": {\"ticker\": {\"description\": \"The stock ticker symbol to lookup for the next dividend payout date.\", \"type\": \"str\", \"default\": \"aapl\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"history_prices\", \"description\": \"Fetches historical stock prices including Date, Open, High, Low, Close, Adj Close, and Volume for a given stock symbol over a specified range.\", \"parameters\": {\"range\": {\"description\": \"The time period for which to fetch stock prices. Choices are ['1y', '5y', 'max']. Defaults to '1y'.\", \"type\": \"str\", \"default\": \"1y\"}, \"symbol\": {\"description\": \"The ticker symbol of the company. Defaults to 'TSLA'.\", \"type\": \"str\", \"default\": \"TSLA\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What are the trading signals and trends for BTC and ETH on Binance for both SPOT and FUTURES markets?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_signals\", \"arguments\": {\"coin\": \"BTC\", \"exchange\": \"Binance\", \"market_type\": \"SPOT\"}}, {\"name\": \"get_signals\", \"arguments\": {\"coin\": \"BTC\", \"exchange\": \"Binance\", \"market_type\": \"FUTURES\"}}, {\"name\": \"get_signals\", \"arguments\": {\"coin\": \"ETH\", \"exchange\": \"Binance\", \"market_type\": \"SPOT\"}}, {\"name\": \"get_signals\", \"arguments\": {\"coin\": \"ETH\", \"exchange\": \"Binance\", \"market_type\": \"FUTURES\"}}]",
"style": "rule"
}
|
{
"index": 73,
"split": "train"
}
|
[{"name": "calculate_investment_return", "description": "Calculates the return on investment based on the initial deposit amount, annual interest rate, and investment period.", "parameters": {"initial_amount": {"description": "The initial deposit amount.", "type": "int"}, "interest_rate": {"description": "The annual interest rate provided by the bank.", "type": "float"}, "num_years": {"description": "The number of years the money is invested.", "type": "int"}}}, {"name": "integrate", "description": "Calculate the area under a curve for a specified function between two x values.", "parameters": {"function": {"description": "The function to integrate, represented as a string. For example, 'x^3'", "type": "str", "default": "trapezoid"}, "start_x": {"description": "The starting x-value to integrate over.", "type": "int", "default": "trapezoid"}, "end_x": {"description": "The ending x-value to integrate over.", "type": "int"}, "method": {"description": "The method of numerical integration to use. Choices are 'trapezoid' or 'simpson'.", "type": "str"}}}, {"name": "is_power_of_two", "description": "Checks if a number is a power of two.", "parameters": {"num": {"description": "The number to check.", "type": "int"}}}, {"name": "find_next_greater_element", "description": "Finds the next greater element for each element in a list.", "parameters": {"nums": {"description": "The list of numbers.", "type": "List[int]"}}}, {"name": "probability_of_consecutive_rolls", "description": "Calculates the probability of rolling a specific value on a die consecutively for a given number of rolls.", "parameters": {"target_value": {"description": "The desired value to be rolled.", "type": "int", "default": 6}, "num_rolls": {"description": "The number of consecutive rolls.", "type": "int", "default": 6}, "num_sides": {"description": "The number of sides on the die. Defaults to 6.", "type": "int, optional"}}}]
|
[
{
"from": "human",
"value": "Calculate the probability of rolling a 6 on a six-sided die three times consecutively."
}
] |
[{"name": "probability_of_consecutive_rolls", "arguments": {"target_value": 6, "num_rolls": 3}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_investment_return\", \"description\": \"Calculates the return on investment based on the initial deposit amount, annual interest rate, and investment period.\", \"parameters\": {\"initial_amount\": {\"description\": \"The initial deposit amount.\", \"type\": \"int\"}, \"interest_rate\": {\"description\": \"The annual interest rate provided by the bank.\", \"type\": \"float\"}, \"num_years\": {\"description\": \"The number of years the money is invested.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"integrate\", \"description\": \"Calculate the area under a curve for a specified function between two x values.\", \"parameters\": {\"function\": {\"description\": \"The function to integrate, represented as a string. For example, 'x^3'\", \"type\": \"str\", \"default\": \"trapezoid\"}, \"start_x\": {\"description\": \"The starting x-value to integrate over.\", \"type\": \"int\", \"default\": \"trapezoid\"}, \"end_x\": {\"description\": \"The ending x-value to integrate over.\", \"type\": \"int\"}, \"method\": {\"description\": \"The method of numerical integration to use. Choices are 'trapezoid' or 'simpson'.\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"is_power_of_two\", \"description\": \"Checks if a number is a power of two.\", \"parameters\": {\"num\": {\"description\": \"The number to check.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"find_next_greater_element\", \"description\": \"Finds the next greater element for each element in a list.\", \"parameters\": {\"nums\": {\"description\": \"The list of numbers.\", \"type\": \"List[int]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"probability_of_consecutive_rolls\", \"description\": \"Calculates the probability of rolling a specific value on a die consecutively for a given number of rolls.\", \"parameters\": {\"target_value\": {\"description\": \"The desired value to be rolled.\", \"type\": \"int\", \"default\": 6}, \"num_rolls\": {\"description\": \"The number of consecutive rolls.\", \"type\": \"int\", \"default\": 6}, \"num_sides\": {\"description\": \"The number of sides on the die. Defaults to 6.\", \"type\": \"int, optional\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Calculate the probability of rolling a 6 on a six-sided die three times consecutively.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"probability_of_consecutive_rolls\", \"arguments\": {\"target_value\": 6, \"num_rolls\": 3}}]",
"style": "rule"
}
|
{
"index": 74,
"split": "train"
}
|
[{"name": "stays_auto_complete", "description": "Fetches auto-complete suggestions for stays based on a given location.", "parameters": {"location": {"description": "The location for which to get auto-complete suggestions.", "type": "str", "default": "ch"}, "language_code": {"description": "The language code for the results. Defaults to 'en-us'.", "type": "str, optional", "default": "en-us"}}}, {"name": "get_category", "description": "Fetches categories from the Airbnb API, optionally in a specified language.", "parameters": {"languageid": {"description": "The ID of the language in which the response should be returned. To obtain the language ID, use the `getLanguages` API.", "type": "str, optional", "default": ""}}}, {"name": "bus_trolley_locations", "description": "Retrieves the current bus and trolley locations for a specified route.", "parameters": {"route": {"description": "The route identifier for which to retrieve bus and trolley locations.", "type": "str", "default": "17"}}}, {"name": "airport_info", "description": "Fetches and returns detailed information about an airport using its IATA code from the Airports Info API.", "parameters": {"iata": {"description": "The IATA code of the airport for which information is being requested.", "type": "str", "default": "JFK"}}}]
|
[
{
"from": "human",
"value": "What is the current location of buses and trolleys on route 12 in Philadelphia? Can you also provide information about the airport with IATA code LHR?"
}
] |
[{"name": "bus_trolley_locations", "arguments": {"route": "12"}}, {"name": "airport_info", "arguments": {"iata": "LHR"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"stays_auto_complete\", \"description\": \"Fetches auto-complete suggestions for stays based on a given location.\", \"parameters\": {\"location\": {\"description\": \"The location for which to get auto-complete suggestions.\", \"type\": \"str\", \"default\": \"ch\"}, \"language_code\": {\"description\": \"The language code for the results. Defaults to 'en-us'.\", \"type\": \"str, optional\", \"default\": \"en-us\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_category\", \"description\": \"Fetches categories from the Airbnb API, optionally in a specified language.\", \"parameters\": {\"languageid\": {\"description\": \"The ID of the language in which the response should be returned. To obtain the language ID, use the `getLanguages` API.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"bus_trolley_locations\", \"description\": \"Retrieves the current bus and trolley locations for a specified route.\", \"parameters\": {\"route\": {\"description\": \"The route identifier for which to retrieve bus and trolley locations.\", \"type\": \"str\", \"default\": \"17\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"airport_info\", \"description\": \"Fetches and returns detailed information about an airport using its IATA code from the Airports Info API.\", \"parameters\": {\"iata\": {\"description\": \"The IATA code of the airport for which information is being requested.\", \"type\": \"str\", \"default\": \"JFK\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the current location of buses and trolleys on route 12 in Philadelphia? Can you also provide information about the airport with IATA code LHR?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"bus_trolley_locations\", \"arguments\": {\"route\": \"12\"}}, {\"name\": \"airport_info\", \"arguments\": {\"iata\": \"LHR\"}}]",
"style": "rule"
}
|
{
"index": 75,
"split": "train"
}
|
[{"name": "v3_auto_complete", "description": "Fetches auto-suggestions based on a given symbol or company name using the RapidAPI Fidelity Investments endpoint.", "parameters": {"q": {"description": "Symbol or company name for which to fetch auto-suggestions.", "type": "str", "default": "apple"}}}]
|
[
{
"from": "human",
"value": "I need suggestions for 'GOOG' and 'AMZN' symbols, please."
}
] |
[{"name": "v3_auto_complete", "arguments": {"q": "GOOG"}}, {"name": "v3_auto_complete", "arguments": {"q": "AMZN"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"v3_auto_complete\", \"description\": \"Fetches auto-suggestions based on a given symbol or company name using the RapidAPI Fidelity Investments endpoint.\", \"parameters\": {\"q\": {\"description\": \"Symbol or company name for which to fetch auto-suggestions.\", \"type\": \"str\", \"default\": \"apple\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I need suggestions for 'GOOG' and 'AMZN' symbols, please.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"v3_auto_complete\", \"arguments\": {\"q\": \"GOOG\"}}, {\"name\": \"v3_auto_complete\", \"arguments\": {\"q\": \"AMZN\"}}]",
"style": "rule"
}
|
{
"index": 76,
"split": "train"
}
|
[{"name": "facilities_lookup", "description": "Fetch a list of facilities in Cameroon based on provided query parameters.", "parameters": {"type": {"description": "The type of facility to search for (e.g., hospital, bank, college). Refer to the OpenStreetMap Map features for more options.", "type": "str", "default": "hospital"}, "region": {"description": "The region where the facility is located.", "type": "str", "default": "littoral"}, "city": {"description": "The city where the facility is located. Default is 'douala'.", "type": "str, optional", "default": "douala"}, "limit": {"description": "The maximum number of facilities to return. Default is 10.", "type": "int, optional", "default": "10"}}}, {"name": "measure_distance", "description": "Calculates the distance between two geographical locations specified by their latitude and longitude coordinates.", "parameters": {"lat1": {"description": "Latitude of the first location.", "type": "int", "default": "6.465422"}, "lon1": {"description": "Longitude of the first location.", "type": "int", "default": "3.406448"}, "lon2": {"description": "Longitude of the second location.", "type": "int", "default": "8.6753"}, "lat2": {"description": "Latitude of the second location.", "type": "int", "default": "9.0820"}, "unit": {"description": "Unit of distance measurement. Valid options are 'km' (default), 'mi', 'ft', and 'yd'.", "type": "str, optional", "default": "km"}}}, {"name": "directions_between_2_locations", "description": "Fetches the route information between two geographical locations including distance, duration, and steps.", "parameters": {"start_lon": {"description": "Longitude of the starting point (required).", "type": "int", "default": "-16.0755888102153"}, "end_lon": {"description": "Longitude of the ending point (required).", "type": "int", "default": "-17.447938"}, "end_lat": {"description": "Latitude of the ending point (required).", "type": "int", "default": "14.693425"}, "start_lat": {"description": "Latitude of the starting point (required).", "type": "int", "default": "14.14129815"}, "distance_unit": {"description": "Unit of distance measurement, valid options are 'km' (default) and 'mi'.", "type": "str, optional", "default": "km"}}}]
|
[
{
"from": "human",
"value": "Get driving directions from Dakar (14.7164° N, 17.4746° W) to Saint-Louis (16.0236° N, 16.4854° W) in kilometers."
}
] |
[{"name": "directions_between_2_locations", "arguments": {"start_lon": -17, "end_lon": -16, "end_lat": 16, "start_lat": 14, "distance_unit": "km"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"facilities_lookup\", \"description\": \"Fetch a list of facilities in Cameroon based on provided query parameters.\", \"parameters\": {\"type\": {\"description\": \"The type of facility to search for (e.g., hospital, bank, college). Refer to the OpenStreetMap Map features for more options.\", \"type\": \"str\", \"default\": \"hospital\"}, \"region\": {\"description\": \"The region where the facility is located.\", \"type\": \"str\", \"default\": \"littoral\"}, \"city\": {\"description\": \"The city where the facility is located. Default is 'douala'.\", \"type\": \"str, optional\", \"default\": \"douala\"}, \"limit\": {\"description\": \"The maximum number of facilities to return. Default is 10.\", \"type\": \"int, optional\", \"default\": \"10\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"measure_distance\", \"description\": \"Calculates the distance between two geographical locations specified by their latitude and longitude coordinates.\", \"parameters\": {\"lat1\": {\"description\": \"Latitude of the first location.\", \"type\": \"int\", \"default\": \"6.465422\"}, \"lon1\": {\"description\": \"Longitude of the first location.\", \"type\": \"int\", \"default\": \"3.406448\"}, \"lon2\": {\"description\": \"Longitude of the second location.\", \"type\": \"int\", \"default\": \"8.6753\"}, \"lat2\": {\"description\": \"Latitude of the second location.\", \"type\": \"int\", \"default\": \"9.0820\"}, \"unit\": {\"description\": \"Unit of distance measurement. Valid options are 'km' (default), 'mi', 'ft', and 'yd'.\", \"type\": \"str, optional\", \"default\": \"km\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"directions_between_2_locations\", \"description\": \"Fetches the route information between two geographical locations including distance, duration, and steps.\", \"parameters\": {\"start_lon\": {\"description\": \"Longitude of the starting point (required).\", \"type\": \"int\", \"default\": \"-16.0755888102153\"}, \"end_lon\": {\"description\": \"Longitude of the ending point (required).\", \"type\": \"int\", \"default\": \"-17.447938\"}, \"end_lat\": {\"description\": \"Latitude of the ending point (required).\", \"type\": \"int\", \"default\": \"14.693425\"}, \"start_lat\": {\"description\": \"Latitude of the starting point (required).\", \"type\": \"int\", \"default\": \"14.14129815\"}, \"distance_unit\": {\"description\": \"Unit of distance measurement, valid options are 'km' (default) and 'mi'.\", \"type\": \"str, optional\", \"default\": \"km\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Get driving directions from Dakar (14.7164° N, 17.4746° W) to Saint-Louis (16.0236° N, 16.4854° W) in kilometers.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"directions_between_2_locations\", \"arguments\": {\"start_lon\": -17, \"end_lon\": -16, \"end_lat\": 16, \"start_lat\": 14, \"distance_unit\": \"km\"}}]",
"style": "rule"
}
|
{
"index": 77,
"split": "train"
}
|
[{"name": "/people", "description": "Get a list of random generated fake people data.", "parameters": {"type": "dict", "properties": {}, "required": []}, "required": null}, {"name": "Get Sub Regions", "description": "Retrieve a list of sub-regions for a given region", "parameters": {"type": "dict", "properties": {"region": {"description": "The name of the region for which to retrieve sub-regions", "type": "string", "default": "americas"}}, "required": ["region"]}, "required": null}, {"name": "Technology Usage Lookup", "description": "Retrieve technology usage information for a given domain", "parameters": {"type": "dict", "properties": {"lookup": {"description": "The domain or domains to lookup technology usage for", "type": "string"}, "key": {"description": "Your API key for authentication", "type": "string"}}, "required": ["lookup", "key"]}, "required": null}, {"name": "List of Countries by Income Level", "description": "Retrieves a list of countries grouped by income level, sourced from the World Bank Group.", "parameters": {"type": "dict", "properties": {}, "required": []}, "required": null}, {"name": "GetNewsletters", "description": "Retrieve a list of Power BI newsletters", "parameters": {"type": "dict", "properties": {"start_string": {"description": "The start string of the string range for which to retrieve newsletters", "type": "string"}, "end_string": {"description": "The end string of the string range for which to retrieve newsletters", "type": "string"}, "category": {"description": "The category of newsletters to retrieve (e.g., 'announcements', 'tips', etc.)", "type": "string"}}, "required": ["start_string", "end_string"]}, "required": null}]
|
[
{
"from": "human",
"value": "Can you provide me with a list of countries categorized by their income levels? I need this data to prepare for an upcoming presentation on global economic development."
},
{
"from": "function_call",
"value": "[{\"name\": \"List of Countries by Income Level\", \"arguments\": {}}]"
},
{
"from": "observation",
"value": "[{\"name\": \"List of Countries by Income Level\", \"results\": {\"countries\": [{\"country\": \"United States\", \"incomeLevel\": \"High\"}, {\"country\": \"Germany\", \"incomeLevel\": \"High\"}, {\"country\": \"Brazil\", \"incomeLevel\": \"Upper middle\"}, {\"country\": \"India\", \"incomeLevel\": \"Lower middle\"}, {\"country\": \"Nigeria\", \"incomeLevel\": \"Low\"}]}}]"
},
{
"from": "gpt",
"value": "Here's the list of countries categorized by their income levels suitable for your presentation on global economic development:\n\n1. **High Income**\n - United States\n - Germany\n\n2. **Upper Middle Income**\n - Brazil\n\n3. **Lower Middle Income**\n - India\n\n4. **Low Income**\n - Nigeria\n\nYou can use this information to enhance your presentation with global economic perspectives based on income levels. If you need further details or additional data, feel free to ask!"
},
{
"from": "human",
"value": "Absolutely fascinating to see how economic levels can influence the global stage! Pivoting a bit, have you noticed any specific trends in how different income level countries adopt technology differently? This interplay between economics and technological shifts is quite the spine-tingling topic for my upcoming discussions!"
},
{
"from": "gpt",
"value": "The relationship between a country's income level and its technology adoption is indeed a complex and intriguing topic. While specific data would require a detailed analysis, some general trends could be highlighted based on global observations:\n\n1. **High-Income Countries**:\n - Typically, these countries exhibit high levels of technology adoption across various sectors, primarily due to better infrastructure, higher education levels, and more substantial financial resources.\n - They are often leaders in developing new technologies, including artificial intelligence, robotics, and green technologies.\n\n2. **Upper-Middle-Income Countries**:\n - These countries often show rapid technology adoption, particularly in tech that improves industrial productivity and economic diversification.\n - They may not innovate at the rate of high-income countries but make significant investments in technology to boost economic sectors.\n\n3. **Lower-Middle-Income and Low-Income Countries**:\n - Technology adoption can vary widely, often focused on mobile technology and internet access due to immediate impacts on communication and small-scale commerce.\n - Lower-middle-income countries might start investing in broader technological infrastructure as part of development programs, whereas low-income countries may still be struggling with basic issues like consistent electricity access.\n\nThese trends are increasingly influenced by global initiatives that aim to reduce the digital divide and promote inclusive access to technology, ensuring that economic development is balanced with technological growth.\n\nIf you need a more tailored analysis or specific examples of technology adoption in these income categories, I can help gather detailed data or look up specific instances that illustrate these trends."
},
{
"from": "human",
"value": "Could you help me understand the main technologies used by websites in high-income countries? Let's start with a lookup for 'apple.com' and 'bmw.com' — I am particularly interested in catching trends that might be prevalent in their digital footprints."
},
{
"from": "gpt",
"value": "To proceed with retrieving the technology usage data for 'apple.com' and 'bmw.com', an API key is required for authentication purposes. Unfortunately, I don't have the capability to generate or access such keys. If you have an API key, or can obtain one, I can assist you with using it to fetch the desired information. Please provide the API key or let me know how you'd like to proceed!"
},
{
"from": "human",
"value": "Got it! I'll see if my tech team can provide an API key shortly. Meanwhile, could we pivot and fetch some latest articles on technological trends in high-income countries? This might give us additional insights until we sort out the API key issue."
},
{
"from": "gpt",
"value": "Based on recent trends and reports, technological adoption and trends in high-income countries for 2024 highlight several key areas:\n\n1. **Artificial Intelligence (AI) and Machine Learning**: AI adoption is transforming various sectors, from healthcare to finance. The widespread implementation of AI technologies is expected to continue growing, significantly impacting productivity and innovation across industries.\n\n2. **Cloud Technologies**: Cloud computing remains a cornerstone for businesses aiming to enhance scalability, security, and cost-efficiency. Roles like Cloud Solutions Architect and Cloud Security Engineer are in high demand, with salaries reflecting their importance in maintaining robust cloud infrastructures.\n\n3. **Blockchain and Cybersecurity**: The increasing need for secure online transactions has spurred the demand for Blockchain Software Engineers and Information Security Analysts. These roles are crucial in developing secure frameworks to protect data and ensure compliance with evolving security standards.\n\n4. **Economic and Employment Trends**: Despite resilient growth in some high-income countries, there are notable challenges such as inflation risks and economic divergences. Labor markets have shown resilience, yet disparities in employment and income inequality persist. Addressing these issues requires targeted policy interventions to ensure sustainable and inclusive growth.\n\n5. **Salaries and Job Markets**: High-income countries, particularly cities like San Jose and San Francisco, offer lucrative salaries for IT professionals, driven by their central role in global tech ecosystems. These regions are synonymous with innovation, providing extensive networking and career advancement opportunities.\n\nFor more detailed insights, you can explore the reports from sources like the International Monetary Fund (IMF), International Labour Organization (ILO), and industry-specific analyses from Splunk.\n\nIf you need further information or specific examples, feel free to ask!"
},
{
"from": "human",
"value": "Indeed, your insights are illuminating. Now, could you fetch some newsletters on the latest technological trends from stating from 'A' to 'H'? Let's focus on the 'updates' category this time."
}
] |
[{"name": "GetNewsletters", "arguments": {"start_string": "A", "end_string": "H", "category": "updates"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections.
Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections.\nHere is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"/people\", \"description\": \"Get a list of random generated fake people data.\", \"parameters\": {\"type\": \"dict\", \"properties\": {}, \"required\": []}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Get Sub Regions\", \"description\": \"Retrieve a list of sub-regions for a given region\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"region\": {\"description\": \"The name of the region for which to retrieve sub-regions\", \"type\": \"string\", \"default\": \"americas\"}}, \"required\": [\"region\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"Technology Usage Lookup\", \"description\": \"Retrieve technology usage information for a given domain\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"lookup\": {\"description\": \"The domain or domains to lookup technology usage for\", \"type\": \"string\"}, \"key\": {\"description\": \"Your API key for authentication\", \"type\": \"string\"}}, \"required\": [\"lookup\", \"key\"]}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"List of Countries by Income Level\", \"description\": \"Retrieves a list of countries grouped by income level, sourced from the World Bank Group.\", \"parameters\": {\"type\": \"dict\", \"properties\": {}, \"required\": []}, \"required\": null}}\n{\"type\": \"function\", \"function\": {\"name\": \"GetNewsletters\", \"description\": \"Retrieve a list of Power BI newsletters\", \"parameters\": {\"type\": \"dict\", \"properties\": {\"start_string\": {\"description\": \"The start string of the string range for which to retrieve newsletters\", \"type\": \"string\"}, \"end_string\": {\"description\": \"The end string of the string range for which to retrieve newsletters\", \"type\": \"string\"}, \"category\": {\"description\": \"The category of newsletters to retrieve (e.g., 'announcements', 'tips', etc.)\", \"type\": \"string\"}}, \"required\": [\"start_string\", \"end_string\"]}, \"required\": null}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Can you provide me with a list of countries categorized by their income levels? I need this data to prepare for an upcoming presentation on global economic development.",
"role": "user"
},
{
"content": "\"[{\\\"name\\\": \\\"List of Countries by Income Level\\\", \\\"arguments\\\": {}}]\"",
"role": "assistant"
},
{
"content": "[{\"name\": \"List of Countries by Income Level\", \"results\": {\"countries\": [{\"country\": \"United States\", \"incomeLevel\": \"High\"}, {\"country\": \"Germany\", \"incomeLevel\": \"High\"}, {\"country\": \"Brazil\", \"incomeLevel\": \"Upper middle\"}, {\"country\": \"India\", \"incomeLevel\": \"Lower middle\"}, {\"country\": \"Nigeria\", \"incomeLevel\": \"Low\"}]}}]",
"role": "tool"
},
{
"content": "Here's the list of countries categorized by their income levels suitable for your presentation on global economic development:\n\n1. **High Income**\n - United States\n - Germany\n\n2. **Upper Middle Income**\n - Brazil\n\n3. **Lower Middle Income**\n - India\n\n4. **Low Income**\n - Nigeria\n\nYou can use this information to enhance your presentation with global economic perspectives based on income levels. If you need further details or additional data, feel free to ask!",
"role": "assistant"
},
{
"content": "Absolutely fascinating to see how economic levels can influence the global stage! Pivoting a bit, have you noticed any specific trends in how different income level countries adopt technology differently? This interplay between economics and technological shifts is quite the spine-tingling topic for my upcoming discussions!",
"role": "user"
},
{
"content": "The relationship between a country's income level and its technology adoption is indeed a complex and intriguing topic. While specific data would require a detailed analysis, some general trends could be highlighted based on global observations:\n\n1. **High-Income Countries**:\n - Typically, these countries exhibit high levels of technology adoption across various sectors, primarily due to better infrastructure, higher education levels, and more substantial financial resources.\n - They are often leaders in developing new technologies, including artificial intelligence, robotics, and green technologies.\n\n2. **Upper-Middle-Income Countries**:\n - These countries often show rapid technology adoption, particularly in tech that improves industrial productivity and economic diversification.\n - They may not innovate at the rate of high-income countries but make significant investments in technology to boost economic sectors.\n\n3. **Lower-Middle-Income and Low-Income Countries**:\n - Technology adoption can vary widely, often focused on mobile technology and internet access due to immediate impacts on communication and small-scale commerce.\n - Lower-middle-income countries might start investing in broader technological infrastructure as part of development programs, whereas low-income countries may still be struggling with basic issues like consistent electricity access.\n\nThese trends are increasingly influenced by global initiatives that aim to reduce the digital divide and promote inclusive access to technology, ensuring that economic development is balanced with technological growth.\n\nIf you need a more tailored analysis or specific examples of technology adoption in these income categories, I can help gather detailed data or look up specific instances that illustrate these trends.",
"role": "assistant"
},
{
"content": "Could you help me understand the main technologies used by websites in high-income countries? Let's start with a lookup for 'apple.com' and 'bmw.com' — I am particularly interested in catching trends that might be prevalent in their digital footprints.",
"role": "user"
},
{
"content": "To proceed with retrieving the technology usage data for 'apple.com' and 'bmw.com', an API key is required for authentication purposes. Unfortunately, I don't have the capability to generate or access such keys. If you have an API key, or can obtain one, I can assist you with using it to fetch the desired information. Please provide the API key or let me know how you'd like to proceed!",
"role": "assistant"
},
{
"content": "Got it! I'll see if my tech team can provide an API key shortly. Meanwhile, could we pivot and fetch some latest articles on technological trends in high-income countries? This might give us additional insights until we sort out the API key issue.",
"role": "user"
},
{
"content": "Based on recent trends and reports, technological adoption and trends in high-income countries for 2024 highlight several key areas:\n\n1. **Artificial Intelligence (AI) and Machine Learning**: AI adoption is transforming various sectors, from healthcare to finance. The widespread implementation of AI technologies is expected to continue growing, significantly impacting productivity and innovation across industries.\n\n2. **Cloud Technologies**: Cloud computing remains a cornerstone for businesses aiming to enhance scalability, security, and cost-efficiency. Roles like Cloud Solutions Architect and Cloud Security Engineer are in high demand, with salaries reflecting their importance in maintaining robust cloud infrastructures.\n\n3. **Blockchain and Cybersecurity**: The increasing need for secure online transactions has spurred the demand for Blockchain Software Engineers and Information Security Analysts. These roles are crucial in developing secure frameworks to protect data and ensure compliance with evolving security standards.\n\n4. **Economic and Employment Trends**: Despite resilient growth in some high-income countries, there are notable challenges such as inflation risks and economic divergences. Labor markets have shown resilience, yet disparities in employment and income inequality persist. Addressing these issues requires targeted policy interventions to ensure sustainable and inclusive growth.\n\n5. **Salaries and Job Markets**: High-income countries, particularly cities like San Jose and San Francisco, offer lucrative salaries for IT professionals, driven by their central role in global tech ecosystems. These regions are synonymous with innovation, providing extensive networking and career advancement opportunities.\n\nFor more detailed insights, you can explore the reports from sources like the International Monetary Fund (IMF), International Labour Organization (ILO), and industry-specific analyses from Splunk.\n\nIf you need further information or specific examples, feel free to ask!",
"role": "assistant"
},
{
"content": "Indeed, your insights are illuminating. Now, could you fetch some newsletters on the latest technological trends from stating from 'A' to 'H'? Let's focus on the 'updates' category this time.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"GetNewsletters\", \"arguments\": {\"start_string\": \"A\", \"end_string\": \"H\", \"category\": \"updates\"}}]",
"style": "rule"
}
|
{
"index": 78,
"split": "train"
}
|
[{"name": "retrieve_rewards", "description": "Retrieve the bid rewards for a specific collection using Blur API.", "parameters": {"slug": {"description": "The identifier for the specific collection to retrieve rewards for.", "type": "str", "default": "nakamigos"}}}, {"name": "top_property_managers", "description": "Fetches and returns information about the largest property managers for a given location from the AirDNA API.", "parameters": {"location": {"description": "The location to query for the top property managers.", "type": "str", "default": "santa monica"}}}, {"name": "top_free_mac_apps", "description": "Fetches a list of the top free Mac apps from the RapidAPI App Store.", "parameters": {"lang": {"description": "The language for the app descriptions. Default is 'en'.", "type": "str", "default": "en"}, "category": {"description": "The category ID for the apps. Default is '6016'.", "type": "str", "default": "6016"}, "country": {"description": "The country code for the App Store. Default is 'us'.", "type": "str", "default": "us"}, "num": {"description": "The number of results to return. Default is 100. Maximum is 200.", "type": "int", "default": "100"}}}, {"name": "calculate_grid_coordinate_points", "description": "Calculate all grid coordinate points based on a center geocoordinate point and distance arguments.", "parameters": {"radius": {"description": "The distance between coordinate points (on the same row/column in the grid). The units of the radius are determined by the `radius_units` parameter. Allowed values are 0.1-100. Default is 1.", "type": "str", "default": "1"}, "lng": {"description": "Grid center coordinate point longitude value.", "type": "str", "default": "-121.938314"}, "grid_size": {"description": "The size of the grid (e.g., 3x3, 5x5, 7x7, etc). Allowed values are 3, 5, 7, 9, 11, 13, 15.", "type": "str", "default": "3"}, "lat": {"description": "Grid center coordinate point latitude value.", "type": "str", "default": "37.341759"}, "radius_units": {"description": "Distance measurement units for the radius parameter. Allowed values are 'km' for kilometers and 'mi' for miles. Default is 'km'.", "type": "str, optional", "default": ""}}}]
|
[
{
"from": "human",
"value": "Calculate the grid coordinate points with a 10km radius and a 5x5 grid size centered at (40.7128° N, 74.0060° W)."
}
] |
[{"name": "calculate_grid_coordinate_points", "arguments": {"radius": "10", "lng": "-74.0060", "grid_size": "5", "lat": "40.7128", "radius_units": "km"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"retrieve_rewards\", \"description\": \"Retrieve the bid rewards for a specific collection using Blur API.\", \"parameters\": {\"slug\": {\"description\": \"The identifier for the specific collection to retrieve rewards for.\", \"type\": \"str\", \"default\": \"nakamigos\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"top_property_managers\", \"description\": \"Fetches and returns information about the largest property managers for a given location from the AirDNA API.\", \"parameters\": {\"location\": {\"description\": \"The location to query for the top property managers.\", \"type\": \"str\", \"default\": \"santa monica\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"top_free_mac_apps\", \"description\": \"Fetches a list of the top free Mac apps from the RapidAPI App Store.\", \"parameters\": {\"lang\": {\"description\": \"The language for the app descriptions. Default is 'en'.\", \"type\": \"str\", \"default\": \"en\"}, \"category\": {\"description\": \"The category ID for the apps. Default is '6016'.\", \"type\": \"str\", \"default\": \"6016\"}, \"country\": {\"description\": \"The country code for the App Store. Default is 'us'.\", \"type\": \"str\", \"default\": \"us\"}, \"num\": {\"description\": \"The number of results to return. Default is 100. Maximum is 200.\", \"type\": \"int\", \"default\": \"100\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_grid_coordinate_points\", \"description\": \"Calculate all grid coordinate points based on a center geocoordinate point and distance arguments.\", \"parameters\": {\"radius\": {\"description\": \"The distance between coordinate points (on the same row/column in the grid). The units of the radius are determined by the `radius_units` parameter. Allowed values are 0.1-100. Default is 1.\", \"type\": \"str\", \"default\": \"1\"}, \"lng\": {\"description\": \"Grid center coordinate point longitude value.\", \"type\": \"str\", \"default\": \"-121.938314\"}, \"grid_size\": {\"description\": \"The size of the grid (e.g., 3x3, 5x5, 7x7, etc). Allowed values are 3, 5, 7, 9, 11, 13, 15.\", \"type\": \"str\", \"default\": \"3\"}, \"lat\": {\"description\": \"Grid center coordinate point latitude value.\", \"type\": \"str\", \"default\": \"37.341759\"}, \"radius_units\": {\"description\": \"Distance measurement units for the radius parameter. Allowed values are 'km' for kilometers and 'mi' for miles. Default is 'km'.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Calculate the grid coordinate points with a 10km radius and a 5x5 grid size centered at (40.7128° N, 74.0060° W).",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"calculate_grid_coordinate_points\", \"arguments\": {\"radius\": \"10\", \"lng\": \"-74.0060\", \"grid_size\": \"5\", \"lat\": \"40.7128\", \"radius_units\": \"km\"}}]",
"style": "rule"
}
|
{
"index": 79,
"split": "train"
}
|
[{"name": "get_data_and_story", "description": "Fetches data and story for a given Snapchat username using the RapidAPI service.", "parameters": {"user": {"description": "The Snapchat username for which to fetch the data and story.", "type": "str", "default": "ysyn_lny"}}}]
|
[
{
"from": "human",
"value": "Could you get the data and story for snapchat user 'kimkardashian'?"
}
] |
[{"name": "get_data_and_story", "arguments": {"user": "kimkardashian"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_data_and_story\", \"description\": \"Fetches data and story for a given Snapchat username using the RapidAPI service.\", \"parameters\": {\"user\": {\"description\": \"The Snapchat username for which to fetch the data and story.\", \"type\": \"str\", \"default\": \"ysyn_lny\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Could you get the data and story for snapchat user 'kimkardashian'?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_data_and_story\", \"arguments\": {\"user\": \"kimkardashian\"}}]",
"style": "rule"
}
|
{
"index": 80,
"split": "train"
}
|
[{"name": "find_peak_element", "description": "Finds a peak element in a list of integers.", "parameters": {"nums": {"description": "The list of integers.", "type": "List[int]"}}}, {"name": "calculate_angle", "description": "Calculates the angle between the hour and minute hands of a clock.", "parameters": {"hour": {"description": "The hour value (1-12).", "type": "int"}, "minute": {"description": "The minute value (0-59).", "type": "int"}}}, {"name": "dice_roll_probability", "description": "Calculates the probability of rolling a specific sum with a given number of dice, each having a certain number of faces.", "parameters": {"target_sum": {"description": "The target sum to calculate the probability for.", "type": "int", "default": 6}, "num_dice": {"description": "The number of dice being rolled.", "type": "int", "default": 6}, "num_faces": {"description": "The number of faces on each die. Defaults to 6.", "type": "int, optional"}}}, {"name": "displacement", "description": "Calculates the displacement of an object given its initial velocity, acceleration, and time.", "parameters": {"initial_velocity": {"description": "The initial velocity of the object.", "type": "float"}, "acceleration": {"description": "The acceleration of the object.", "type": "float"}, "time": {"description": "The time elapsed.", "type": "float"}}}, {"name": "batting_average", "description": "Calculates the batting average of a baseball player based on the number of hits and at-bats.", "parameters": {"num_hits": {"description": "The number of hits.", "type": "int", "default": 3}, "num_at_bats": {"description": "The number of at-bats.", "type": "int", "default": 3}, "precision": {"description": "The number of decimal places to round the batting average. Defaults to 3.", "type": "int, optional"}}}]
|
[
{
"from": "human",
"value": "What is the probability of rolling a sum of 8 with 3 dice?"
}
] |
[{"name": "dice_roll_probability", "arguments": {"target_sum": 8, "num_dice": 3}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"find_peak_element\", \"description\": \"Finds a peak element in a list of integers.\", \"parameters\": {\"nums\": {\"description\": \"The list of integers.\", \"type\": \"List[int]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_angle\", \"description\": \"Calculates the angle between the hour and minute hands of a clock.\", \"parameters\": {\"hour\": {\"description\": \"The hour value (1-12).\", \"type\": \"int\"}, \"minute\": {\"description\": \"The minute value (0-59).\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"dice_roll_probability\", \"description\": \"Calculates the probability of rolling a specific sum with a given number of dice, each having a certain number of faces.\", \"parameters\": {\"target_sum\": {\"description\": \"The target sum to calculate the probability for.\", \"type\": \"int\", \"default\": 6}, \"num_dice\": {\"description\": \"The number of dice being rolled.\", \"type\": \"int\", \"default\": 6}, \"num_faces\": {\"description\": \"The number of faces on each die. Defaults to 6.\", \"type\": \"int, optional\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"displacement\", \"description\": \"Calculates the displacement of an object given its initial velocity, acceleration, and time.\", \"parameters\": {\"initial_velocity\": {\"description\": \"The initial velocity of the object.\", \"type\": \"float\"}, \"acceleration\": {\"description\": \"The acceleration of the object.\", \"type\": \"float\"}, \"time\": {\"description\": \"The time elapsed.\", \"type\": \"float\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"batting_average\", \"description\": \"Calculates the batting average of a baseball player based on the number of hits and at-bats.\", \"parameters\": {\"num_hits\": {\"description\": \"The number of hits.\", \"type\": \"int\", \"default\": 3}, \"num_at_bats\": {\"description\": \"The number of at-bats.\", \"type\": \"int\", \"default\": 3}, \"precision\": {\"description\": \"The number of decimal places to round the batting average. Defaults to 3.\", \"type\": \"int, optional\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the probability of rolling a sum of 8 with 3 dice?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"dice_roll_probability\", \"arguments\": {\"target_sum\": 8, \"num_dice\": 3}}]",
"style": "rule"
}
|
{
"index": 81,
"split": "train"
}
|
[{"name": "product_offers", "description": "Fetches a list of offers for a specific product on Amazon based on the given ASIN.", "parameters": {"asin": {"description": "Product ASIN to get offers for. Supports batching up to 10 ASINs in a single request, separated by a comma (e.g., 'B08PPDJWC8,B07ZPKBL9V,B08BHXG144').", "type": "str", "default": "B07ZPKBL9V"}, "delivery": {"description": "[EXPERIMENTAL] Find products with specific delivery options, specified as a comma-delimited list. Valid values: 'PRIME_ELIGIBLE', 'FREE_DELIVERY'. Default is None.", "type": "str, optional", "default": ""}, "limit": {"description": "Maximum number of offers to return. Default is 100.", "type": "int, optional", "default": "100"}, "product_condition": {"description": "Filter products by condition, specified as a comma-delimited list. Valid values: 'NEW', 'USED_LIKE_NEW', 'USED_VERY_GOOD', 'USED_GOOD', 'USED_ACCEPTABLE'. Default is None.", "type": "str, optional", "default": ""}, "country": {"description": "Sets the marketplace country, language, and currency. Allowed values: 'US', 'AU', 'BR', 'CA', 'CN', 'FR', 'DE', 'IN', 'IT', 'MX', 'NL', 'SG', 'ES', 'TR', 'AE', 'GB', 'JP'. Default is 'US'.", "type": "str, optional", "default": "US"}}}, {"name": "product_details", "description": "Returns detailed product information from the Target API including variants, ratings, reviews, images, videos, price, promotion, and child products.", "parameters": {"tcin": {"description": "Target product ID which is obtained from the product search API.", "type": "str", "default": "16251811"}, "store_id": {"description": "The ID of the store from which the product details data is being retrieved. This field is required and cannot be empty.", "type": "str", "default": "3330"}, "zip": {"description": "User's zip code. Defaults to '94611'.", "type": "str, optional", "default": "94611"}, "state": {"description": "State code of the user's location. Defaults to 'CA'.", "type": "str, optional", "default": "CA"}, "latitude": {"description": "User's latitude information. Defaults to '37.820'.", "type": "str, optional", "default": "37.820"}, "longitude": {"description": "User's longitude information. Defaults to '-122.200'.", "type": "str, optional", "default": "-122.200"}}}, {"name": "get_product_s_offers", "description": "Fetches the offers for a given product from the Amazon Data Scraper API.", "parameters": {"productid": {"description": "The unique identifier for the product whose offers you want to retrieve.", "type": "str", "default": "B00K3OM3PS"}}}]
|
[
{
"from": "human",
"value": "Find the offers for a product with ASIN B08PPDJWC8 and limit the results to 50."
}
] |
[{"name": "product_offers", "arguments": {"asin": "B08PPDJWC8", "limit": 50}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"product_offers\", \"description\": \"Fetches a list of offers for a specific product on Amazon based on the given ASIN.\", \"parameters\": {\"asin\": {\"description\": \"Product ASIN to get offers for. Supports batching up to 10 ASINs in a single request, separated by a comma (e.g., 'B08PPDJWC8,B07ZPKBL9V,B08BHXG144').\", \"type\": \"str\", \"default\": \"B07ZPKBL9V\"}, \"delivery\": {\"description\": \"[EXPERIMENTAL] Find products with specific delivery options, specified as a comma-delimited list. Valid values: 'PRIME_ELIGIBLE', 'FREE_DELIVERY'. Default is None.\", \"type\": \"str, optional\", \"default\": \"\"}, \"limit\": {\"description\": \"Maximum number of offers to return. Default is 100.\", \"type\": \"int, optional\", \"default\": \"100\"}, \"product_condition\": {\"description\": \"Filter products by condition, specified as a comma-delimited list. Valid values: 'NEW', 'USED_LIKE_NEW', 'USED_VERY_GOOD', 'USED_GOOD', 'USED_ACCEPTABLE'. Default is None.\", \"type\": \"str, optional\", \"default\": \"\"}, \"country\": {\"description\": \"Sets the marketplace country, language, and currency. Allowed values: 'US', 'AU', 'BR', 'CA', 'CN', 'FR', 'DE', 'IN', 'IT', 'MX', 'NL', 'SG', 'ES', 'TR', 'AE', 'GB', 'JP'. Default is 'US'.\", \"type\": \"str, optional\", \"default\": \"US\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"product_details\", \"description\": \"Returns detailed product information from the Target API including variants, ratings, reviews, images, videos, price, promotion, and child products.\", \"parameters\": {\"tcin\": {\"description\": \"Target product ID which is obtained from the product search API.\", \"type\": \"str\", \"default\": \"16251811\"}, \"store_id\": {\"description\": \"The ID of the store from which the product details data is being retrieved. This field is required and cannot be empty.\", \"type\": \"str\", \"default\": \"3330\"}, \"zip\": {\"description\": \"User's zip code. Defaults to '94611'.\", \"type\": \"str, optional\", \"default\": \"94611\"}, \"state\": {\"description\": \"State code of the user's location. Defaults to 'CA'.\", \"type\": \"str, optional\", \"default\": \"CA\"}, \"latitude\": {\"description\": \"User's latitude information. Defaults to '37.820'.\", \"type\": \"str, optional\", \"default\": \"37.820\"}, \"longitude\": {\"description\": \"User's longitude information. Defaults to '-122.200'.\", \"type\": \"str, optional\", \"default\": \"-122.200\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_product_s_offers\", \"description\": \"Fetches the offers for a given product from the Amazon Data Scraper API.\", \"parameters\": {\"productid\": {\"description\": \"The unique identifier for the product whose offers you want to retrieve.\", \"type\": \"str\", \"default\": \"B00K3OM3PS\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Find the offers for a product with ASIN B08PPDJWC8 and limit the results to 50.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"product_offers\", \"arguments\": {\"asin\": \"B08PPDJWC8\", \"limit\": 50}}]",
"style": "rule"
}
|
{
"index": 82,
"split": "train"
}
|
[{"name": "count_vowels", "description": "Counts the number of vowels in a given text.", "parameters": {"text": {"description": "The input text.", "type": "str"}}}, {"name": "fibonacci", "description": "Calculates the nth Fibonacci number.", "parameters": {"n": {"description": "The position of the Fibonacci number.", "type": "int"}}}, {"name": "is_anagram_phrase", "description": "Checks if two phrases are anagrams of each other, ignoring whitespace and punctuation.", "parameters": {"phrase1": {"description": "The first phrase.", "type": "str"}, "phrase2": {"description": "The second phrase.", "type": "str"}}}]
|
[
{
"from": "human",
"value": "How many vowels are there in the sentence 'Hello, how are you?' and what is the 10th Fibonacci number?"
}
] |
[{"name": "count_vowels", "arguments": {"text": "Hello, how are you?"}}, {"name": "fibonacci", "arguments": {"n": 10}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"count_vowels\", \"description\": \"Counts the number of vowels in a given text.\", \"parameters\": {\"text\": {\"description\": \"The input text.\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"fibonacci\", \"description\": \"Calculates the nth Fibonacci number.\", \"parameters\": {\"n\": {\"description\": \"The position of the Fibonacci number.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"is_anagram_phrase\", \"description\": \"Checks if two phrases are anagrams of each other, ignoring whitespace and punctuation.\", \"parameters\": {\"phrase1\": {\"description\": \"The first phrase.\", \"type\": \"str\"}, \"phrase2\": {\"description\": \"The second phrase.\", \"type\": \"str\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "How many vowels are there in the sentence 'Hello, how are you?' and what is the 10th Fibonacci number?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"count_vowels\", \"arguments\": {\"text\": \"Hello, how are you?\"}}, {\"name\": \"fibonacci\", \"arguments\": {\"n\": 10}}]",
"style": "rule"
}
|
{
"index": 83,
"split": "train"
}
|
[{"name": "topic_topic", "description": "Fetches entries from a specific topic using the Uncovered Treasure API.", "parameters": {"topic": {"description": "The topic for which to fetch entries.", "type": "str", "default": ""}, "callback": {"description": "The optional JSONP callback function name.", "type": "str, optional", "default": ""}}}, {"name": "getting_data", "description": "This function retrieves supermarket sales data from three different cities using the provided RapidAPI keys.", "parameters": {"x_rapidapi_key": {"description": "The RapidAPI key for accessing the `data_visualisation_` API. Defaults to 'demo'.", "type": "str", "default": "demo"}}}]
|
[
{
"from": "human",
"value": "Fetch entries about ancient Egyptian artifacts and also retrieve supermarket sales data from three different cities."
}
] |
[{"name": "topic_topic", "arguments": {"topic": "ancient Egyptian artifacts"}}, {"name": "getting_data", "arguments": {}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"topic_topic\", \"description\": \"Fetches entries from a specific topic using the Uncovered Treasure API.\", \"parameters\": {\"topic\": {\"description\": \"The topic for which to fetch entries.\", \"type\": \"str\", \"default\": \"\"}, \"callback\": {\"description\": \"The optional JSONP callback function name.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"getting_data\", \"description\": \"This function retrieves supermarket sales data from three different cities using the provided RapidAPI keys.\", \"parameters\": {\"x_rapidapi_key\": {\"description\": \"The RapidAPI key for accessing the `data_visualisation_` API. Defaults to 'demo'.\", \"type\": \"str\", \"default\": \"demo\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch entries about ancient Egyptian artifacts and also retrieve supermarket sales data from three different cities.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"topic_topic\", \"arguments\": {\"topic\": \"ancient Egyptian artifacts\"}}, {\"name\": \"getting_data\", \"arguments\": {}}]",
"style": "rule"
}
|
{
"index": 84,
"split": "train"
}
|
[{"name": "get_city_from_zipcode", "description": "Retrieves the city name for a given ZIP code using the Ziptastic API.", "parameters": {"zipcode": {"description": "The ZIP code to look up.", "type": "str"}}}, {"name": "get_pokemon_move_info", "description": "Retrieves information about a Pok\u00e9mon's move using the Pok\u00e9API.", "parameters": {"pokemon_name": {"description": "The name of the Pok\u00e9mon.", "type": "str", "default": "run"}, "move_name": {"description": "The name of the move to check. Defaults to \"run\".", "type": "str, optional", "default": "run"}}}, {"name": "project_population", "description": "Projects the population size after a specified number of years.", "parameters": {"current_pop": {"description": "The current population size.", "type": "int", "default": 1.2}, "num_years": {"description": "The number of years into the future to make the projection.", "type": "int", "default": 1.2}, "annual_growth": {"description": "The annual population growth rate as a percentage. Defaults to 1.2.", "type": "float, optional"}}}]
|
[
{
"from": "human",
"value": "If the current population of a city is 100,000 and it grows at an annual rate of 2%, what will be the population after 10 years? Also, what city does the ZIP code 10001 belong to?"
}
] |
[{"name": "project_population", "arguments": {"current_pop": 100000, "num_years": 10, "annual_growth": 2}}, {"name": "get_city_from_zipcode", "arguments": {"zipcode": "10001"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_city_from_zipcode\", \"description\": \"Retrieves the city name for a given ZIP code using the Ziptastic API.\", \"parameters\": {\"zipcode\": {\"description\": \"The ZIP code to look up.\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_pokemon_move_info\", \"description\": \"Retrieves information about a Pok\\u00e9mon's move using the Pok\\u00e9API.\", \"parameters\": {\"pokemon_name\": {\"description\": \"The name of the Pok\\u00e9mon.\", \"type\": \"str\", \"default\": \"run\"}, \"move_name\": {\"description\": \"The name of the move to check. Defaults to \\\"run\\\".\", \"type\": \"str, optional\", \"default\": \"run\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"project_population\", \"description\": \"Projects the population size after a specified number of years.\", \"parameters\": {\"current_pop\": {\"description\": \"The current population size.\", \"type\": \"int\", \"default\": 1.2}, \"num_years\": {\"description\": \"The number of years into the future to make the projection.\", \"type\": \"int\", \"default\": 1.2}, \"annual_growth\": {\"description\": \"The annual population growth rate as a percentage. Defaults to 1.2.\", \"type\": \"float, optional\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "If the current population of a city is 100,000 and it grows at an annual rate of 2%, what will be the population after 10 years? Also, what city does the ZIP code 10001 belong to?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"project_population\", \"arguments\": {\"current_pop\": 100000, \"num_years\": 10, \"annual_growth\": 2}}, {\"name\": \"get_city_from_zipcode\", \"arguments\": {\"zipcode\": \"10001\"}}]",
"style": "rule"
}
|
{
"index": 85,
"split": "train"
}
|
[{"name": "calculate_age", "description": "Calculates the age based on the birthdate.", "parameters": {"birthdate": {"description": "The birthdate in the format 'YYYY-MM-DD'.", "type": "str"}}}, {"name": "get_range", "description": "Helper function to format the range string.", "parameters": {"start": {"description": "The start of the range.", "type": "int"}, "end": {"description": "The end of the range.", "type": "int"}}}, {"name": "find_longest_word", "description": "Finds the longest word in a list of words.", "parameters": {"words": {"description": "A list of words.", "type": "List[str]"}}}]
|
[
{
"from": "human",
"value": "What is the range from 25 to 35?"
}
] |
[{"name": "get_range", "arguments": {"start": 25, "end": 35}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"calculate_age\", \"description\": \"Calculates the age based on the birthdate.\", \"parameters\": {\"birthdate\": {\"description\": \"The birthdate in the format 'YYYY-MM-DD'.\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_range\", \"description\": \"Helper function to format the range string.\", \"parameters\": {\"start\": {\"description\": \"The start of the range.\", \"type\": \"int\"}, \"end\": {\"description\": \"The end of the range.\", \"type\": \"int\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"find_longest_word\", \"description\": \"Finds the longest word in a list of words.\", \"parameters\": {\"words\": {\"description\": \"A list of words.\", \"type\": \"List[str]\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What is the range from 25 to 35?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_range\", \"arguments\": {\"start\": 25, \"end\": 35}}]",
"style": "rule"
}
|
{
"index": 86,
"split": "train"
}
|
[{"name": "top_paid_ios_apps", "description": "Fetches a list of the top paid iOS apps from the App Store.", "parameters": {"lang": {"description": "Language code for the results. Defaults to 'en'.", "type": "str", "default": "en"}, "category": {"description": "Category ID to filter results by. Defaults to '6016'.", "type": "str", "default": "6016"}, "country": {"description": "Country code for the App Store to search in. Defaults to 'us'.", "type": "str", "default": "us"}, "num": {"description": "Number of results to return. Defaults to 100. Maximum is 200.", "type": "int", "default": "100"}}}, {"name": "skill_child", "description": "Fetches child skill data from an external API using provided identifiers.", "parameters": {"is_id": {"description": "The unique identifier for the desired child skill data. Defaults to 'files/198956'.", "type": "str, optional", "default": "files/198956"}}}, {"name": "pluses_and_minuses_of_the_car", "description": "Fetches the list of pluses and minuses for a specific car model using the ToolBench RapidAPI.", "parameters": {"year": {"description": "The year of manufacture of the car.", "type": "str", "default": "2012"}, "make": {"description": "The make (manufacturer) of the car.", "type": "str", "default": "bmw"}, "model": {"description": "The model of the car.", "type": "str", "default": "5 series"}}}]
|
[
{
"from": "human",
"value": "Find the top 20 paid iOS apps in the Health & Fitness category in the UK App Store."
}
] |
[{"name": "top_paid_ios_apps", "arguments": {"lang": "en", "category": "6013", "country": "gb", "num": 20}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"top_paid_ios_apps\", \"description\": \"Fetches a list of the top paid iOS apps from the App Store.\", \"parameters\": {\"lang\": {\"description\": \"Language code for the results. Defaults to 'en'.\", \"type\": \"str\", \"default\": \"en\"}, \"category\": {\"description\": \"Category ID to filter results by. Defaults to '6016'.\", \"type\": \"str\", \"default\": \"6016\"}, \"country\": {\"description\": \"Country code for the App Store to search in. Defaults to 'us'.\", \"type\": \"str\", \"default\": \"us\"}, \"num\": {\"description\": \"Number of results to return. Defaults to 100. Maximum is 200.\", \"type\": \"int\", \"default\": \"100\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"skill_child\", \"description\": \"Fetches child skill data from an external API using provided identifiers.\", \"parameters\": {\"is_id\": {\"description\": \"The unique identifier for the desired child skill data. Defaults to 'files/198956'.\", \"type\": \"str, optional\", \"default\": \"files/198956\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"pluses_and_minuses_of_the_car\", \"description\": \"Fetches the list of pluses and minuses for a specific car model using the ToolBench RapidAPI.\", \"parameters\": {\"year\": {\"description\": \"The year of manufacture of the car.\", \"type\": \"str\", \"default\": \"2012\"}, \"make\": {\"description\": \"The make (manufacturer) of the car.\", \"type\": \"str\", \"default\": \"bmw\"}, \"model\": {\"description\": \"The model of the car.\", \"type\": \"str\", \"default\": \"5 series\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Find the top 20 paid iOS apps in the Health & Fitness category in the UK App Store.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"top_paid_ios_apps\", \"arguments\": {\"lang\": \"en\", \"category\": \"6013\", \"country\": \"gb\", \"num\": 20}}]",
"style": "rule"
}
|
{
"index": 87,
"split": "train"
}
|
[{"name": "assess_diabetes_risk", "description": "Assesses the risk of developing type 2 diabetes based on body mass index (BMI) and physical activity level.", "parameters": {"weight_lbs": {"description": "Body weight in pounds.", "type": "int"}, "height_inches": {"description": "Height in inches.", "type": "int"}, "activity": {"description": "Physical activity level. Allowed values: \"sedentary\", \"lightly active\", \"moderately active\", or \"very active\".", "type": "str"}}}, {"name": "project_investment_growth", "description": "Projects the growth of an investment over a specified number of years.", "parameters": {"principal": {"description": "The initial investment amount.", "type": "float", "default": true}, "annual_addition": {"description": "The amount added to the investment annually.", "type": "float", "default": true}, "years": {"description": "The number of years to project the investment growth.", "type": "int"}, "return_rate": {"description": "The annual return rate as a decimal (e.g., 0.07 for 7%).", "type": "float"}, "inflation": {"description": "A list of annual inflation rates as decimals.", "type": "List[float]"}, "inflation_adjusted": {"description": "Whether to adjust the final value for inflation. Defaults to True.", "type": "bool, optional"}}}, {"name": "get_ip_zipcode", "description": "Retrieves the ZIP code of a given IP address using the ip-api.com API.", "parameters": {"ip": {"description": "The IP address to locate.", "type": "str"}}}]
|
[
{
"from": "human",
"value": "Get the ZIP code for IP addresses '173.194.40.120' and '208.67.222.222'."
}
] |
[{"name": "get_ip_zipcode", "arguments": {"ip": "173.194.40.120"}}, {"name": "get_ip_zipcode", "arguments": {"ip": "208.67.222.222"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"assess_diabetes_risk\", \"description\": \"Assesses the risk of developing type 2 diabetes based on body mass index (BMI) and physical activity level.\", \"parameters\": {\"weight_lbs\": {\"description\": \"Body weight in pounds.\", \"type\": \"int\"}, \"height_inches\": {\"description\": \"Height in inches.\", \"type\": \"int\"}, \"activity\": {\"description\": \"Physical activity level. Allowed values: \\\"sedentary\\\", \\\"lightly active\\\", \\\"moderately active\\\", or \\\"very active\\\".\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"project_investment_growth\", \"description\": \"Projects the growth of an investment over a specified number of years.\", \"parameters\": {\"principal\": {\"description\": \"The initial investment amount.\", \"type\": \"float\", \"default\": true}, \"annual_addition\": {\"description\": \"The amount added to the investment annually.\", \"type\": \"float\", \"default\": true}, \"years\": {\"description\": \"The number of years to project the investment growth.\", \"type\": \"int\"}, \"return_rate\": {\"description\": \"The annual return rate as a decimal (e.g., 0.07 for 7%).\", \"type\": \"float\"}, \"inflation\": {\"description\": \"A list of annual inflation rates as decimals.\", \"type\": \"List[float]\"}, \"inflation_adjusted\": {\"description\": \"Whether to adjust the final value for inflation. Defaults to True.\", \"type\": \"bool, optional\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_ip_zipcode\", \"description\": \"Retrieves the ZIP code of a given IP address using the ip-api.com API.\", \"parameters\": {\"ip\": {\"description\": \"The IP address to locate.\", \"type\": \"str\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Get the ZIP code for IP addresses '173.194.40.120' and '208.67.222.222'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_ip_zipcode\", \"arguments\": {\"ip\": \"173.194.40.120\"}}, {\"name\": \"get_ip_zipcode\", \"arguments\": {\"ip\": \"208.67.222.222\"}}]",
"style": "rule"
}
|
{
"index": 88,
"split": "train"
}
|
[{"name": "schedule", "description": "Fetches the TV schedule based on the given parameters.", "parameters": {"country": {"description": "An ISO country code to filter the schedule by country.", "type": "str, optional", "default": ""}, "date": {"description": "An ISO formatted date to filter the schedule for a specific day.", "type": "str, optional", "default": ""}, "filter": {"description": "A filter to specify whether to show only primetime shows. Default is 'primetime'.", "type": "str, optional", "default": "primetime"}}}, {"name": "chapters_list_paginated", "description": "Fetches a paginated list of chapters for a specific webtoon from a specified provider.", "parameters": {"provider": {"description": "The slug identifying the webtoon provider. Refer to /providers for the list of providers.", "type": "str", "default": "cosmic"}, "webtoon": {"description": "The slug identifying the webtoon. Refer to /webtoons for the list of webtoons.", "type": "str", "default": "eleceed"}, "limit": {"description": "The number of results to return per page, between 1 and 20.", "type": "int", "default": "10"}, "page": {"description": "The page number to fetch.", "type": "int", "default": "1"}}}, {"name": "get_match", "description": "Calculates the match percentage between two names using the Love Calculator API.", "parameters": {"fname": {"description": "The first name for the love match calculation.", "type": "str", "default": "oliver m"}, "sname": {"description": "The second name for the love match calculation.", "type": "str", "default": "chloe p"}}}]
|
[
{
"from": "human",
"value": "Determine the love match between 'Emily' and 'David'."
}
] |
[{"name": "get_match", "arguments": {"fname": "Emily", "sname": "David"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"schedule\", \"description\": \"Fetches the TV schedule based on the given parameters.\", \"parameters\": {\"country\": {\"description\": \"An ISO country code to filter the schedule by country.\", \"type\": \"str, optional\", \"default\": \"\"}, \"date\": {\"description\": \"An ISO formatted date to filter the schedule for a specific day.\", \"type\": \"str, optional\", \"default\": \"\"}, \"filter\": {\"description\": \"A filter to specify whether to show only primetime shows. Default is 'primetime'.\", \"type\": \"str, optional\", \"default\": \"primetime\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"chapters_list_paginated\", \"description\": \"Fetches a paginated list of chapters for a specific webtoon from a specified provider.\", \"parameters\": {\"provider\": {\"description\": \"The slug identifying the webtoon provider. Refer to /providers for the list of providers.\", \"type\": \"str\", \"default\": \"cosmic\"}, \"webtoon\": {\"description\": \"The slug identifying the webtoon. Refer to /webtoons for the list of webtoons.\", \"type\": \"str\", \"default\": \"eleceed\"}, \"limit\": {\"description\": \"The number of results to return per page, between 1 and 20.\", \"type\": \"int\", \"default\": \"10\"}, \"page\": {\"description\": \"The page number to fetch.\", \"type\": \"int\", \"default\": \"1\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_match\", \"description\": \"Calculates the match percentage between two names using the Love Calculator API.\", \"parameters\": {\"fname\": {\"description\": \"The first name for the love match calculation.\", \"type\": \"str\", \"default\": \"oliver m\"}, \"sname\": {\"description\": \"The second name for the love match calculation.\", \"type\": \"str\", \"default\": \"chloe p\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Determine the love match between 'Emily' and 'David'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_match\", \"arguments\": {\"fname\": \"Emily\", \"sname\": \"David\"}}]",
"style": "rule"
}
|
{
"index": 89,
"split": "train"
}
|
[{"name": "address_postal_code", "description": "Fetch address information based on the given postal code and additional parameters.", "parameters": {"postal_code": {"description": "Postal code string (minimum: 3 digits, maximum: 7 digits).", "type": "str", "default": "1510053"}, "datum": {"description": "Geodetic system of latitude and longitude (default: 'wgs84'). Possible values are 'wgs84' for World Geodetic System and 'tokyo' for Old Japan Geodetic System.", "type": "str, optional", "default": "wgs84"}, "offset": {"description": "Skips a given number of first data (minimum value: 0, maximum value: 2000, default: 0).", "type": "int, optional", "default": "0"}, "coord_unit": {"description": "The unit of latitude and longitude in the output data. Possible values are 'degree' for decimal system of degrees (default) and 'millisec' for milliseconds.", "type": "str, optional", "default": "degree"}, "limit": {"description": "Limits the number of response data (minimum value: 1, maximum value: 100, default: 10).", "type": "int, optional", "default": "10"}}}, {"name": "measure_distance", "description": "Calculates the distance between two geographic locations based on their latitude and longitude coordinates, with optional specification of the unit of measurement.", "parameters": {"lat1": {"description": "Latitude of the first location.", "type": "int", "default": "0.365816"}, "lat2": {"description": "Latitude of the second location.", "type": "int", "default": "0.32493795000000003"}, "lon2": {"description": "Longitude of the second location.", "type": "int", "default": "32.57523607707668"}, "lon1": {"description": "Longitude of the first location.", "type": "int", "default": "32.529226"}, "unit": {"description": "Unit of distance measurement. Valid options are 'km' (default), 'mi', 'ft', and 'yd'.", "type": "str, optional", "default": "km"}}}, {"name": "ip_geolocation_lookup", "description": "Fetch geolocation data for a given IPv4 address using the RapidAPI IP geolocation lookup service.", "parameters": {"ip": {"description": "The IPv4 address for which geolocation data is to be retrieved.", "type": "str", "default": "193.114.112.1"}}}, {"name": "countiessearchinboundingbox", "description": "Fetch county boundaries within a specified bounding box in GeoJSON format.", "parameters": {"northeast": {"description": "Coordinates of the northeast corner of the bounding box (e.g., '40.81,-73.41').", "type": "str", "default": ""}, "southwest": {"description": "Coordinates of the southwest corner of the bounding box (e.g., '40.62,-74.73').", "type": "str", "default": ""}, "intersect": {"description": "Whether to include areas that intersect with the bounding box. Default is None.", "type": "bool, optional", "default": true}}}]
|
[
{
"from": "human",
"value": "Could you lookup the geolocation for IP 1.1.1.1? Also, find the counties that intersect with a bounding box in New York with corners at (40.78, -73.97) and (40.74, -74.01)."
}
] |
[{"name": "ip_geolocation_lookup", "arguments": {"ip": "1.1.1.1"}}, {"name": "countiessearchinboundingbox", "arguments": {"northeast": "40.78,-73.97", "southwest": "40.74,-74.01", "intersect": true}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"address_postal_code\", \"description\": \"Fetch address information based on the given postal code and additional parameters.\", \"parameters\": {\"postal_code\": {\"description\": \"Postal code string (minimum: 3 digits, maximum: 7 digits).\", \"type\": \"str\", \"default\": \"1510053\"}, \"datum\": {\"description\": \"Geodetic system of latitude and longitude (default: 'wgs84'). Possible values are 'wgs84' for World Geodetic System and 'tokyo' for Old Japan Geodetic System.\", \"type\": \"str, optional\", \"default\": \"wgs84\"}, \"offset\": {\"description\": \"Skips a given number of first data (minimum value: 0, maximum value: 2000, default: 0).\", \"type\": \"int, optional\", \"default\": \"0\"}, \"coord_unit\": {\"description\": \"The unit of latitude and longitude in the output data. Possible values are 'degree' for decimal system of degrees (default) and 'millisec' for milliseconds.\", \"type\": \"str, optional\", \"default\": \"degree\"}, \"limit\": {\"description\": \"Limits the number of response data (minimum value: 1, maximum value: 100, default: 10).\", \"type\": \"int, optional\", \"default\": \"10\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"measure_distance\", \"description\": \"Calculates the distance between two geographic locations based on their latitude and longitude coordinates, with optional specification of the unit of measurement.\", \"parameters\": {\"lat1\": {\"description\": \"Latitude of the first location.\", \"type\": \"int\", \"default\": \"0.365816\"}, \"lat2\": {\"description\": \"Latitude of the second location.\", \"type\": \"int\", \"default\": \"0.32493795000000003\"}, \"lon2\": {\"description\": \"Longitude of the second location.\", \"type\": \"int\", \"default\": \"32.57523607707668\"}, \"lon1\": {\"description\": \"Longitude of the first location.\", \"type\": \"int\", \"default\": \"32.529226\"}, \"unit\": {\"description\": \"Unit of distance measurement. Valid options are 'km' (default), 'mi', 'ft', and 'yd'.\", \"type\": \"str, optional\", \"default\": \"km\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"ip_geolocation_lookup\", \"description\": \"Fetch geolocation data for a given IPv4 address using the RapidAPI IP geolocation lookup service.\", \"parameters\": {\"ip\": {\"description\": \"The IPv4 address for which geolocation data is to be retrieved.\", \"type\": \"str\", \"default\": \"193.114.112.1\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"countiessearchinboundingbox\", \"description\": \"Fetch county boundaries within a specified bounding box in GeoJSON format.\", \"parameters\": {\"northeast\": {\"description\": \"Coordinates of the northeast corner of the bounding box (e.g., '40.81,-73.41').\", \"type\": \"str\", \"default\": \"\"}, \"southwest\": {\"description\": \"Coordinates of the southwest corner of the bounding box (e.g., '40.62,-74.73').\", \"type\": \"str\", \"default\": \"\"}, \"intersect\": {\"description\": \"Whether to include areas that intersect with the bounding box. Default is None.\", \"type\": \"bool, optional\", \"default\": true}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Could you lookup the geolocation for IP 1.1.1.1? Also, find the counties that intersect with a bounding box in New York with corners at (40.78, -73.97) and (40.74, -74.01).",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"ip_geolocation_lookup\", \"arguments\": {\"ip\": \"1.1.1.1\"}}, {\"name\": \"countiessearchinboundingbox\", \"arguments\": {\"northeast\": \"40.78,-73.97\", \"southwest\": \"40.74,-74.01\", \"intersect\": true}}]",
"style": "rule"
}
|
{
"index": 90,
"split": "train"
}
|
[{"name": "find_longest_word", "description": "Finds the longest word in a list of words.", "parameters": {"words": {"description": "A list of words.", "type": "List[str]"}}}, {"name": "is_valid_parentheses", "description": "Checks if a string contains valid parentheses.", "parameters": {"s": {"description": "The input string.", "type": "str"}}}, {"name": "get_range", "description": "Helper function to format the range string.", "parameters": {"start": {"description": "The start of the range.", "type": "int"}, "end": {"description": "The end of the range.", "type": "int"}}}]
|
[
{
"from": "human",
"value": "Give me the range from 25 to 30 and verify if the parentheses in the string '([]{})' are valid."
}
] |
[{"name": "get_range", "arguments": {"start": 25, "end": 30}}, {"name": "is_valid_parentheses", "arguments": {"s": "([]{})"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"find_longest_word\", \"description\": \"Finds the longest word in a list of words.\", \"parameters\": {\"words\": {\"description\": \"A list of words.\", \"type\": \"List[str]\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"is_valid_parentheses\", \"description\": \"Checks if a string contains valid parentheses.\", \"parameters\": {\"s\": {\"description\": \"The input string.\", \"type\": \"str\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_range\", \"description\": \"Helper function to format the range string.\", \"parameters\": {\"start\": {\"description\": \"The start of the range.\", \"type\": \"int\"}, \"end\": {\"description\": \"The end of the range.\", \"type\": \"int\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Give me the range from 25 to 30 and verify if the parentheses in the string '([]{})' are valid.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_range\", \"arguments\": {\"start\": 25, \"end\": 30}}, {\"name\": \"is_valid_parentheses\", \"arguments\": {\"s\": \"([]{})\"}}]",
"style": "rule"
}
|
{
"index": 91,
"split": "train"
}
|
[{"name": "getdivision", "description": "Divides two numbers by making an API call to a division service.", "parameters": {"divisor": {"description": "The divisor in the division operation.", "type": "int", "default": ""}, "dividend": {"description": "The dividend in the division operation.", "type": "int", "default": ""}}}]
|
[
{
"from": "human",
"value": "What are the results of dividing 225 by 9 and 330 by 11?"
}
] |
[{"name": "getdivision", "arguments": {"divisor": 9, "dividend": 225}}, {"name": "getdivision", "arguments": {"divisor": 11, "dividend": 330}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"getdivision\", \"description\": \"Divides two numbers by making an API call to a division service.\", \"parameters\": {\"divisor\": {\"description\": \"The divisor in the division operation.\", \"type\": \"int\", \"default\": \"\"}, \"dividend\": {\"description\": \"The dividend in the division operation.\", \"type\": \"int\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "What are the results of dividing 225 by 9 and 330 by 11?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"getdivision\", \"arguments\": {\"divisor\": 9, \"dividend\": 225}}, {\"name\": \"getdivision\", \"arguments\": {\"divisor\": 11, \"dividend\": 330}}]",
"style": "rule"
}
|
{
"index": 92,
"split": "train"
}
|
[{"name": "get_analysis", "description": "Fetches website traffic and key metrics for a given domain using the RapidAPI service.", "parameters": {"domain": {"description": "The domain to analyze, e.g., 'amazon.com'.", "type": "str", "default": ""}}}, {"name": "check", "description": "Checks and returns SSL information for a given domain. Optionally, additional information can be requested by setting the extended property.", "parameters": {"domain": {"description": "The domain name to check SSL information for.", "type": "str", "default": "test.com"}, "extended": {"description": "Optional; Set to 'true' for additional information. Default is 'true'.", "type": "str", "default": "true"}}}]
|
[
{
"from": "human",
"value": "I need the traffic metrics for 'walmart.com' and the SSL information for 'target.com'."
}
] |
[{"name": "get_analysis", "arguments": {"domain": "walmart.com"}}, {"name": "check", "arguments": {"domain": "target.com"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_analysis\", \"description\": \"Fetches website traffic and key metrics for a given domain using the RapidAPI service.\", \"parameters\": {\"domain\": {\"description\": \"The domain to analyze, e.g., 'amazon.com'.\", \"type\": \"str\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"check\", \"description\": \"Checks and returns SSL information for a given domain. Optionally, additional information can be requested by setting the extended property.\", \"parameters\": {\"domain\": {\"description\": \"The domain name to check SSL information for.\", \"type\": \"str\", \"default\": \"test.com\"}, \"extended\": {\"description\": \"Optional; Set to 'true' for additional information. Default is 'true'.\", \"type\": \"str\", \"default\": \"true\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I need the traffic metrics for 'walmart.com' and the SSL information for 'target.com'.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_analysis\", \"arguments\": {\"domain\": \"walmart.com\"}}, {\"name\": \"check\", \"arguments\": {\"domain\": \"target.com\"}}]",
"style": "rule"
}
|
{
"index": 93,
"split": "train"
}
|
[{"name": "loginuser", "description": "Logs a user into the system using the provided username and password.", "parameters": {"password": {"description": "The password for login in clear text.", "type": "str", "default": "string"}, "username": {"description": "The username for login.", "type": "str", "default": "string"}}}]
|
[
{
"from": "human",
"value": "I want to log in to the system with my username 'guest' and password 'guestpass'. However, I'm not sure if I need to include the API key. Can you help me with that?"
}
] |
[{"name": "loginuser", "arguments": {"password": "guestpass", "username": "guest"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"loginuser\", \"description\": \"Logs a user into the system using the provided username and password.\", \"parameters\": {\"password\": {\"description\": \"The password for login in clear text.\", \"type\": \"str\", \"default\": \"string\"}, \"username\": {\"description\": \"The username for login.\", \"type\": \"str\", \"default\": \"string\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "I want to log in to the system with my username 'guest' and password 'guestpass'. However, I'm not sure if I need to include the API key. Can you help me with that?",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"loginuser\", \"arguments\": {\"password\": \"guestpass\", \"username\": \"guest\"}}]",
"style": "rule"
}
|
{
"index": 94,
"split": "train"
}
|
[{"name": "stock_calendar_events", "description": "Fetches calendar events for a specified stock symbol using the Yahoo Finance API.", "parameters": {"symbol": {"description": "The stock symbol for which to retrieve calendar events.", "type": "str", "default": "AAPL"}}}, {"name": "screeners_details", "description": "Fetch detailed information about a specified stock screener using the Seeking Alpha API.", "parameters": {"screener_id": {"description": "The unique identifier of the screener from the Screeners list and Screeners filters.", "type": "str", "default": "96793299"}}}, {"name": "latest_information_for_symbol", "description": "Fetch the latest ticker information for a given symbol from the Bybit API.", "parameters": {"symbol": {"description": "The market symbol to retrieve information for.", "type": "str", "default": "BTCUSD"}}}, {"name": "key_statistics", "description": "Fetches key statistics for a given stock ticker using the Toolbench RapidAPI service.", "parameters": {"ticker": {"description": "The stock ticker symbol to retrieve key statistics for.", "type": "str", "default": "AAPL"}}}]
|
[
{
"from": "human",
"value": "Fetch the latest ticker information for Ethereum and key statistics for Apple Inc."
}
] |
[{"name": "latest_information_for_symbol", "arguments": {"symbol": "ETHUSD"}}, {"name": "key_statistics", "arguments": {"ticker": "AAPL"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"stock_calendar_events\", \"description\": \"Fetches calendar events for a specified stock symbol using the Yahoo Finance API.\", \"parameters\": {\"symbol\": {\"description\": \"The stock symbol for which to retrieve calendar events.\", \"type\": \"str\", \"default\": \"AAPL\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"screeners_details\", \"description\": \"Fetch detailed information about a specified stock screener using the Seeking Alpha API.\", \"parameters\": {\"screener_id\": {\"description\": \"The unique identifier of the screener from the Screeners list and Screeners filters.\", \"type\": \"str\", \"default\": \"96793299\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"latest_information_for_symbol\", \"description\": \"Fetch the latest ticker information for a given symbol from the Bybit API.\", \"parameters\": {\"symbol\": {\"description\": \"The market symbol to retrieve information for.\", \"type\": \"str\", \"default\": \"BTCUSD\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"key_statistics\", \"description\": \"Fetches key statistics for a given stock ticker using the Toolbench RapidAPI service.\", \"parameters\": {\"ticker\": {\"description\": \"The stock ticker symbol to retrieve key statistics for.\", \"type\": \"str\", \"default\": \"AAPL\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch the latest ticker information for Ethereum and key statistics for Apple Inc.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"latest_information_for_symbol\", \"arguments\": {\"symbol\": \"ETHUSD\"}}, {\"name\": \"key_statistics\", \"arguments\": {\"ticker\": \"AAPL\"}}]",
"style": "rule"
}
|
{
"index": 95,
"split": "train"
}
|
[{"name": "categories", "description": "Fetches categories from the AliExpress unofficial API, optionally filtered by locale and country.", "parameters": {"locale": {"description": "The locale to filter categories by. Defaults to None.", "type": "str, optional", "default": ""}, "country": {"description": "The country to filter categories by. Defaults to None.", "type": "str, optional", "default": ""}}}, {"name": "get_call", "description": "Fetches the API result using the given request ID.", "parameters": {"request_id": {"description": "The unique identifier for the API request.", "type": "str", "default": "76d1c748-51ed-435b-bcd8-3d9c9d3eb68a"}}}, {"name": "get_order", "description": "Retrieves the details of an order by making a GET request to the RapidAPI store.", "parameters": {"is_id": {"description": "The ID of the order to retrieve.", "type": "str", "default": ""}}}]
|
[
{
"from": "human",
"value": "Retrieve the details of orders with ID 'ORD001' and 'ORD002'"
}
] |
[{"name": "get_order", "arguments": {"is_id": "ORD001"}}, {"name": "get_order", "arguments": {"is_id": "ORD002"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"categories\", \"description\": \"Fetches categories from the AliExpress unofficial API, optionally filtered by locale and country.\", \"parameters\": {\"locale\": {\"description\": \"The locale to filter categories by. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}, \"country\": {\"description\": \"The country to filter categories by. Defaults to None.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_call\", \"description\": \"Fetches the API result using the given request ID.\", \"parameters\": {\"request_id\": {\"description\": \"The unique identifier for the API request.\", \"type\": \"str\", \"default\": \"76d1c748-51ed-435b-bcd8-3d9c9d3eb68a\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"get_order\", \"description\": \"Retrieves the details of an order by making a GET request to the RapidAPI store.\", \"parameters\": {\"is_id\": {\"description\": \"The ID of the order to retrieve.\", \"type\": \"str\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Retrieve the details of orders with ID 'ORD001' and 'ORD002'",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"get_order\", \"arguments\": {\"is_id\": \"ORD001\"}}, {\"name\": \"get_order\", \"arguments\": {\"is_id\": \"ORD002\"}}]",
"style": "rule"
}
|
{
"index": 96,
"split": "train"
}
|
[{"name": "binance_charts", "description": "Fetch candlestick chart data for a specified cryptocurrency trading pair from Binance.", "parameters": {"symbol": {"description": "Symbol for the trading pair. Example: 'BTCUSDT'", "type": "str", "default": "BTCUSDT"}, "content_type": {"description": "Type of content for the query. Defaults to 'application/x-www-form-urlencoded'.", "type": "str, optional", "default": "application/x-www-form-urlencoded"}, "limit": {"description": "Number of candles to include in the chart. Defaults to 16. Maximum is 1000.", "type": "int, optional", "default": "16"}, "interval": {"description": "Time interval for each candle. Defaults to '1m'. Valid intervals are:", "type": "str, optional", "default": "1m"}, "lastprice": {"description": "The specified last price for the chart. Defaults to 57500.", "type": "int, optional", "default": "57500"}}}, {"name": "mini_chart", "description": "Generates a TradingView mini chart image based on the specified parameters and returns the image data or error message.", "parameters": {"width": {"description": "Width of the chart image. Must be within the valid range. Minimum: 320. Default is 800.", "type": "int, optional", "default": "800"}, "format": {"description": "Format of the chart image. Supported formats are 'png' and 'jpeg'. Default is 'png'.", "type": "str, optional", "default": "png"}, "symbol": {"description": "TradingView symbol for the chart. Examples include 'BINANCE:BTCUSDT' and 'BINANCE:BTCUSDTPERP'. Default is 'BINANCE:BTCUSDT'.", "type": "str, optional", "default": "BINANCE:BTCUSDT"}, "interval": {"description": "Time interval for the chart. Supported intervals are '1d', '1M', '3M', '1Y', '5Y', and 'all'. Default is '1M'.", "type": "str, optional", "default": "1M"}, "theme": {"description": "Color theme of the chart. Supported themes are 'light' and 'dark'. Default is 'dark'.", "type": "str, optional", "default": "dark"}, "height": {"description": "Height of the chart image. Must be within the valid range. Minimum: 220. Default is 400.", "type": "int, optional", "default": "400"}}}, {"name": "peer_ratio_averages", "description": "Fetches and returns an average of company peer ratios for trailing twelve months (TTM) data for a given company symbol.", "parameters": {"symbol": {"description": "The stock symbol of the company for which to fetch peer ratio averages.", "type": "str", "default": "AAPL"}}}, {"name": "converter", "description": "Performs currency conversion between multiple currencies using the given parameters.", "parameters": {"target": {"description": "The currency code to convert to. This should be a valid three-letter currency code. Multiple target currencies can be specified, separated by a comma.", "type": "str", "default": "EUR,INR,JPY"}, "source": {"description": "The currency code to convert from. This should be a valid three-letter currency code, e.g., USD or EUR.", "type": "str", "default": "USD"}, "amount": {"description": "The amount to convert from the source currency to the target currency. Defaults to 1 if not provided.", "type": "int, optional", "default": "1"}}}]
|
[
{
"from": "human",
"value": "Fetch the candlestick chart data for the BTC/USDT trading pair on Binance with a 4-hour interval for the last 200 candles and a last price of 45000. Also, generate a TradingView mini chart image for the same trading pair with a time interval of 6 months in dark theme, and convert 5000 Euros to US dollars and Japanese yen."
}
] |
[{"name": "binance_charts", "arguments": {"symbol": "BTCUSDT", "content_type": "application/x-www-form-urlencoded", "limit": 200, "interval": "4h", "lastprice": 45000}}, {"name": "mini_chart", "arguments": {"symbol": "BINANCE:BTCUSDT", "interval": "6M", "theme": "dark"}}, {"name": "converter", "arguments": {"target": "USD,JPY", "source": "EUR", "amount": 5000}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"binance_charts\", \"description\": \"Fetch candlestick chart data for a specified cryptocurrency trading pair from Binance.\", \"parameters\": {\"symbol\": {\"description\": \"Symbol for the trading pair. Example: 'BTCUSDT'\", \"type\": \"str\", \"default\": \"BTCUSDT\"}, \"content_type\": {\"description\": \"Type of content for the query. Defaults to 'application/x-www-form-urlencoded'.\", \"type\": \"str, optional\", \"default\": \"application/x-www-form-urlencoded\"}, \"limit\": {\"description\": \"Number of candles to include in the chart. Defaults to 16. Maximum is 1000.\", \"type\": \"int, optional\", \"default\": \"16\"}, \"interval\": {\"description\": \"Time interval for each candle. Defaults to '1m'. Valid intervals are:\", \"type\": \"str, optional\", \"default\": \"1m\"}, \"lastprice\": {\"description\": \"The specified last price for the chart. Defaults to 57500.\", \"type\": \"int, optional\", \"default\": \"57500\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"mini_chart\", \"description\": \"Generates a TradingView mini chart image based on the specified parameters and returns the image data or error message.\", \"parameters\": {\"width\": {\"description\": \"Width of the chart image. Must be within the valid range. Minimum: 320. Default is 800.\", \"type\": \"int, optional\", \"default\": \"800\"}, \"format\": {\"description\": \"Format of the chart image. Supported formats are 'png' and 'jpeg'. Default is 'png'.\", \"type\": \"str, optional\", \"default\": \"png\"}, \"symbol\": {\"description\": \"TradingView symbol for the chart. Examples include 'BINANCE:BTCUSDT' and 'BINANCE:BTCUSDTPERP'. Default is 'BINANCE:BTCUSDT'.\", \"type\": \"str, optional\", \"default\": \"BINANCE:BTCUSDT\"}, \"interval\": {\"description\": \"Time interval for the chart. Supported intervals are '1d', '1M', '3M', '1Y', '5Y', and 'all'. Default is '1M'.\", \"type\": \"str, optional\", \"default\": \"1M\"}, \"theme\": {\"description\": \"Color theme of the chart. Supported themes are 'light' and 'dark'. Default is 'dark'.\", \"type\": \"str, optional\", \"default\": \"dark\"}, \"height\": {\"description\": \"Height of the chart image. Must be within the valid range. Minimum: 220. Default is 400.\", \"type\": \"int, optional\", \"default\": \"400\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"peer_ratio_averages\", \"description\": \"Fetches and returns an average of company peer ratios for trailing twelve months (TTM) data for a given company symbol.\", \"parameters\": {\"symbol\": {\"description\": \"The stock symbol of the company for which to fetch peer ratio averages.\", \"type\": \"str\", \"default\": \"AAPL\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"converter\", \"description\": \"Performs currency conversion between multiple currencies using the given parameters.\", \"parameters\": {\"target\": {\"description\": \"The currency code to convert to. This should be a valid three-letter currency code. Multiple target currencies can be specified, separated by a comma.\", \"type\": \"str\", \"default\": \"EUR,INR,JPY\"}, \"source\": {\"description\": \"The currency code to convert from. This should be a valid three-letter currency code, e.g., USD or EUR.\", \"type\": \"str\", \"default\": \"USD\"}, \"amount\": {\"description\": \"The amount to convert from the source currency to the target currency. Defaults to 1 if not provided.\", \"type\": \"int, optional\", \"default\": \"1\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Fetch the candlestick chart data for the BTC/USDT trading pair on Binance with a 4-hour interval for the last 200 candles and a last price of 45000. Also, generate a TradingView mini chart image for the same trading pair with a time interval of 6 months in dark theme, and convert 5000 Euros to US dollars and Japanese yen.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"binance_charts\", \"arguments\": {\"symbol\": \"BTCUSDT\", \"content_type\": \"application/x-www-form-urlencoded\", \"limit\": 200, \"interval\": \"4h\", \"lastprice\": 45000}}, {\"name\": \"mini_chart\", \"arguments\": {\"symbol\": \"BINANCE:BTCUSDT\", \"interval\": \"6M\", \"theme\": \"dark\"}}, {\"name\": \"converter\", \"arguments\": {\"target\": \"USD,JPY\", \"source\": \"EUR\", \"amount\": 5000}}]",
"style": "rule"
}
|
{
"index": 97,
"split": "train"
}
|
[{"name": "disposable_domain_and_suggest_domain", "description": "Checks if the given domain is disposable and provides a suggested alternative domain.", "parameters": {"domain": {"description": "The domain to be checked.", "type": "str", "default": "domain.org"}}}, {"name": "verify", "description": "Verifies an email address by normalizing it and optionally checking SMTP and suggesting a valid domain.", "parameters": {"email": {"description": "The email address to be verified.", "type": "str", "default": "cognitive.camp@gmail.com"}, "checksmtp": {"description": "Whether to check the SMTP server on port 25. Defaults to None.", "type": "bool, optional", "default": "false"}, "suggestdomain": {"description": "Whether to suggest a valid domain if the provided one is incorrect. Defaults to None.", "type": "bool, optional", "default": "false"}}}, {"name": "role_account", "description": "Check if a given domain has a role-based email account using the Fast Email Verifier API.", "parameters": {"domain": {"description": "The domain name to check for role-based email accounts.", "type": "str", "default": "domain.org"}}}]
|
[
{
"from": "human",
"value": "Check if 'support@techfirm.io' is a role-based email and suggest a domain if 'tempdomain.xyz' is disposable."
}
] |
[{"name": "role_account", "arguments": {"domain": "techfirm.io"}}, {"name": "disposable_domain_and_suggest_domain", "arguments": {"domain": "tempdomain.xyz"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"disposable_domain_and_suggest_domain\", \"description\": \"Checks if the given domain is disposable and provides a suggested alternative domain.\", \"parameters\": {\"domain\": {\"description\": \"The domain to be checked.\", \"type\": \"str\", \"default\": \"domain.org\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"verify\", \"description\": \"Verifies an email address by normalizing it and optionally checking SMTP and suggesting a valid domain.\", \"parameters\": {\"email\": {\"description\": \"The email address to be verified.\", \"type\": \"str\", \"default\": \"cognitive.camp@gmail.com\"}, \"checksmtp\": {\"description\": \"Whether to check the SMTP server on port 25. Defaults to None.\", \"type\": \"bool, optional\", \"default\": \"false\"}, \"suggestdomain\": {\"description\": \"Whether to suggest a valid domain if the provided one is incorrect. Defaults to None.\", \"type\": \"bool, optional\", \"default\": \"false\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"role_account\", \"description\": \"Check if a given domain has a role-based email account using the Fast Email Verifier API.\", \"parameters\": {\"domain\": {\"description\": \"The domain name to check for role-based email accounts.\", \"type\": \"str\", \"default\": \"domain.org\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "Check if 'support@techfirm.io' is a role-based email and suggest a domain if 'tempdomain.xyz' is disposable.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"role_account\", \"arguments\": {\"domain\": \"techfirm.io\"}}, {\"name\": \"disposable_domain_and_suggest_domain\", \"arguments\": {\"domain\": \"tempdomain.xyz\"}}]",
"style": "rule"
}
|
{
"index": 98,
"split": "train"
}
|
[{"name": "airports_direct_routes_for_an_airport", "description": "Returns a list of direct routes for a given airport using the RapidAPI service.", "parameters": {"airportiatacode": {"description": "The IATA code of the airport for which the direct routes are being queried.", "type": "str", "default": ""}}}, {"name": "driving_directions", "description": "Fetches driving directions and routes between specified source and destination coordinates using the Waze/Google API.", "parameters": {"source_coordinates": {"description": "Geographic coordinates (latitude, longitude pair) of the starting point.", "type": "str", "default": "32.0852999,34.78176759999999"}, "destination_coordinates": {"description": "Geographic coordinates (latitude, longitude pair) of the destination.", "type": "str", "default": "32.7940463,34.989571"}, "return_route_coordinates": {"description": "Whether to return the route coordinate pairs. Defaults to None.", "type": "bool, optional", "default": ""}, "arrival_timestamp": {"description": "Unix timestamp (seconds since epoch) of the desired arrival time. Defaults to None, which returns directions for the current time.", "type": "int, optional", "default": ""}}}, {"name": "mileages", "description": "Fetch mileage data from the car API based on various optional filters and sorting options.", "parameters": {"make_model_id": {"description": "The ID of the make and model.", "type": "str, optional", "default": ""}, "limit": {"description": "The number of results to limit the response to.", "type": "int, optional", "default": ""}, "make_model_trim_id": {"description": "The ID of the make, model, and trim.", "type": "str, optional", "default": ""}, "trim": {"description": "The trim level of the car.", "type": "str, optional", "default": ""}, "json": {"description": "An array of URL encoded JSON conditions for complex queries.", "type": "str, optional", "default": ""}, "range_highway": {"description": "The range of highway mileage.", "type": "str, optional", "default": ""}, "sort": {"description": "The field to sort the results by. Default is 'id'.", "type": "str, optional", "default": "id"}, "direction": {"description": "The direction to sort by ('asc' or 'desc'). Default is 'asc'.", "type": "str, optional", "default": "asc"}, "range_city": {"description": "The range of city mileage.", "type": "str, optional", "default": ""}, "page": {"description": "The page number for paginated results.", "type": "int, optional", "default": ""}, "combined_mpg": {"description": "The combined miles per gallon value.", "type": "str, optional", "default": ""}, "verbose": {"description": "Include make, model and trim information in the results. Default is 'yes'.", "type": "str, optional", "default": "yes"}, "epa_highway_mpg": {"description": "The EPA highway miles per gallon value.", "type": "str, optional", "default": ""}, "epa_city_mpg": {"description": "The EPA city miles per gallon value.", "type": "str, optional", "default": ""}, "model": {"description": "The car model.", "type": "str, optional", "default": ""}, "year": {"description": "The year of the car.", "type": "str, optional", "default": ""}, "make_id": {"description": "The ID of the car make.", "type": "str, optional", "default": ""}, "make": {"description": "The car make.", "type": "str, optional", "default": ""}}}, {"name": "engines", "description": "Fetches engine information from a car API based on various query parameters.", "parameters": {"year": {"description": "The year of the vehicle.", "type": "str, optional", "default": ""}, "direction": {"description": "The direction to sort the results by, either 'asc' or 'desc'. Defaults to 'asc'.", "type": "str, optional", "default": "asc"}, "valves": {"description": "The number of valves in the engine.", "type": "str, optional", "default": ""}, "valve_timing": {"description": "The valve timing of the engine.", "type": "str, optional", "default": ""}, "fuel_type": {"description": "The fuel type of the vehicle.", "type": "str, optional", "default": ""}, "json": {"description": "A JSON string for complex queries.", "type": "str, optional", "default": ""}, "model": {"description": "The model of the vehicle.", "type": "str, optional", "default": ""}, "make": {"description": "The make of the vehicle.", "type": "str, optional", "default": ""}, "make_model_id": {"description": "The ID of the make and model.", "type": "str, optional", "default": ""}, "trim": {"description": "The trim level of the vehicle.", "type": "str, optional", "default": ""}, "cam_type": {"description": "The cam type of the engine.", "type": "str, optional", "default": ""}, "engine_type": {"description": "The type of the engine.", "type": "str, optional", "default": ""}, "make_model_trim_id": {"description": "The ID of the make, model, and trim.", "type": "str, optional", "default": ""}, "limit": {"description": "The maximum number of results to return.", "type": "int, optional", "default": ""}, "drive_type": {"description": "The drive type of the vehicle.", "type": "str, optional", "default": ""}, "verbose": {"description": "Include additional information such as make, model, and trim when 'yes'. Defaults to 'yes'.", "type": "str, optional", "default": "yes"}, "make_id": {"description": "The ID of the make.", "type": "str, optional", "default": ""}, "cylinders": {"description": "The number of cylinders in the engine.", "type": "str, optional", "default": ""}, "page": {"description": "The page number of the results.", "type": "int, optional", "default": ""}, "sort": {"description": "The field to sort the results by. Defaults to 'id'.", "type": "str, optional", "default": "id"}, "size": {"description": "The size of the engine.", "type": "str, optional", "default": ""}, "horsepower_hp": {"description": "The horsepower of the engine in HP.", "type": "str, optional", "default": ""}, "transmission": {"description": "The type of transmission in the vehicle.", "type": "str, optional", "default": ""}}}]
|
[
{
"from": "human",
"value": "List all engines available for the 2015 Ford Mustang with at least 300 horsepower."
}
] |
[{"name": "engines", "arguments": {"make": "Ford", "model": "Mustang", "year": "2015", "horsepower_hp": "300"}}]
|
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, point it out. If the given question lacks the parameters required by the function,
also point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:
|
toolcall
|
[
{
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. \nBased on the question, you will need to make one or more function/tool calls to achieve the purpose. \nIf none of the function can be used, point it out. If the given question lacks the parameters required by the function,\nalso point it out. You should only return the function call in tools call sections. Here is a list of functions in JSON format that you can invoke:\n# Tool\n\nYou are provided with function signatures within <tools></tools> XML tags:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"airports_direct_routes_for_an_airport\", \"description\": \"Returns a list of direct routes for a given airport using the RapidAPI service.\", \"parameters\": {\"airportiatacode\": {\"description\": \"The IATA code of the airport for which the direct routes are being queried.\", \"type\": \"str\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"driving_directions\", \"description\": \"Fetches driving directions and routes between specified source and destination coordinates using the Waze/Google API.\", \"parameters\": {\"source_coordinates\": {\"description\": \"Geographic coordinates (latitude, longitude pair) of the starting point.\", \"type\": \"str\", \"default\": \"32.0852999,34.78176759999999\"}, \"destination_coordinates\": {\"description\": \"Geographic coordinates (latitude, longitude pair) of the destination.\", \"type\": \"str\", \"default\": \"32.7940463,34.989571\"}, \"return_route_coordinates\": {\"description\": \"Whether to return the route coordinate pairs. Defaults to None.\", \"type\": \"bool, optional\", \"default\": \"\"}, \"arrival_timestamp\": {\"description\": \"Unix timestamp (seconds since epoch) of the desired arrival time. Defaults to None, which returns directions for the current time.\", \"type\": \"int, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"mileages\", \"description\": \"Fetch mileage data from the car API based on various optional filters and sorting options.\", \"parameters\": {\"make_model_id\": {\"description\": \"The ID of the make and model.\", \"type\": \"str, optional\", \"default\": \"\"}, \"limit\": {\"description\": \"The number of results to limit the response to.\", \"type\": \"int, optional\", \"default\": \"\"}, \"make_model_trim_id\": {\"description\": \"The ID of the make, model, and trim.\", \"type\": \"str, optional\", \"default\": \"\"}, \"trim\": {\"description\": \"The trim level of the car.\", \"type\": \"str, optional\", \"default\": \"\"}, \"json\": {\"description\": \"An array of URL encoded JSON conditions for complex queries.\", \"type\": \"str, optional\", \"default\": \"\"}, \"range_highway\": {\"description\": \"The range of highway mileage.\", \"type\": \"str, optional\", \"default\": \"\"}, \"sort\": {\"description\": \"The field to sort the results by. Default is 'id'.\", \"type\": \"str, optional\", \"default\": \"id\"}, \"direction\": {\"description\": \"The direction to sort by ('asc' or 'desc'). Default is 'asc'.\", \"type\": \"str, optional\", \"default\": \"asc\"}, \"range_city\": {\"description\": \"The range of city mileage.\", \"type\": \"str, optional\", \"default\": \"\"}, \"page\": {\"description\": \"The page number for paginated results.\", \"type\": \"int, optional\", \"default\": \"\"}, \"combined_mpg\": {\"description\": \"The combined miles per gallon value.\", \"type\": \"str, optional\", \"default\": \"\"}, \"verbose\": {\"description\": \"Include make, model and trim information in the results. Default is 'yes'.\", \"type\": \"str, optional\", \"default\": \"yes\"}, \"epa_highway_mpg\": {\"description\": \"The EPA highway miles per gallon value.\", \"type\": \"str, optional\", \"default\": \"\"}, \"epa_city_mpg\": {\"description\": \"The EPA city miles per gallon value.\", \"type\": \"str, optional\", \"default\": \"\"}, \"model\": {\"description\": \"The car model.\", \"type\": \"str, optional\", \"default\": \"\"}, \"year\": {\"description\": \"The year of the car.\", \"type\": \"str, optional\", \"default\": \"\"}, \"make_id\": {\"description\": \"The ID of the car make.\", \"type\": \"str, optional\", \"default\": \"\"}, \"make\": {\"description\": \"The car make.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n{\"type\": \"function\", \"function\": {\"name\": \"engines\", \"description\": \"Fetches engine information from a car API based on various query parameters.\", \"parameters\": {\"year\": {\"description\": \"The year of the vehicle.\", \"type\": \"str, optional\", \"default\": \"\"}, \"direction\": {\"description\": \"The direction to sort the results by, either 'asc' or 'desc'. Defaults to 'asc'.\", \"type\": \"str, optional\", \"default\": \"asc\"}, \"valves\": {\"description\": \"The number of valves in the engine.\", \"type\": \"str, optional\", \"default\": \"\"}, \"valve_timing\": {\"description\": \"The valve timing of the engine.\", \"type\": \"str, optional\", \"default\": \"\"}, \"fuel_type\": {\"description\": \"The fuel type of the vehicle.\", \"type\": \"str, optional\", \"default\": \"\"}, \"json\": {\"description\": \"A JSON string for complex queries.\", \"type\": \"str, optional\", \"default\": \"\"}, \"model\": {\"description\": \"The model of the vehicle.\", \"type\": \"str, optional\", \"default\": \"\"}, \"make\": {\"description\": \"The make of the vehicle.\", \"type\": \"str, optional\", \"default\": \"\"}, \"make_model_id\": {\"description\": \"The ID of the make and model.\", \"type\": \"str, optional\", \"default\": \"\"}, \"trim\": {\"description\": \"The trim level of the vehicle.\", \"type\": \"str, optional\", \"default\": \"\"}, \"cam_type\": {\"description\": \"The cam type of the engine.\", \"type\": \"str, optional\", \"default\": \"\"}, \"engine_type\": {\"description\": \"The type of the engine.\", \"type\": \"str, optional\", \"default\": \"\"}, \"make_model_trim_id\": {\"description\": \"The ID of the make, model, and trim.\", \"type\": \"str, optional\", \"default\": \"\"}, \"limit\": {\"description\": \"The maximum number of results to return.\", \"type\": \"int, optional\", \"default\": \"\"}, \"drive_type\": {\"description\": \"The drive type of the vehicle.\", \"type\": \"str, optional\", \"default\": \"\"}, \"verbose\": {\"description\": \"Include additional information such as make, model, and trim when 'yes'. Defaults to 'yes'.\", \"type\": \"str, optional\", \"default\": \"yes\"}, \"make_id\": {\"description\": \"The ID of the make.\", \"type\": \"str, optional\", \"default\": \"\"}, \"cylinders\": {\"description\": \"The number of cylinders in the engine.\", \"type\": \"str, optional\", \"default\": \"\"}, \"page\": {\"description\": \"The page number of the results.\", \"type\": \"int, optional\", \"default\": \"\"}, \"sort\": {\"description\": \"The field to sort the results by. Defaults to 'id'.\", \"type\": \"str, optional\", \"default\": \"id\"}, \"size\": {\"description\": \"The size of the engine.\", \"type\": \"str, optional\", \"default\": \"\"}, \"horsepower_hp\": {\"description\": \"The horsepower of the engine in HP.\", \"type\": \"str, optional\", \"default\": \"\"}, \"transmission\": {\"description\": \"The type of transmission in the vehicle.\", \"type\": \"str, optional\", \"default\": \"\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n",
"role": "system"
},
{
"content": "List all engines available for the 2015 Ford Mustang with at least 300 horsepower.",
"role": "user"
}
] |
toolcall
|
{
"ground_truth": "[{\"name\": \"engines\", \"arguments\": {\"make\": \"Ford\", \"model\": \"Mustang\", \"year\": \"2015\", \"horsepower_hp\": \"300\"}}]",
"style": "rule"
}
|
{
"index": 99,
"split": "train"
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.