| {"system": "You are a function calling AI model. Given a user query, the following tools are available:\nYou have access to the following tools:\n- Tool: `search_memory`\n - Description: Searches the internal document memory (RAG) for information about specific, previously uploaded files. Use this ONLY for questions about internal or private documents. Topics currently in memory might include: [Security Audit Results, Holiday Schedule].\n - Arguments: {\"query\": {\"type\": \"string\", \"description\": \"The question or topic to search for within the document memory.\"}}\n\nRespond with only the JSON object for the correct tool call.", "instruction": "How did the increased reliance on steam power impact the North American fur trade?", "output": "{\"tool\": \"search_memory\", \"arguments\": {\"query\": \"impact of steam power on the North American fur trade\"}}"} | |
| {"system": "You are a function calling AI model. Given a user query, the following tools are available:\nYou have access to the following tools:\n- Tool: `scrape_url`\n - Description: Scrapes and returns the full text content from a given web URL. Use this when you need to analyze the contents of a specific webpage.\n - Arguments: {\"url\": {\"type\": \"string\", \"description\": \"The valid web URL to scrape (e.g., 'https://example.com').\"}}\n- Tool: `search_memory`\n - Description: Searches the internal document memory (RAG) for information about specific, previously uploaded files. Use this ONLY for questions about internal or private documents. Topics currently in memory might include: [Marketing Strategy 2024, Onboarding Documentation].\n - Arguments: {\"query\": {\"type\": \"string\", \"description\": \"The question or topic to search for within the document memory.\"}}\n\nRespond with only the JSON object for the correct tool call.", "instruction": "How can I find the volume of a cube with a side length of 5 cm?", "output": "{\"tool\": \"scrape_url\", \"arguments\": {\"url\": \"https://www.mathsformulas.com/cube_dimensions.html\"}}"} | |
| {"system": "You are a function calling AI model. Given a user query, the following tools are available:\nYou have access to the following tools:\n- Tool: `search_memory`\n - Description: Searches the internal document memory (RAG) for information about specific, previously uploaded files. Use this ONLY for questions about internal or private documents. Topics currently in memory might include: [Internal Memos, Marketing Strategy 2024, Project Chimera Brief].\n - Arguments: {\"query\": {\"type\": \"string\", \"description\": \"The question or topic to search for within the document memory.\"}}\n- Tool: `respond_to_user`\n - Description: Provides the final answer to the user once all necessary information has been gathered. Use this as the very last step in your reasoning process. You MUST use this tool to communicate with the user.\n - Arguments: {\"final_answer\": {\"type\": \"string\", \"description\": \"The complete, well-formatted, and final response to deliver to the user.\"}}\n- Tool: `internet_search`\n - Description: Searches the internet for real-time information, current events, or general knowledge. Use this for questions about anything public.\n - Arguments: {\"query\": {\"type\": \"string\", \"description\": \"The search query to send to the search engine.\"}}\n\nRespond with only the JSON object for the correct tool call.", "instruction": "What is the capital of France?", "output": "{\"tool\": \"internet_search\", \"arguments\": {\"query\": \"capital of France\"}}"} | |