Spaces:
Sleeping
Sleeping
Nguyen Nhu Trung
commited on
Commit
·
1c89ca6
1
Parent(s):
eea473e
update tool description -- increase delay
Browse files
agent.py
CHANGED
|
@@ -43,16 +43,16 @@ tavily_extract_tool = TavilyExtract()
|
|
| 43 |
|
| 44 |
|
| 45 |
@tool
|
| 46 |
-
def read_excel_file(
|
| 47 |
"""Read the content of excel file.
|
| 48 |
|
| 49 |
Args:
|
| 50 |
-
|
| 51 |
"""
|
| 52 |
# Load the Excel file using pandas
|
| 53 |
try:
|
| 54 |
# Read the Excel file
|
| 55 |
-
df = pd.read_excel(
|
| 56 |
|
| 57 |
# Convert each sheet to a dictionary of rows
|
| 58 |
json_output = {}
|
|
@@ -68,14 +68,14 @@ def read_excel_file(excel_file_path: str) -> str:
|
|
| 68 |
|
| 69 |
|
| 70 |
@tool
|
| 71 |
-
def transcribe_audio(
|
| 72 |
"""Transcribe the audio file into text.
|
| 73 |
|
| 74 |
Args:
|
| 75 |
-
|
| 76 |
"""
|
| 77 |
config = aai.TranscriptionConfig(speech_model=aai.SpeechModel.best)
|
| 78 |
-
transcript = aai.Transcriber(config=config).transcribe(
|
| 79 |
if transcript.status == "error":
|
| 80 |
raise RuntimeError(f"Transcription failed: {transcript.error}")
|
| 81 |
return f"Here is the transcript: {transcript.text}"
|
|
@@ -92,6 +92,7 @@ def wiki_search(query: str) -> str:
|
|
| 92 |
f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
|
| 93 |
for doc in search_docs
|
| 94 |
])
|
|
|
|
| 95 |
return {"wiki_results": formatted_search_docs}
|
| 96 |
|
| 97 |
# @tool
|
|
@@ -122,8 +123,8 @@ sys_msg = SystemMessage(content=system_prompt)
|
|
| 122 |
|
| 123 |
tools = [
|
| 124 |
wiki_search,
|
| 125 |
-
|
| 126 |
-
|
| 127 |
repl_tool,
|
| 128 |
read_excel_file,
|
| 129 |
transcribe_audio
|
|
@@ -168,9 +169,9 @@ def get_answer(query):
|
|
| 168 |
|
| 169 |
if __name__ == "__main__":
|
| 170 |
question = "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?"
|
| 171 |
-
question = "Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study for my Calculus mid-term next week. My friend from class sent me an audio recording of Professor Willowbrook giving out the recommended reading for the test, but my headphones are broken :(\n\nCould you please listen to the recording for me and tell me the page numbers I'm supposed to go over? I've attached a file called Homework.mp3 that has the recording. Please provide just the page numbers as a comma-delimited list. And please provide the list in ascending order."
|
| 172 |
-
question = "What is the first name of the only Malko Competition recipient from the 20th Century (after 1977) whose nationality on record is a country that no longer exists?"
|
| 173 |
-
question = "Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually deposited? Just give me the city name without abbreviations."
|
| 174 |
question = "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia."
|
| 175 |
# getmessages = [HumanMessage(content=question)]
|
| 176 |
# messages = graph.invoke({"messages": messages})
|
|
|
|
| 43 |
|
| 44 |
|
| 45 |
@tool
|
| 46 |
+
def read_excel_file(file_name: str) -> str:
|
| 47 |
"""Read the content of excel file.
|
| 48 |
|
| 49 |
Args:
|
| 50 |
+
file_name: name of excel file
|
| 51 |
"""
|
| 52 |
# Load the Excel file using pandas
|
| 53 |
try:
|
| 54 |
# Read the Excel file
|
| 55 |
+
df = pd.read_excel(file_name, sheet_name=None) # sheet_name=None loads all sheets
|
| 56 |
|
| 57 |
# Convert each sheet to a dictionary of rows
|
| 58 |
json_output = {}
|
|
|
|
| 68 |
|
| 69 |
|
| 70 |
@tool
|
| 71 |
+
def transcribe_audio(file_name: str) -> str:
|
| 72 |
"""Transcribe the audio file into text.
|
| 73 |
|
| 74 |
Args:
|
| 75 |
+
file_name: name of audio file
|
| 76 |
"""
|
| 77 |
config = aai.TranscriptionConfig(speech_model=aai.SpeechModel.best)
|
| 78 |
+
transcript = aai.Transcriber(config=config).transcribe(file_name)
|
| 79 |
if transcript.status == "error":
|
| 80 |
raise RuntimeError(f"Transcription failed: {transcript.error}")
|
| 81 |
return f"Here is the transcript: {transcript.text}"
|
|
|
|
| 92 |
f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
|
| 93 |
for doc in search_docs
|
| 94 |
])
|
| 95 |
+
print(formatted_search_docs)
|
| 96 |
return {"wiki_results": formatted_search_docs}
|
| 97 |
|
| 98 |
# @tool
|
|
|
|
| 123 |
|
| 124 |
tools = [
|
| 125 |
wiki_search,
|
| 126 |
+
tavily_search_tool,
|
| 127 |
+
tavily_extract_tool,
|
| 128 |
repl_tool,
|
| 129 |
read_excel_file,
|
| 130 |
transcribe_audio
|
|
|
|
| 169 |
|
| 170 |
if __name__ == "__main__":
|
| 171 |
question = "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?"
|
| 172 |
+
# question = "Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study for my Calculus mid-term next week. My friend from class sent me an audio recording of Professor Willowbrook giving out the recommended reading for the test, but my headphones are broken :(\n\nCould you please listen to the recording for me and tell me the page numbers I'm supposed to go over? I've attached a file called Homework.mp3 that has the recording. Please provide just the page numbers as a comma-delimited list. And please provide the list in ascending order."
|
| 173 |
+
# question = "What is the first name of the only Malko Competition recipient from the 20th Century (after 1977) whose nationality on record is a country that no longer exists?"
|
| 174 |
+
# question = "Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually deposited? Just give me the city name without abbreviations."
|
| 175 |
question = "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia."
|
| 176 |
# getmessages = [HumanMessage(content=question)]
|
| 177 |
# messages = graph.invoke({"messages": messages})
|
app.py
CHANGED
|
@@ -77,7 +77,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
|
|
| 77 |
answers_payload = []
|
| 78 |
print(f"Running agent on {len(questions_data)} questions...")
|
| 79 |
for item in questions_data:
|
| 80 |
-
time.sleep(
|
| 81 |
task_id = item.get("task_id")
|
| 82 |
question_text = item.get("question")
|
| 83 |
if not task_id or question_text is None:
|
|
|
|
| 77 |
answers_payload = []
|
| 78 |
print(f"Running agent on {len(questions_data)} questions...")
|
| 79 |
for item in questions_data:
|
| 80 |
+
time.sleep(10)
|
| 81 |
task_id = item.get("task_id")
|
| 82 |
question_text = item.get("question")
|
| 83 |
if not task_id or question_text is None:
|