agent.py

import os
from dotenv import load_dotenv
import pandas as pd
import json
import base64

from langgraph.graph import START, StateGraph, MessagesState
from langgraph.prebuilt import tools_condition
from langgraph.prebuilt import ToolNode
from langchain_groq import ChatGroq
from langchain_community.tools import DuckDuckGoSearchResults
from langchain_community.document_loaders import WikipediaLoader
from langchain_core.messages import SystemMessage, HumanMessage
from langchain_core.tools import tool
from langchain_core.output_parsers import StrOutputParser
from langchain_core.tools import Tool
from langchain_tavily import TavilySearch
from langchain_tavily import TavilySearch, TavilyExtract
from langchain_google_genai import ChatGoogleGenerativeAI


# from langchain_community.tools.tavily_search import TavilySearchResults

from langchain_experimental.utilities import PythonREPL
import assemblyai as aai

load_dotenv()

aai.settings.api_key = os.getenv("ASSEMBLY_AI_KEY")

repl_tool = Tool(
    name="python_repl",
    description="A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.",
    func=PythonREPL().run,
)

# Initialize Tavily Search Tool
tavily_search_tool = TavilySearch(
    max_results=5,
    topic="general",
    search_depth="advanced"
)

# Initialize Tavily Extract Tool
tavily_extract_tool = TavilyExtract()

@tool
def describe_image(file_name: str) -> str:
  """Describe the image.

  Args:
    file_name: name of image file
  """
  with open(file_name, "rb") as image_file:
      encoded_image = base64.b64encode(image_file.read()).decode("utf-8")
  message_local = HumanMessage(
      content=[
          {"type": "text", "text": "Describe the local image."},
          {"type": "image_url", "image_url": f"data:image/png;base64,{encoded_image}"},
      ]
  )
  llm = ChatGoogleGenerativeAI(
    model="gemini-2.0-flash",
    temperature=0.1,
    max_tokens=None,
    timeout=None,
    max_retries=2,
    # other params...
  )
  result_local = llm.invoke([message_local])
  return "Response for local image: {result_local.content}"


@tool
def read_excel_file(file_name: str) -> str:
    """Read the content of excel file.

    Args:
      file_name: name of excel file
    """
    # Load the Excel file using pandas
    try:
        # Read the Excel file
        df = pd.read_excel(file_name, sheet_name=None)  # sheet_name=None loads all sheets
        
        # Convert each sheet to a dictionary of rows
        json_output = {}
        for sheet_name, sheet_data in df.items():
            # Convert the dataframe to a list of dictionaries (rows)
            json_output[sheet_name] = sheet_data.to_dict(orient="records")
        
        # Convert the result to a JSON formatted string
        json_result = json.dumps(json_output, indent=4)
        return json_result
    except Exception as e:
        return str(e)


@tool
def transcribe_audio(file_name: str) -> str:
  """Transcribe the audio file into text.
  
  Args:
    file_name: name of audio file
  """
  config = aai.TranscriptionConfig(speech_model=aai.SpeechModel.best)
  transcript = aai.Transcriber(config=config).transcribe(file_name)
  if transcript.status == "error":
    raise RuntimeError(f"Transcription failed: {transcript.error}")
  return f"Here is the transcript: {transcript.text}"

@tool
def wiki_search(query: str) -> str:
    """Search Wikipedia for a query and return maximum 2 results.
    
    Args:
        query: The search query."""
    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
            for doc in search_docs
        ])
    return {"wiki_results": formatted_search_docs}

@tool
def solve_math_problem(problem: str) -> str:
    """Solve logic or math problem.
    
    Args:
        problem: The problem statement."""
    print('solve')
    llm = ChatGoogleGenerativeAI(
      model="gemini-2.0-flash",
      temperature=0.1,
      max_tokens=None,
      timeout=None,
      max_retries=2,
      # other params...
    )
    response = llm.invoke(problem)
    return response.content


# @tool
# def web_search(query: str) -> str:
#     """Search Tavily for a query and return maximum 3 results.
    
#     Args:
#         query: The search query."""
#     search_docs = TavilySearchResults(max_results=5).invoke(query=query)
#     formatted_search_docs = "\n\n---\n\n".join(
#         [
#             f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
#             for doc in search_docs
#         ])
#     print({"web_results": formatted_search_docs})
#     return {"web_results": formatted_search_docs}

    
system_prompt = """
You are a helpful assistant tasked with answering questions using a set of tools. 
If the question is related to math or logic or a puzzle, ALWAYS USE a tool and NOT trying to answer by yourself.
Now, I will ask you a question. Report your thoughts, and finish your answer with the following template: 
FINAL ANSWER: [YOUR FINAL ANSWER]. 
YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
Your answer should only start with "FINAL ANSWER: ", then follows with the answer. 
"""
sys_msg = SystemMessage(content=system_prompt)


tools = [
    solve_math_problem,
    wiki_search,
    describe_image,
    tavily_search_tool,
    tavily_extract_tool,
    repl_tool,
    read_excel_file,
    transcribe_audio,
    
]


llm = ChatGroq(model="qwen-qwq-32b", temperature=0.1)
llm_with_tools = llm.bind_tools(tools)

def assistant(state: MessagesState):
    """Assistant node"""
    return {"messages": [llm_with_tools.invoke(state["messages"])]}

def final_answer(answer):
  return answer.replace("FINAL ANSWER:","")

builder = StateGraph(MessagesState)
builder.add_node("assistant", assistant)
builder.add_node("tools", ToolNode(tools))
builder.add_edge(START, "assistant")
builder.add_conditional_edges(
    "assistant",
    tools_condition,
)
builder.add_edge("tools", "assistant")
graph = builder.compile()


def get_answer(query):
  messages = [sys_msg, HumanMessage(content=query)]
  results = graph.invoke({"messages": messages})
  return final_answer(results["messages"][-1].content)

if __name__ == "__main__":
    question = "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?"
    # 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."
    # 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?"
    # question = "Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually deposited? Just give me the city name without abbreviations."
    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."
    question ="Given this table defining * on the set S = {a, b, c, d, e}\n\n|*|a|b|c|d|e|\n|---|---|---|---|---|---|\n|a|a|b|c|b|d|\n|b|b|c|a|e|c|\n|c|c|a|b|b|a|\n|d|b|e|b|e|d|\n|e|d|b|a|d|c|\n\nprovide the subset of S involved in any possible counter-examples that prove * is not commutative. Provide your answer as a comma separated list of the elements in the set in alphabetical order."
    # getmessages = [HumanMessage(content=question)]
    # messages = graph.invoke({"messages": messages})
    # for m in messages["messages"]:
    #     m.pretty_print()
    print(f"FINAL ANSWER: {get_answer(question)}")