agent.py

import os
from dotenv import load_dotenv
import pandas as pd
import json
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_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,
)

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

    Args:
      excel_file_path: path to excel file
    """
    # Load the Excel file using pandas
    try:
        # Read the Excel file
        df = pd.read_excel(excel_file_path, 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_path: str) -> str:
  """Transcribe the audio file into text.
  
  Args:
    file_path: path to audio file
  """
  config = aai.TranscriptionConfig(speech_model=aai.SpeechModel.best)
  transcript = aai.Transcriber(config=config).transcribe(file_path)
  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 web_search(query: str) -> str:
    """Search DuckDuckGo for a query and return maximum 5 results.
    
    Args:
        query: The search query."""
    search_docs = DuckDuckGoSearchResults(max_results=5).invoke(query)
    return {"web_results": search_docs}
    

system_prompt =  "You are a helpful assistant"
sys_msg = SystemMessage(content=system_prompt)

tools = [
    wiki_search,
    web_search,
    repl_tool,
    read_excel_file,
    transcribe_audio
]

llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
llm_with_tools = llm.bind_tools(tools)

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

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 = [HumanMessage(content=query)]
  results = graph.invoke({"messages": messages})
  return 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?"
    messages = [HumanMessage(content=question)]
    messages = graph.invoke({"messages": messages})
    for m in messages["messages"]:
        m.pretty_print()