agent.py

import os
from pathlib import Path
from dotenv import load_dotenv
from langgraph.graph import START, StateGraph, MessagesState
from langgraph.prebuilt import tools_condition
from langgraph.prebuilt import ToolNode
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_core.messages import SystemMessage, HumanMessage
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_community.vectorstores import SupabaseVectorStore
from langchain.tools.retriever import create_retriever_tool
from supabase.client import Client, create_client

from tools.math_tools import add, subtract, multiply, divide, modulus, power, sqrt
from tools.search_tools import search_wikipedia, web_search, arxiv_search
from tools.image_video_tools import query_image
from tools.file_tools import analyze_excel_file, execute_python_code

system_prompt = Path("system_prompt.txt").read_text()

# embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
# supabase: Client = create_client(
#     os.environ.get("SUPABASE_URL"), 
#     os.environ.get("SUPABASE_SERVICE_KEY"))
# vector_store = SupabaseVectorStore(
#     client=supabase,
#     embedding= embeddings,
#     table_name="documents",
#     query_name="match_documents_langchain",
# )
# retriever_tool = create_retriever_tool(
#     retriever=vector_store.as_retriever(),
#     name="Question Search",
#     description="A tool to retrieve similar questions from a vector store.",
# )

def build_graph():
    llm = ChatGoogleGenerativeAI(
        model="gemini-2.0-flash-001",
        temperature=0.8,
        max_tokens=None,
        timeout=None,
        max_retries=2,
        google_api_key=os.getenv("GOOGLE_API_KEY")  # Get API key from environment variable
        )
    tools = [add, subtract, multiply, divide, modulus, power, sqrt, web_search, arxiv_search, search_wikipedia, query_image, analyze_excel_file, execute_python_code]

    llm_with_tools = llm.bind_tools(tools)

    def assistant(state: MessagesState):
        """Assistant node for invoking the LLM."""
        messages = state["messages"]
        # Add system message if not present
        if not any(isinstance(m, SystemMessage) for m in messages):
            messages = [SystemMessage(content=system_prompt)] + messages
        response = llm_with_tools.invoke(messages)
        return {"messages": [response]}
    
    # def retriever(state: MessagesState):
    #     """Retriever node"""
    #     # Add system message if not present
    #     messages = state["messages"]
    #     if not any(isinstance(m, SystemMessage) for m in messages):
    #         messages = [SystemMessage(content="You are a helpful AI assistant. Use the available tools to answer questions accurately. When providing your final answer, use the format: FINAL ANSWER: [your answer]")] + messages
    #     similar_question = vector_store.similarity_search(state["messages"][0].content)

    #     example_msg = HumanMessage(
    #         content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
    #     )
        
    #     return {"messages": messages + [example_msg]}


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

    # Compile graph
    return builder.compile()


if __name__ == "__main__":
    question = "On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?"
    # Build the graph
    graph = build_graph()
    # Run the graph
    messages = [HumanMessage(content=question)]
    messages = graph.invoke({"messages": messages})
    for m in messages["messages"]:
        m.pretty_print()