agent.py

"""LangGraph Agent"""
import os
from dotenv import load_dotenv


from langchain_core.tools import tool
from langchain_tavily import TavilySearch
from langchain_community.document_loaders import ArxivLoader, WikipediaLoader
from langchain_core.messages import AIMessage
from langgraph.graph import StateGraph, MessagesState
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_groq import ChatGroq
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
from langchain_community.vectorstores import SupabaseVectorStore
from langchain.tools.retriever import create_retriever_tool
from supabase.client import Client, create_client


@tool
def multiply(a: int, b: int) -> int:
    """Multiply two numbers.
    Args:
        a: first int
        b: second int
    """
    return a * b

@tool
def add(a: int, b: int) -> int:
    """Add two numbers.
    
    Args:
        a: first int
        b: second int
    """
    return a + b

@tool
def subtract(a: int, b: int) -> int:
    """Subtract two numbers.
    
    Args:
        a: first int
        b: second int
    """
    return a - b

@tool
def divide(a: int, b: int) -> int:
    """Divide two numbers.
    
    Args:
        a: first int
        b: second int
    """
    if b == 0:
        raise ValueError("Cannot divide by zero.")
    return a / b

@tool
def modulus(a: int, b: int) -> int:
    """Get the modulus of two numbers.
    
    Args:
        a: first int
        b: second int
    """
    return a % b

@tool
def web_search(query: str) -> str:
    """Search the web for a query.

    Args:
        query: The search query string.

    Returns:
        The search results as a string.
    """
    raw_result = TavilySearch(max_results=3).invoke(query)
    search_results = raw_result.get("results", [])

    formatted_search_results = "\n\n---\n\n".join(
        [
            f'<Document source="{res.get("url")}" page=""/>\n{res.get("content", "")}\n</Document>'
            for res in search_results
        ])
    return {"web_results": formatted_search_results}

@tool
def arxiv_search(query: str) -> str:
    """Search Arxiv for a query and return maximum 3 result.
    
    Args:
        query: The search query."""
    loader = ArxivLoader(query=query, load_max_docs=3).load()
    docs = loader.load()

    formatted_list = []
    for doc in docs:
        if "id" in doc:
            arxiv_id = doc["id"]
            source = f"https://arxiv.org/abs/{arxiv_id}"

            formatted = f'<Document Source="{source}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
            formatted_list.append(formatted)

    formatted_search_docs = "\n\n---\n\n".join(formatted_list)

    return {"arxiv_results": formatted_search_docs}

@tool
def wiki_search(query: str) -> str:
    """Search Wikipedia for a query and return maximum 3 result.
    
    Args:
        query: The search query."""

    loader = WikipediaLoader(query=query, load_max_docs=3)
    docs = loader.load()

    formatted_docs = "\n\n---\n\n".join(
        f'<Document Source="{doc.metadata.get("source", "")}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
        for doc in docs
    )

    return {"wiki_results": formatted_docs}

tools = [
    multiply,
    add,
    subtract,
    divide,
    modulus,
    wiki_search,
    web_search,
    arxiv_search,
]

# Build retriever
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",
)
create_retriever_tool = create_retriever_tool(
    retriever=vector_store.as_retriever(),
    name="Question Search",
    description="A tool to retrieve similar questions from a vector store.",
)


# Build graph function
def build_graph(provider: str = "google"):
    """Build the graph"""
    # Load environment variables from .env file
    if provider == "google":
        # Google Gemini
        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
    elif provider == "groq":
        # Groq https://console.groq.com/docs/models
        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
    elif provider == "huggingface":
        # TODO: Add huggingface endpoint
        llm = ChatHuggingFace(
            llm=HuggingFaceEndpoint(
                url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
                temperature=0,
            ),
        )
    else:
        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
    
    # Bind tools to LLM
    llm_with_tools = llm.bind_tools(tools)

    def retriever(state: MessagesState):
        query = state["messages"][-1].content
        similar_doc = vector_store.similarity_search(query, k=1)[0]

        content = similar_doc.page_content
        if "Final answer :" in content:
            answer = content.split("Final answer :")[-1].strip()
        else:
            answer = content.strip()

        return {"messages": [AIMessage(content=answer)]}

    builder = StateGraph(MessagesState)
    builder.add_node("retriever", retriever)

    # Retriever start and end points
    builder.set_entry_point("retriever")
    builder.set_finish_point("retriever")

    # Compile graph
    return builder.compile()


if __name__ == "__main__":
    # Example usage
    print("testing agent tools")
    print(web_search("LangGraph Agent"))  # Outputs search results as a string