agent.py

"""LangGraph Agent"""
import os
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_groq import ChatGroq
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_community.document_loaders import WikipediaLoader
from langchain_community.document_loaders import ArxivLoader
from langchain_community.vectorstores import SupabaseVectorStore
from langchain_core.messages import SystemMessage, HumanMessage
from langchain_core.tools import tool
from langchain.tools.retriever import create_retriever_tool
from supabase.client import Client, create_client

load_dotenv()

@tool
def multiply(a: int, b: int) -> int:
    """Multiply two integers and return the result."""
    return a * b

@tool
def add(a: int, b: int) -> int:
    """Add two integers and return the result."""
    return a + b

@tool
def subtract(a: int, b: int) -> int:
    """Subtract the second integer from the first and return the result."""
    return a - b

@tool
def divide(a: int, b: int) -> float:
    """Divide the first integer by the second and return the result as float."""
    if b == 0:
        raise ValueError("Cannot divide by zero.")
    return a / b

@tool
def modulus(a: int, b: int) -> int:
    """Return the remainder when the first integer is divided by the second."""
    return a % b

@tool
def wiki_search(query: str) -> str:
    """Search Wikipedia for a query and return up to 2 results."""
    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
    formatted = "\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}

@tool
def web_search(query: str) -> str:
    """Search Tavily for a query and return up to 3 results."""
    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
    formatted = "\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 {"web_results": formatted}

@tool
def arvix_search(query: str) -> str:
    """Search Arxiv for a query and return up to 3 results."""
    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
    formatted = "\n\n---\n\n".join(
        [f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>' for doc in search_docs]
    )
    return {"arvix_results": formatted}

# Load system prompt
with open("system_prompt.txt", "r", encoding="utf-8") as f:
    system_prompt = f.read()

sys_msg = SystemMessage(content=system_prompt)

# Setup Supabase vector retriever
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
supabase: Client = create_client(os.environ.get("SUPABASE_URL"), os.environ.get("SUPABASE_SERVICE_KEY"))
vector_store = SupabaseVectorStore(
    client=supabase,
    embedding=embeddings,
    table_name="Vector_Test",
    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."
)

# Define tool list
tools = [
    multiply, add, subtract, divide, modulus,
    wiki_search, web_search, arvix_search
]

# Build graph
def build_graph(provider: str = "groq"):
    if provider == "google":
        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
    elif provider == "groq":
        llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
    elif provider == "huggingface":
        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'.")

    llm_with_tools = llm.bind_tools(tools)

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

    def retriever(state: MessagesState):
        similar = 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[0].page_content}")
        return {"messages": [sys_msg] + state["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, "retriever")
    builder.add_edge("retriever", "assistant")
    builder.add_conditional_edges("assistant", tools_condition)
    builder.add_edge("tools", "assistant")

    return builder.compile()

if __name__ == "__main__":
    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
    graph = build_graph("groq")
    messages = [HumanMessage(content=question)]
    messages = graph.invoke({"messages": messages})
    for m in messages["messages"]:
        m.pretty_print()