agent.py

"""LangGraph Agent"""

import os

from dotenv import load_dotenv
from langchain.agents import Tool, initialize_agent
from langchain.tools.retriever import create_retriever_tool
from langchain_community.document_loaders import ArxivLoader, WikipediaLoader
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_community.vectorstores import SupabaseVectorStore
from langchain_core.messages import HumanMessage, SystemMessage
from langchain_core.tools import tool
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_groq import ChatGroq
from langchain_huggingface import (
    ChatHuggingFace,
    HuggingFaceEmbeddings,
    HuggingFaceEndpoint,
)
from langchain_openai import ChatOpenAI
from langgraph.graph import START, MessagesState, StateGraph
from langgraph.prebuilt import ToolNode, tools_condition
from supabase.client import Client, create_client

load_dotenv()


@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 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 Tavily for a query and return maximum 3 results.
    Args:
        query: The search query."""
    search_docs = TavilySearchResults(max_results=3).invoke(
        query
    )  # Fixed: pass query as positional argument
    return {"web_results": search_docs}  # Also fixed the return type issue


@tool
def arvix_search(query: str) -> str:
    """Search Arxiv for a query and return maximum 3 result.
    Args:
        query: The search query."""
    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
    formatted_search_docs = "\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_search_docs}


def test_supabase_connection():
    load_dotenv()

    try:
        supabase = create_client(
            os.environ.get("SUPABASE_URL"), os.environ.get("SUPABASE_SERVICE_KEY")
        )

        # Test query
        result = supabase.table("documents").select("*").limit(1).execute()
        print("Connection successful!")
        return True

    except Exception as e:
        print(f"Connection failed: {e}")
        return False


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

# System message
sys_msg = SystemMessage(content=system_prompt)

# build a 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.",
)

test_supabase_connection()

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


# 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-2.5-flash-preview-05-20", 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 == "openai":
        # OpenAI
        llm = ChatOpenAI(model="gpt-4o-mini", 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'.")
    # Bind tools to LLM
    llm_with_tools = llm.bind_tools(tools)

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

    def retriever(state: MessagesState):
        """Retriever node"""
        try:
            # Use the vector store to find similar questions
            similar_question = vector_store.similarity_search(
                state["messages"][0].content
            )
            if not similar_question:
                raise ValueError("No similar questions found.")
        except Exception as e:
            print(f"Error occurred while searching for similar questions: {e}")
            return {"messages": [sys_msg] + state["messages"]}

        example_msg = HumanMessage(
            content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[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")

    # Compile graph
    return builder.compile()