utils/agent2.py

import os
from dotenv import load_dotenv

from langchain_core.tools import tool
from langgraph.prebuilt import tools_condition, ToolNode
from langgraph.graph import START, StateGraph, MessagesState

from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
from langchain_core.messages import SystemMessage, HumanMessage
from langchain_community.vectorstores import FAISS 
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_groq import ChatGroq
from langchain.tools.retriever import create_retriever_tool

"""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,FAISS 
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

# ──────────────────────────────────────────────────────────
# ENV
# ──────────────────────────────────────────────────────────
load_dotenv()
# API Keys from .env file
os.environ.setdefault("OPENAI_API_KEY", "<YOUR_OPENAI_KEY>")  # Set your own key or env var
os.environ["GROQ_API_KEY"] = os.getenv("GROQ_API_KEY", "default_key_or_placeholder")
os.environ["MISTRAL_API_KEY"] = os.getenv("MISTRAL_API_KEY", "default_key_or_placeholder")

# Tavily API Key
TAVILY_API_KEY = os.getenv("TAVILY_API_KEY", "default_key_or_placeholder")
_forbidden = ["nsfw", "porn", "sex", "explicit"]
_playwright_available = True  # set False to disable Playwright

embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")  # dim = 768

@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=query)
    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 {"web_results": formatted_search_docs}

@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}



# 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

INDEX_PATH = "faiss_index"
if os.path.exists(INDEX_PATH):
    vector_store = FAISS.load_local(INDEX_PATH, embeddings, allow_dangerous_deserialization=True)
else:
    vector_store = FAISS.from_texts(["__init__"], embeddings)
    vector_store.save_local(INDEX_PATH)

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



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

# Build graph function
def build_graph(provider: str = "groq"):
    """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
        try:
            llm = ChatGroq(model="deepseek-r1-distill-llama-70b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
        except Exception as e:
            print(f"Error initializing Groq: {str(e)}")
            raise
    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)

    # Node
    def assistant(state: MessagesState):
        """Assistant node"""
        try:
            if not state["messages"] or not state["messages"][-1].content:
                raise ValueError("Empty message content")
            return {"messages": [llm_with_tools.invoke(state["messages"])]}
        except Exception as e:
            print(f"Error in assistant node: {str(e)}")
            raise
    
    def retriever(state: MessagesState):
        """Retriever node"""
        try:
            if not state["messages"] or not state["messages"][0].content:
                raise ValueError("Empty message content")
            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": [sys_msg] + state["messages"] + [example_msg]}
        except Exception as e:
            print(f"Error in retriever node: {str(e)}")
            raise

    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()

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