model.py

# ============================
# model.py
# ============================

import os
from dotenv import load_dotenv
from langgraph.graph import START, StateGraph, MessagesState
from langgraph.prebuilt import tools_condition, ToolNode
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_groq import ChatGroq
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
from langchain_community.vectorstores import SupabaseVectorStore
from langchain_core.messages import SystemMessage, HumanMessage
from langchain_core.tools import tool
from langchain_tavily import TavilySearch
from langchain.tools.retriever import create_retriever_tool
from supabase.client import Client, create_client

load_dotenv()

# Setup Supabase
url = os.getenv("SUPABASE_URL")
key = os.getenv("SUPABASE_KEY")
supabase: Client = create_client(url, key)

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

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

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

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

@tool
def modulus(a: int, b: int) -> int:
    """Return the modulus (remainder) of two numbers."""
    return a % b

@tool
def wiki_search(query: str) -> str:
    """Search Wikipedia and return 2 results."""
    docs = WikipediaLoader(query=query, load_max_docs=2).load()
    return "\n\n---\n\n".join(doc.page_content for doc in docs)

@tool
def web_search(query: str) -> str:
    """Search the web using Tavily and return 3 results."""
    docs = TavilySearch(max_results=3).invoke(query)
    return "\n\n---\n\n".join(doc.page_content for doc in docs)

@tool
def arvix_search(query: str) -> str:
    """Search Arxiv for academic papers and return 3 results."""
    docs = ArxivLoader(query=query, load_max_docs=3).load()
    return "\n\n---\n\n".join(doc.page_content[:1000] for doc in docs)

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

sys_msg = SystemMessage(content=system_prompt)

# Vector search setup
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
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="Retrieve similar questions from vector DB.",
)

# Tools list
tools = [
    multiply, add, subtract, divide, modulus,
    wiki_search, web_search, arvix_search,
    retriever_tool,
]

# Build LangGraph

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, api_key=os.getenv("GROQ_API"))
    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")

    llm_with_tools = llm.bind_tools(tools)

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

    def retriever(state: MessagesState):
        docs = vector_store.similarity_search(state["messages"][0].content)
        if not docs:
            return {"messages": [sys_msg] + state["messages"]}
        similar_msg = HumanMessage(content=f"Reference: {docs[0].page_content}")
        return {"messages": [sys_msg] + state["messages"] + [similar_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()


# ============================
# Save this as model.py and let me know when you want full app.py regenerated to match
# ============================