import gradio as gr
from langgraph.graph import START, StateGraph, MessagesState
from langgraph.prebuilt import tools_condition, ToolNode
from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
from langchain_core.tools import tool
from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
from langchain_core.runnables import RunnableConfig

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


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


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


@tool
def divide(a: int, b: int) -> float:
    """Divide two numbers."""
    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."""
    return a % b

@tool
def wiki_search(query: str) -> dict:
    """Search Wikipedia for a query and return maximum 2 results."""
    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) -> dict:
    """Search Tavily for a query and return maximum 3 results."""
    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) -> dict:
    """Search Arxiv for a query and return maximum 3 results."""
    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}


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

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

# 🧠 LLM setup (ChatHuggingFace via hosted endpoint)
llm = ChatHuggingFace(
    llm=HuggingFaceEndpoint(
        endpoint_url="Qwen/Qwen2.5-Coder-32B-Instruct"
        # huggingfacehub_api_token="your_huggingface_token_here",  # Replace this
    ),
    temperature=0,
)

llm_with_tools = llm.bind_tools(tools)

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

# 🧠 LangGraph setup
def build_graph():
    from langchain_core.messages import HumanMessage, SystemMessage

    llm = ChatHuggingFace(
            llm=HuggingFaceEndpoint
            ( 
                model="Qwen/Qwen2.5-Coder-32B-Instruct",
            ),
            temperature=0, 
            verbose=True
            )

    llm_with_tools = llm.bind_tools(tools)

    with open("system_prompt.txt", "r", encoding="utf-8") as f:
        system_prompt = f.read()
        sys_msg = SystemMessage(content=system_prompt)

    messages = [sys_msg]
    # llm_with_tools = llm.invoke(messages)
    return llm_with_tools, messages