"""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_deepseek import ChatDeepSeek
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
from langchain_tavily import TavilySearch
import time

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) -> float:
    """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 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 = TavilySearch(max_results=3).invoke(input=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 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 formatted_search_docs



# System message
def get_sys_msg():
    sys_msg = ""
    # load the system prompt from the file
    with open("system_prompt.txt", "r", encoding="utf-8") as f:
        system_prompt = f.read()    
        sys_msg = SystemMessage(content=system_prompt)
        
    return sys_msg

# Build a retriever
def get_vector_store():
    """Build a retriever tool."""
    # Load environment variables from .env file
    supabase_url = os.environ.get("SUPABASE_URL")
    supabase_key = os.environ.get("SUPABASE_KEY")
    if not supabase_url or not supabase_key:
        raise ValueError("SUPABASE_URL and SUPABASE_URL must be set in environment variables.")
    supabase: Client = create_client(
        supabase_url, 
        supabase_key)
    
    return SupabaseVectorStore(
        client=supabase,
        embedding= HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2"), #  dim=768
        table_name="documents",
        query_name="match_documents",
    )
    
    return create_retriever_tool(
        retriever=vector_store.as_retriever(),
        name="Question Search",
        description="A tool to retrieve similar questions from a vector store.",
    )

# Tools list (functions that can be called by the LLM): can add more like file reader, image, audio recogonition
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 == "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 == "gemini":
        # Google Gemini
        llm = ChatGoogleGenerativeAI(model="gemini-2.5-pro", temperature=0)
    elif provider == "deepseek":
        # DeepSeek
        llm = ChatDeepSeek(model="deepseek-chat", temperature=0)      
    elif provider == "huggingface":
        # HuggingFace endpoint
        llm = ChatHuggingFace(model="Meta-DeepLearning/llama-2-7b-chat-hf", temperature=0)
    else:
        raise ValueError("Invalid provider. Choose 'gemini', 'groq' or 'huggingface'.")
        
    # Bind tools to LLM
    llm_with_tools = llm.bind_tools(tools)

    sys_msg = get_sys_msg()
    vector_store = get_vector_store()    

    # Assistant Node
    def assistant(state: MessagesState):
        """Assistant node"""
        return {"messages": [llm_with_tools.invoke(state["messages"])]}
    
    # Retriever Node
    def retriever(state: MessagesState):
        """Retriever node"""
        query = state["messages"][0].content
        if not isinstance(query, str):
            query = str(query)
        similar_questions = vector_store.similarity_search(query)
        example_msg = HumanMessage(
            content=f"Here I provide a similar question and answer for reference: \n\n{similar_questions[0].page_content}",
        )
        return {"messages": [sys_msg] + state["messages"] + [example_msg]}

    # Build the graph (workflow)  
    builder = StateGraph(MessagesState)         # StateGraph is a graph that stores the state of the conversation
    builder.add_node("retriever", retriever)    # Retriever Node
    builder.add_node("assistant", assistant)    # Assistant Node
    builder.add_node("tools", ToolNode(tools)) # Tool Node
    builder.add_edge(START, "retriever")       # Edge from START to Retriever Node
    builder.add_edge("retriever", "assistant") # Edge from Retriever Node to Assistant Node
    builder.add_conditional_edges("assistant", tools_condition) # Edge from Assistant Node to Tool Node
    builder.add_edge("tools", "assistant")     # Edge from Tool Node to Assistant Node

    # Compile graph
    return builder.compile()

# test
if __name__ == "__main__":
    from langchain_core.messages import AnyMessage
    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="deepseek")
    # Run the graph
    messages: list[AnyMessage] = [HumanMessage(content=question)]
    result = graph.invoke({"messages": messages})
    for m in result["messages"]:
        m.pretty_print()