"""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
from langchain_core.messages import SystemMessage, HumanMessage
from langchain_core.tools import tool
from langchain.tools.retriever import create_retriever_tool
from langchain_community.document_loaders import ArxivLoader
import ast
import pandas as pd
from langchain_community.vectorstores import FAISS
from langchain.agents import initialize_agent, AgentType
import requests
from transformers import pipeline

load_dotenv()
# os.environ["TAVILY_API_KEY"]=""
os.getenv("TAVILY_API_KEY")
os.getenv("HF_TOKEN")
# model_endpoint = os.getenv("model_endpoint")
# access_token = os.getenv("access_token")

# system_prompt = "You are a helpful assistant. Always answer as helpfully as possible, give the exact answer without any detaile just the answer don't add any text."
# user_question = "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia."
 
# def query_model(
#     user_question: str,
#     text: str,
#     system_prompt: str,
#     model_endpoint: str,
#     access_token: str
# ) -> str:
#     """
#     Send `text` plus `user_question` to the model endpoint, returning its reply.
#     """
#     headers = {
#         "Authorization": f"Bearer {access_token}",
#         "Content-Type": "application/json"
#     }
#     payload = {
#         "messages": [
#             {"role": "system", "content": system_prompt},
#             {"role": "user", "content": f"Text: {text}\n\nQuestion: {user_question}"}
#         ],
#         "temperature": 0.3,
#         "max_tokens": 5000,
#         "n": 1
#     }


#     resp = requests.post(model_endpoint, headers=headers, json=payload)
#     resp.raise_for_status()
#     data = resp.json()
#     return data["choices"][0]["message"]["content"]


@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 substract(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}

@tool
def transcribe_audio(file_path: str) -> str:
    """Transcribe audio files to text using speech recognition.
    
    Args:
        file_path: Path to audio file (supports .mp3, .wav, .flac, etc.)
    """
    transcriber = pipeline(
        "automatic-speech-recognition",
        model="openai/whisper-medium"
    )
    return transcriber(file_path)["text"]


# with open("Systeme_prompt.txt", "r", encoding="Utf-8")as f:
#     system_promt = f.read()
System_promt = """You are a concise assistant. When asked a question, reply with the answer only—no explanations, commentary, or extra words.
Your answer should only start with "FINAL ANSWER: ", then follows with the answer. 
"""

sys_msg  = SystemMessage(content=System_promt)

# 1) LOAD YOUR DATAFRAME
df = pd.read_csv("supabase_docs.csv")

# 2) PARSE 'embedding' AND 'metadata' COLUMNS
df["embedding"] = df["embedding"].apply(
    lambda e: ast.literal_eval(e) if isinstance(e, str) else e
)
df["metadata"] = df["metadata"].apply(
    lambda m: ast.literal_eval(m) if isinstance(m, str) else m
)

texts     = df["content"].tolist()
embeddings = df["embedding"].tolist()
metadatas  = df["metadata"].tolist()
ids        = df.index.astype(str).tolist()

# 3) SET UP QUERY-TIME EMBEDDINGS
embedder = HuggingFaceEmbeddings(
    model_name="sentence-transformers/all-mpnet-base-v2"
)

# 4) BUILD THE FAISS INDEX
vector_store = FAISS.from_embeddings(
    text_embeddings=zip(texts, embeddings),
    embedding=embedder,
    metadatas=metadatas,
    ids=ids,
)

# 5) CREATE A RETRIEVER
retriever = vector_store.as_retriever(search_kwargs={"k": 5})

# 6) EXPOSE AS A TOOL
question_search_tool = create_retriever_tool(
    retriever=retriever,
    name="Question Search",
    description="Retrieve the top 5 most similar questions given a user query."
)

tools = [
    multiply,
    add,
    substract,
    divide,
    modulus,
    wiki_search,
    web_search,
    arvix_search,
    transcribe_audio,
    question_search_tool
]

def build_graph(provider: str = "Huggingface"):
    "building the graph"
    if provider == "Huggingface":
       llm_ENDPOINT = HuggingFaceEndpoint(
          repo_id="meta-llama/Llama-4-Scout-17B-16E-Instruct",
          task="text-generation",
          max_new_tokens=512,
          do_sample=False,
          repetition_penalty=1.03,
          )

       llm = ChatHuggingFace(llm=llm_ENDPOINT)
    else:
        raise ValueError("Invalide model")
    llm_with_tools = llm.bind_tools(tools)
    
    def assistant(state: MessagesState):
        """Assistant node"""
        return {"messages": [llm_with_tools.invoke(state["messages"])]}
    
    def retriever(state: MessagesState):
        """Retrive node"""
        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]}
    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()