"""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.vectorstores import SupabaseVectorStore
from langchain_core.messages import SystemMessage, HumanMessage
from langchain.tools.retriever import create_retriever_tool
from supabase.client import Client, create_client
from langchain_litellm import ChatLiteLLM

# Tools
from tools.wiki_search import wiki_search
from tools.web_search import web_search
from tools.arvix_search import arvix_search
from tools.python_code_parser import python_code_parser
from tools.multiply import multiply
from tools.add import add
from tools.divide import divide
from tools.modulus import modulus
from tools.power import power
from tools.subtract import subtract
from tools.square_root import square_root
from tools.execute_code_multilang import execute_code_multilang
from tools.save_read_file import save_read_file
from tools.download_file import download_file
from tools.extract_text_from_image import extract_text_from_image
from tools.analyze_csv_file import analyze_csv_file
from tools.analyze_excel_file import analyze_excel_file

load_dotenv()

# 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
supabase: Client = create_client(
    os.environ.get("SUPABASE_URL"), 
    os.environ.get("SUPABASE_SERVICE_KEY"))
vector_store = SupabaseVectorStore(
    client=supabase,
    embedding= embeddings,
    table_name="documents",
    query_name="match_documents_langchain",
)
create_retriever_tool = create_retriever_tool(
    retriever=vector_store.as_retriever(),
    name="Question Search",
    description="A tool to retrieve similar questions from a vector store.",
)

tools = [
    wiki_search,
    web_search,
    arvix_search,
    python_code_parser,
    add,
    multiply,
    divide,
    execute_code_multilang,
    modulus,
    power,
    subtract,
    square_root,
    save_read_file,
    download_file,
    extract_text_from_image,
    analyze_csv_file,
    analyze_excel_file,
]

# Build graph function
def build_graph(provider: str = "google"):
    """Build the graph"""
    # Load environment variables from .env file
    if provider == "google":
        # Google Gemini
        llm = ChatGoogleGenerativeAI(
            model="gemini-2.0-flash", 
            temperature=0,
            generation_config={
                "temperature": 0.0,
                "max_output_tokens": 2000,
                "candidate_count": 1,
            }
        )
    elif 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 == "huggingface":
        llm = ChatHuggingFace(
            llm=HuggingFaceEndpoint(
                repo_id="mistralai/Mistral-7B-Instruct-v0.2",
                temperature=0,
                # Other models to try:
                # "meta-llama/Llama-2-7b-chat-hf"
                # "google/gemma-7b-it"
                # "mosaicml/mpt-7b-instruct"
                # "tiiuae/falcon-7b-instruct"
                token=os.environ.get("HF_TOKEN"),
            )
        )
    elif provider == "litellm":
        # HuggingFace Embeddings
        llm = ChatLiteLLM(
                model_id="ollama_chat/qwen2:7b",
                api_base="http://127.0.0.1:11434",
                num_ctx=8192,
            )
    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"""
        return {"messages": [llm_with_tools.invoke(state["messages"])]}
    
    def retriever(state: MessagesState):
        """Retriever 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()

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