import os
import gradio as gr
from dotenv import load_dotenv

from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_astradb import AstraDBVectorStore

#from langchain.agents import AgentExecutor #
from langchain.agents.openai_functions_agent import (
    create_openai_functions_agent,
)
from langchain.tools.retriever import create_retriever_tool
from langchain import hub

from github import fetch_github_issues
from note import note_tool
#import os
#import gradio as gr
#from dotenv import load_dotenv

#from langchain_openai import ChatOpenAI, OpenAIEmbeddings
#from langchain_community.vectorstores import AstraDB
from langchain.agents import initialize_agent, AgentType
#from langchain.tools.retriever import create_retriever_tool
#from langchain import hub

#from github import fetch_github_issues
#from note import note_tool

# ENV

load_dotenv()

# VECTOR STORE
# --------------------------------------------------
def connect_to_vstore():
    embeddings = OpenAIEmbeddings()

    return AstraDBVectorStore(
        embedding=embeddings,
        collection_name="github",
        namespace=os.getenv("ASTRA_DB_KEYSPACE"),
        api_endpoint=os.getenv("ASTRA_DB_API_ENDPOINT"),
        token=os.getenv("ASTRA_DB_APPLICATION_TOKEN"),
    )


vstore = connect_to_vstore()

# --------------------------------------------------
# OPTIONAL: UPDATE VECTOR STORE
# (disable input() for Spaces)
# --------------------------------------------------
UPDATE_VECTORSTORE = True  # change to False if not needed

if UPDATE_VECTORSTORE:
    owner = "Ini-design"
    repo = "register"
    issues = fetch_github_issues(owner, repo)

    try:
        vstore.delete_collection()
    except Exception:
        pass

    vstore = connect_to_vstore()
    vstore.add_documents(issues)

# --------------------------------------------------
# RETRIEVER TOOL
# --------------------------------------------------
retriever = vstore.as_retriever(search_kwargs={"k": 3})

retriever_tool = create_retriever_tool(
    retriever,
    name="github_search",
    description=(
        "Search for information about GitHub issues. "
        "Use this tool for any GitHub issue-related questions."
    ),
)

tools = [retriever_tool, note_tool]

# --------------------------------------------------
# AGENT
# --------------------------------------------------
prompt = hub.pull("hwchase17/openai-functions-agent")

llm = ChatOpenAI(
    model="gpt-3.5-turbo",
    temperature=0,
)

agent = create_openai_functions_agent(
    llm=llm,
    tools=tools,
    prompt=prompt,
)

agent_executor = AgentExecutor(
    agent=agent,
    tools=tools,
    verbose=True,
)

# --------------------------------------------------
# GRADIO APP
# --------------------------------------------------
def answer_question(question):
    if not question.strip():
        return "Please enter a question."

    try:
        response = agent_executor.invoke({"input": question})
        return response["output"]
    except Exception as e:
        return f"Error: {e}"


demo = gr.Interface(
    fn=answer_question,
    inputs=gr.Textbox(
        label="Ask about GitHub Issues",
        placeholder="Type your question here...",
        lines=3,
    ),
    outputs=gr.Textbox(label="Response", lines=6),
    title="GitHub Issues AI Agent",
    description="Ask questions about GitHub issues using AI-powered semantic search.",
    examples=[
        ["What are the recent issues?"],
        ["Are there any open bugs?"],
        ["What features are being requested?"],
    ],
)

if __name__ == "__main__":
    demo.launch(debug=False)