from flask import Flask, request, jsonify
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
import os

app = Flask(__name__)

load_dotenv()
OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')

def get_pdf_text(pdf_docs):
    text = ""
    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf)
        for page in pdf_reader.pages:
            text += page.extract_text()
    return text

def get_text_chunks(text):
    text_splitter = CharacterTextSplitter(
        separator="\n",
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )
    chunks = text_splitter.split_text(text)
    return chunks

def get_vectorstore(text_chunks):
    embeddings = OpenAIEmbeddings()
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

def get_conversation_chain(vectorstore):
    llm = ChatOpenAI()
    memory = ConversationBufferMemory(
        memory_key='chat_history', return_messages=True)
    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=llm,
        retriever=vectorstore.as_retriever(),
        memory=memory
    )
    return conversation_chain

@app.route('/upload', methods=['POST'])
def upload_files():
    if 'files' not in request.files:
        return jsonify({"error": "No file part in the request"}), 400
    files = request.files.getlist('files')
    raw_text = get_pdf_text(files)
    text_chunks = get_text_chunks(raw_text)
    vectorstore = get_vectorstore(text_chunks)
    global conversation_chain
    conversation_chain = get_conversation_chain(vectorstore)
    return jsonify({"status": "Files processed successfully"}), 200

@app.route('/query', methods=['POST'])
def query():
    if 'question' not in request.json:
        return jsonify({"error": "No question provided"}), 400
    question = request.json['question']
    if 'conversation_chain' not in globals():
        return jsonify({"error": "No conversation chain initialized. Please upload documents first."}), 400
    
    response = conversation_chain({'question': question})
    return jsonify({"response": response['answer']})