import gradio as gr
import os

from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import Chroma
from langchain.chains import ConversationalRetrievalChain
from langchain_community.embeddings import HuggingFaceEmbeddings 
from langchain_community.llms import HuggingFacePipeline
from langchain.chains import ConversationChain
from langchain.memory import ConversationBufferMemory
from langchain_community.llms import HuggingFaceEndpoint

from pathlib import Path
import chromadb
from unidecode import unidecode

from transformers import AutoTokenizer
import transformers
import torch
import tqdm 
import accelerate
import re

list_llm = ["HuggingFaceH4/zephyr-7b-beta", "mistralai/Mistral-7B-Instruct-v0.2"]
list_llm_simple = [os.path.basename(llm) for llm in list_llm]

def summarize_document(document_text):
    # Your summarization code here
    summary = "The document covers various topics such as X, Y, and Z, providing detailed insights into each aspect."
    return summary

def demo():
    with gr.Blocks(theme="base") as demo:
        gr.Markdown("<center><h2>PDF Summarizer</center></h2>")
        
        text_input = gr.Textbox(placeholder="Paste your document text here", label="Document Text")
        summarize_btn = gr.Button("Summarize")
        summary_output = gr.Textbox(readonly=True, label="Summary")
        
        summarize_btn.click(summarize_document, inputs=[text_input], outputs=[summary_output])
        
    demo.launch()

if __name__ == "__main__":
    demo()