import gradio as gr
from langchain_together import ChatTogether
from langchain_community.llms import Together
from langchain_pinecone import PineconeVectorStore
from langchain_openai import OpenAIEmbeddings
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_community.document_loaders import PyPDFLoader
from elevenlabs.client import ElevenLabs
from transformers import AutoTokenizer, AutoModelForCausalLM
import os
import torch
from io import BytesIO

# Environment Variables
os.environ['TOGETHER_API_KEY'] = 'e83925ff068ab5e4598a56f68385fd37144469f50eec94f5c2e6647798f1be9e'
os.environ['PINECONE_API_KEY'] = 'f7413055-9b13-4bbc-8c92-56132e034bff'

# Define your functions and classes here based on your original code

# Example function to process questions
def process_question(file):
    # Use your existing functions to process the PDF and generate outputs
    pdffile = extract_text_from_pdf(file)
    three_topics = topic_chain.invoke({"context": pdffile})
    summary = summary_pdf_chain.invoke(pdffile)
    evaluation = evaluate_summary(summary)
    audio_file = text_to_speech_stream(summary)
    prompt = topics_prompt
    shape = generate_gif(prompt)
    ai_asistant = animate_image(audio_file)
    return summary, evaluation, ai_asistant, shape

# Define Gradio Interface
iface = gr.Interface(
    fn=process_question,
    inputs=gr.inputs.File(label="Upload PDF File"),
    outputs=[
        gr.outputs.Textbox(label="Summary"),
        gr.outputs.Textbox(label="Evaluation"),
        gr.outputs.Audio(label="AI Assistant"),
        gr.outputs.Image(label="3D Shape")
    ]
)

if __name__ == "__main__":
    iface.launch()