app.py

import gradio as gr
from transformers import pipeline
from flask import Flask, request, jsonify
import os
from huggingface_hub import login

# Retrieve the Hugging Face token from environment variables
HF_TOKEN = os.getenv("HUGGINGFACE_TOKEN")

if HF_TOKEN is None:
    raise ValueError("Hugging Face token is not set in environment variables")

# Authenticate with Hugging Face
try:
    login(token=HF_TOKEN, add_to_git_credential=True)
except ValueError as e:
    print(f"Error during login: {e}")
    raise

# Load your model and tokenizer
model_id = "rish13/llm_for_advanced_materials"  # Replace with your model repo ID
model = pipeline('text-generation', model=model_id)

# Define Gradio interface
def generate_text(prompt):
    return model(prompt)[0]['generated_text']

gradio_interface = gr.Interface(fn=generate_text, inputs="text", outputs="text")

# Initialize Flask app
app = Flask(__name__)

@app.route('/search', methods=['POST'])
def predict_endpoint():
    data = request.json
    prompt = data.get('prompt', '')
    generated_text = generate_text(prompt)
    return jsonify({"result": generated_text})

@app.route('/')
def home():
    return "Welcome to the text generation API. Use the /search endpoint to generate text."

if __name__ == "__main__":
    # Run the Gradio interface in a separate thread
    from threading import Thread
    gradio_thread = Thread(target=lambda: gradio_interface.launch(share=False, inbrowser=True))
    gradio_thread.start()
    
    # Run the Flask app
    app.run(host='0.0.0.0', port=5000)