app.py

from flask import Flask, request, jsonify, send_from_directory
import requests
import os
from dotenv import load_dotenv

load_dotenv()

app = Flask(__name__)

API_URL = "/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fmodels%2F%26quot%3B%3C%2Fspan%3E%3C!-- HTML_TAG_END -->
headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_KEY')}"}

# Sample text for testing
sample_text = """
This is a sample text for testing our RAG chatbot. 
It contains information about artificial intelligence and machine learning.
AI and ML are revolutionizing various industries and improving efficiency.
"""

def query(payload, model):
    response = requests.post(API_URL + model, headers=headers, json=payload)
    return response.json()

@app.route('/')
def home():
    return send_from_directory('.', 'index.html')

@app.route('/ask', methods=['POST'])
def ask():
    prompt = request.json['question']
    
    # Use sentence-transformers model for embedding
    embedding_model = "sentence-transformers/all-MiniLM-L6-v2"
    context_embedding = query({"inputs": sample_text}, embedding_model)[0]
    query_embedding = query({"inputs": prompt}, embedding_model)[0]
    
    # Simple dot product similarity
    similarity = sum(a*b for a, b in zip(context_embedding, query_embedding))
    
    # Generate response using T5 model
    generator_model = "google/flan-t5-small"
    input_text = f"Context: {sample_text}\n\nQuestion: {prompt}\n\nAnswer:"
    response = query({"inputs": input_text}, generator_model)[0]["generated_text"]

    return jsonify({'response': response})

if __name__ == '__main__':
    app.run(debug=True)