app.py

from flask import Flask, request, jsonify
from flask_cors import CORS
from scraper import WebScraper
from vector_db import VectorDatabase
from chatbot import ChatBot
import os
from dotenv import load_dotenv

load_dotenv()

app = Flask(__name__)
CORS(app)  # Enable CORS for all routes

# Initialize our components
scraper = WebScraper()
vector_db = VectorDatabase()
chatbot = ChatBot()



@app.route('/')
def home():
    return "Hello, this is a Scraper Flask app backend!"

@app.route('/api/scrape', methods=['POST'])
def scrape_url():
    try:
        data = request.json
        url = data.get('url')
        if not url:
            return jsonify({'error': 'URL is required'}), 400

        # Scrape the URL
        result = scraper.scrape_url(url)
        if not result or not result['content']:
            return jsonify({'error': 'Failed to scrape website'}), 400

        # Process and store in vector database
        chunks_count, vector_store_id = vector_db.process_and_store(result)
        
        return jsonify({
            'message': f'Successfully scraped and processed into {chunks_count} chunks', 
            'chunks': chunks_count,
            'url': result['url']
        })
    except Exception as e:
        return jsonify({'error': str(e)}), 500

@app.route('/api/chat', methods=['POST'])
def chat():
    try:
        data = request.json
        message = data.get('message')
        url = data.get('url')  # Optional URL to specify context

        if not message:
            return jsonify({'error': 'Message is required'}), 400

        # Get context from vector database
        context = vector_db.search(message, url)

        # Generate response
        response = chatbot.generate_response(message, context, url)
        
        return jsonify({'response': response})
    except Exception as e:
        return jsonify({'error': str(e)}), 500

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=7860)