Product Search Agent

A web-based e-commerce product search agent. It allows users to search for products across multiple online platforms using a natural language query. The backend entails a combination of web scraping capabilities (via BrightData MCP) and a LLM (configured for Google Gemini via Langchain) to find and present relevant product information.

Features

• Search for products using natural language queries.
• Select from multiple e-commerce platforms (Amazon, Best Buy, Ebay, Walmart, Target, Costco, Newegg).
• Displays product title, URL, and rating.
• Web interface built with Flask.

Prerequisites

• Python 3.x
• Node.js and npm (which includes npx for running the MCP client)
• Access to Google Gemini API (or another compatible LLM)
• BrightData account and credentials (for web scraping)

Setup and Installation

1. Create a Python virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`
   

2. Install Python dependencies:

   pip install flask python-dotenv pydantic model-context-protocol langchain_mcp_adapters langgraph langchain-google-genai
   

3. Set up Environment Variables: Create a file named .env in the root directory of the project and copy the contents of '.env.example' file, replacing the placeholder values with actual credentials:

   # BrightData Credentials
   API_TOKEN=your_brightdata_api_token_here
   BROWSER_AUTH=your_brightdata_browser_auth_here
   WEB_UNLOCKER_ZONE=your_brightdata_web_unlocker_zone_here
   
   # Google Gemini API Key
   GOOGLE_API_KEY=your_google_api_key_here
   

How to Run

1. Ensure all prerequisites are met and environment variables are set.
2. Open your terminal in the project's root directory.
3. Run the Flask application:

   python app.py
   

4. Open your web browser and navigate to http://localhost:8000 (or http://0.0.0.0:8000).