💬 Chat with Websites (OpenAI Version)

An end-to-end Retrieval-Augmented Generation (RAG) application that allows users to have interactive conversations with any website. By providing a URL, the application scrapes the content, indexes it, and allows for context-aware Q&A using OpenAI's powerful language models.

🚀 Features

• URL-Based Chat: Enter any website URL to instantly start a conversation with its content.
• Contextual Memory: Maintains chat history to provide accurate responses based on the full conversation flow.
• RAG Pipeline: Utilizes LangChain for document loading, text splitting, and retrieval.
• Vector Search: Uses Chroma DB and OpenAI Embeddings for high-performance semantic search.

🛠️ Tech Stack

• Frontend: Streamlit
• LLM: OpenAI GPT-4o-mini
• Embeddings: OpenAI text-embedding-3-small
• Orchestration: LangChain
• Database: Chroma DB (Vector Store)

📋 Prerequisites

• Python 3.9+
• OpenAI API Key

⚙️ Setup

1. Clone the repository:

   git clone https://github.com/Anuroop128/chat-with-websites.git
   cd chat-with-websites

2. Install dependencies:

   pip install -r requirements.txt

3. Create a .env file and add your OpenAI API Key:

   OPENAI_API_KEY=your_openai_api_key_here

4. Run the app:

   streamlit run src/app.py