RAG-based AI Assistant Documentation

Figure 1: Retrieval-Augmented Generation Architecture

Project Overview

A Python implementation of a Retrieval-Augmented Generation (RAG) assistant that:

• Retrieves information from Wikipedia
• Processes documents using chunking and embeddings
• Generates answers using LLMs

Key Features:
✔ Vector database (ChromaDB)
✔ Wikipedia document ingestion
✔ Customizable retrieval pipeline
✔ Local (Ollama) or Cloud (OpenAI) LLM support

Installation

# Clone repository
git clone https://github.com/yourusername/rag-assistant.git
cd rag-assistant

# Install dependencies
pip install -r requirements.txt

# For local LLM (optional)
ollama pull llama2