RAG Agent with ChromaDB and Web Search

This project implements a Retrieval-Augmented Generation (RAG) agent that uses ChromaDB as the vector database and the OpenAI API to generate responses based on retrieved documents. It also includes a simple web‑search component that fetches content from specified URLs for indexing.

Features

Vector Store: Uses ChromaDB to store embeddings of text chunks.
OpenAI Integration: Generates answers using GPT‑3.5‑Turbo.
Web Search: Fetches and parses HTML pages, splits them into manageable chunks.
Command Line Interface: Ask questions interactively.

Prerequisites

Node.js v18+ (supports native ES modules and node-fetch v2).
An OpenAI API key.

Setup

Clone the repository (or copy the files into a directory).
Install dependencies
```
npm install
```
Configure environment

Create a .env file in the project root (or edit the existing one) and add your OpenAI API key:
```
OPENAI_API_KEY=your_api_key_here
```
Run the agent
```
npm start
```
The script will:
- Fetch and index the example URLs.
- Prompt you to enter questions.
- Display answers generated by the RAG agent.

Customization

Adding URLs: Edit the urls array in src/index.js to index different web pages.
Chunk Size: Adjust the size parameter in chunkText inside src/webSearch.js if you need larger or smaller chunks.
Model Parameters: Modify temperature, max tokens, or model name in src/agent.js.

Notes

The implementation strictly uses ChromaDB as the vector database; no other vector DBs are used.
All dependencies are declared in package.json and can be installed via npm install.
The OpenAI API key is loaded securely from the .env file using dotenv.

License

MIT License

Enjoy building with RAG!

1.9 KiB Raw Blame History Unescape Escape