RAG Agent with ChromaDB and Web Search

This repository contains a lightweight Retrieval‑Augmented Generation (RAG) agent that uses ChromaDB as the vector store and performs a simple web search to augment the retrieved context before generating an answer with OpenAI's GPT model.

Deadline: 31.08.2026
Version: 14

Features

Vector Store – ChromaDB (local, no external service required)
Embeddings – OpenAI text-embedding-ada-002
LLM – OpenAI gpt-3.5-turbo
Web Search – DuckDuckGo (no API key needed)
Command‑line interface for adding documents and asking questions

Prerequisites

Python 3.9+
An OpenAI API key

Installation

# Clone the repository
git clone https://git.brojs.ru/kuzakhmetovartur/ekzamen-rag-agent-s-chromadb-i-veb-poisk.git
cd ekzamen-rag-agent-s-chromadb-i-veb-poisk

# Create a virtual environment (optional but recommended)
python -m venv .venv
source .venv/bin/activate   # On Windows: .venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

requirements.txt contains:

openai>=1.0.0
chromadb>=0.4.0
requests>=2.31.0
beautifulsoup4>=4.12.0

Configuration

Set your OpenAI API key as an environment variable:

export OPENAI_API_KEY="sk-..."

On Windows:

set OPENAI_API_KEY=sk-...

Usage

1. Add Documents

Add a text file to the vector store. The file will be split into chunks (≈500 tokens each) and embedded.

python -m src.index add path/to/document.txt

Example:

python -m src.index add data/biology.txt

2. Ask a Question

Query the RAG agent. It will:

Retrieve the top‑5 nearest chunks from ChromaDB.
Perform a DuckDuckGo web search for the query.
Combine the retrieved context and web snippets.
Generate an answer with GPT.

python -m src.index ask "What is the function of mitochondria?"

3. Help

python -m src.index

Example

$ python -m src.index add sample.txt
Added 4 chunks from sample.txt to the collection.

$ python -m src.index ask "Explain the water cycle."
Answer:
The water cycle, also known as the hydrologic cycle, describes the continuous movement of water on, above, and below the surface of the Earth. ...

Project Structure

src/
├── index.py          # Main script
README.md
requirements.txt

Notes

ChromaDB Persistence – The vector store is persisted in ./chromadb. Delete this folder to reset the store.
Token Limits – The embedding model text-embedding-ada-002 supports up to 8191 tokens per request. The chunking logic approximates a 500‑token limit per chunk.
Web Search – DuckDuckGo is used for simplicity. For production use, consider a dedicated search API (e.g., SerpAPI, Bing Search API).

License

MIT License

2.8 KiB Raw Blame History Unescape Escape