RAG with MongoDB Atlas Vector Search and Groq Embeddings API

This script demonstrates how to implement a Retrieval-Augmented Generation (RAG) system using MongoDB Atlas Vector Search for document retrieval and the Groq Embeddings API for generating vector representations of text. The workflow includes loading a PDF document, splitting it into chunks, generating embeddings, storing them in MongoDB, and then querying the database to retrieve relevant documents based on a user query.

Key Focus Areas

• Using MongoDB Atlas Vector Search
• Creating Vector indexes for the query retrieval
• Groq LLM & Embeddings API

Run My Project Locally

Here's how I run it on my machine:

git clone https://github.com/nehasinghaniya21/rag-mongodb.git
cd rag-mongodb
uv init
uv venv
source .venv/bin/activate
uv add -r requirements.txt
python rag-mongodb.py