This project implements a Retrieval-Augmented Generation (RAG) system designed for Yelp Reviews Analysis.
The pipeline retrieves the most relevant Yelp review segments from a MongoDB Atlas vector store—powered by embeddings—and uses a Gemini model to generate rich, context-aware responses.
The application is deployed through a Streamlit dashboard (`app.py`), allowing users to query businesses, categories, themes, and sentiment patterns within the Yelp dataset.