How jaskeeratk/rag_chromadb_groq_streamlit works
Project type and purpose
• From the file tree and the README title “RAG_chromaDB_Groq_streamlit,” we see this is a small full-stack RAG (Retrieval-Augmented Generation) application built in Python, with a Streamlit front end, a retrieval & generation core, and a vector database (ChromaDB). Its purpose is to let users query a knowledge base via a UI, retrieve relevant documents, and generate answers using a Groq‐accelerated model.
File structure
• Top-level files:
• app.py – Streamlit UI entry point
• rag_core.py – Core retrieval + generation logic
• preprocessing.py – Data ingestion/vectorization pipeline
• requirements.txt – Python dependencies (e.g., streamlit, chromadb, groq)
• .devcontainer/… – Dev container config for reproducible environment
• There are no separate “frontend” and “backend” folders; instead, the backend (rag_core + preprocessing) and frontend (Streamlit) coexist in the same repo.
README for additional insights
• README only gives the project name, but the file names make clear the architecture: preprocessing → vector store (ChromaDB) → retrieval + generation → Streamlit UI.