Repo

RAG

@mominaali1by Momina Ali · Independent

0

A simple RAG pipeline that It extracts text from a PDF, chunks it into 200-word segments, embeds them using all-MiniLM-L6-v2, stores them in a ChromaDB vector database, and retrieves the most semantically similar chunks to feed as context to Groq's LLaMA 3.

Built withPython

See what other members are building and what each project is looking for.