Skip to content
Sangam Gupta
All work

AI & ML RAG Assistant

Ask questions about a PDF and get answers with the page numbers they came from.

Status
Open source
Stack
Python, LangChain, FAISS, sentence-transformers, Streamlit
Links
Code

How it fits together

  1. PDF
  2. LangChain chunks
  3. MiniLM embeddings
  4. FAISS
  5. Top-3 search
  6. Gemini
  7. Answer + page sources

Learning prototype of retrieval-augmented generation: LangChain chunking, MiniLM embeddings in a FAISS index, top-3 retrieval, and Gemini via OpenRouter answering only from the retrieved context.

Ask about AI & ML RAG Assistant

Answers come from this case study and its code on GitHub.