olioDuan/Domain-Specific-RAG-Chat-Course-Helper

This project is a Local RAG system built for the NYU Machine Learning course.

40
/ 100
Emerging

Computes embeddings using HuggingFace's `all-MiniLM-L6-v2` model and stores them in FAISS for efficient retrieval; generates answers with DeepSeek R1 via Ollama, providing slide-level citations and automatically generated quiz questions. The system uses a one-slide-one-chunk chunking strategy to maintain precise source attribution while preserving slide content integrity. Includes a Gradio web interface with chat, PCA visualization, and retrieval evaluation tabs for comprehensive course material interaction.

No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 13 / 25
Community 12 / 25

How are scores calculated?

Stars

82

Forks

9

Language

Python

License

Apache-2.0

Last pushed

Dec 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/olioDuan/Domain-Specific-RAG-Chat-Course-Helper"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.