leoneversberg/llm-chatbot-rag

A local LLM chatbot with RAG for PDF input files

45
/ 100
Emerging

Leverages Hugging Face models with optional bitsandbytes GPU quantization for inference optimization, and provides a Streamlit-based UI for interactive chat sessions. Supports multiple LLM architectures (including Gemma) via configurable model loading, with RAG implementation that processes PDF documents into searchable context for prompt augmentation. Designed for local deployment with flexible hardware requirements—quantization targets NVIDIA GPUs, but falls back to CPU inference with adjusted configuration.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

87

Forks

30

Language

Jupyter Notebook

License

MIT

Last pushed

Apr 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/leoneversberg/llm-chatbot-rag"

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