amscotti/local-LLM-with-RAG

Running local Language Language Models (LLM) to perform Retrieval-Augmented Generation (RAG)

47
/ 100
Emerging

Implements agentic RAG using Pydantic AI for tool calling, enabling models to autonomously decide when and how to search documents rather than following fixed pipelines. Embeddings are generated locally via Ollama's nomic-embed-text and indexed in LanceDB for vector search, with document parsing handled by MarkItDown to support PDFs, Office files, and multiple formats. Requires tool-calling-capable models (qwen3:8b+ recommended) and provides a Streamlit interface for interactive document querying.

271 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 22 / 25

How are scores calculated?

Stars

271

Forks

52

Language

Python

License

MIT

Last pushed

Jan 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/amscotti/local-LLM-with-RAG"

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