rryam/LumoKit
Swift package for on-device Retrieval-Augmented Generation (RAG)
Combines PicoDocs for multi-format document parsing (PDFs, Markdown, HTML, text) with VecturaKit for vector indexing and semantic search. Offers content-aware chunking strategies—sentence, paragraph, or semantic—with configurable overlap and specialized handling for prose, code, markdown, and mixed content types. Built on Swift concurrency with a complete async API for on-device knowledge base creation and querying.
111 stars.
Stars
111
Forks
6
Language
Swift
License
MIT
Category
Last pushed
Mar 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/rryam/LumoKit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Kain-90/RAG-Play
An interactive visualization tool for understanding Retrieval-Augmented Generation (RAG) pipelines.
CoIR-team/coir
(ACL 2025 Main) A Comprehensive Benchmark for Code Information Retrieval.
harvard-lil/warc-gpt
WARC + AI - Experimental Retrieval Augmented Generation Pipeline for Web Archive Collections.
Global-Witness/augmenta
AI agent for enhancing datasets with information from the internet
constacts/ragtacts
RAG(Retrieval-Augmented Generation) for Evolving Data