Embeded Vector Database for low performance devices
NOTH5 Platform V80 FINAL - Independent compilable language .noth5->Python->25.91 MB EXE + EEHIM DB Ultra WAL 75781 RPS Burst 150K Ultra Compressor 8.4:1 + 105 real controls inside bubble - For ALL Chatbot/RAG/Agentic AI - Not factory only - Author Nagendra Prasad [email protected]
离线 RAG + 编译式 LLM-wiki 知识库模板：raw 原文一次性编译成互链 Markdown 图谱，bge-m3 本机多语言嵌入、中文优先开箱即用；git 多人/多 agent 共建用确定性对账(R1 再生 + merge 驱动)取代人肉 merge。零 keyed LLM，接 Claude Code / DeepSeek / 任意自带 LLM 的 agent。| An offline-RAG + Karpathy-LLM-wiki kit: compiled bilingual-first Markdown wiki, local bge-m3 retrieval, deterministic git-team reconciliation.
PetCare+ is a 100% offline, evidence-grounded RAG desktop app for pet-care guidance across 70 species, running entirely on Windows with zero API costs. It combines BGE-small embeddings, FAISS + BM25 hybrid retrieval, and a local Qwen2.5 LLM to deliver cited answers with safety alerts — all data stays on your machine.
Offline-first Local RAG assistant built during the 4-week Microsoft Turkey AI Project Internship mentored by CSA Manager Barbaros Günay. Powered by Microsoft Foundry SDK & SQLite vector search.
Self-hostable grounded ask and multi-turn diagnose over manufacturer service manuals — citations, model/serial applicability, safety gates, optional LLM semantic curation with human PDF review, Langfuse. LAN-only; proven on Whirlpool WFW5620H.
To associate your repository with the offline-rag topic, visit your repo's landing page and select "manage topics."