TurboQuant-compatible vector search plus graph memory for constrained RAG.
-
Updated
Jun 13, 2026 - Rust
TurboQuant-compatible vector search plus graph memory for constrained RAG.
Movie recommendation engine featuring a 6-model hybrid ensemble (SBERT semantic, turbovec vector search, Collaborative Filtering, PageRank, Content, Knowledge Graph) with FastAPI & React Vite. Powered by PySpark MLOps.
A hyper-optimized, local RAG system built on Streamlit using Google's TurboQuant algorithm and Turbovec vector index for 4 GB RAM setups.
Local-first RAG pipeline using TurboVec for vector search and LangGraph for orchestration, with Gemini API for response generation
Offline Q&A over Wikipedia ZIM files – full‑text + semantic search using TurboRag. Zero internet required after setup. Run on low‑CPU, low‑RAM devices. using llama.cpp
Offline, CPU, RAM RAG engine with quantized vectors (TurboVec), GGUF embedding/LLM models, REST API, MCP server, and multi‑language SDKs.
Lightweight, fast, secure, and free document chat system powered by Qwen AI and TurboVec search.
Offline CRUD + semantic search agent for ZIM archives (Kiwix format). Read, write, edit, delete articles, build vector indexes, and serve via MCP – all offline, low‑resource.
Run offline RAG engines on CPU and RAM using quantized vector indexing, LLM quantization tools, and multi-language support.
Add a description, image, and links to the turbovec topic page so that developers can more easily learn about it.
To associate your repository with the turbovec topic, visit your repo's landing page and select "manage topics."