Local-first RAG pipeline using TurboVec for vector search and LangGraph for orchestration, with Gemini API for response generation
10BC0-
Updated
May 21, 2026 - Python
#
turbovec
Here are 14 public repositories matching this topic...
Offline, CPU, RAM RAG engine with quantized vectors (TurboVec), GGUF embedding/LLM models, REST API, MCP server, and multi‑language SDKs.
nodejs python rust sdk neon embeddings simd quant nearest-neighbors quantization avx512 faiss vector-search faiss-vector-database turboquant turbovec
-
Updated
Jun 7, 2026 - Python
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.
sqlite3 crud-application embedding-models kiwix agents semantic-search rag zim-archives kiwix-offline-wikipedia zimlib mcp-tools wikipedia-offline fts5-search turbovec ahx47 kiwiks zim-agent turborag gemma-embedding-300m
-
Updated
Jun 7, 2026 - Python
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-first wikipedia embeddings kiwix gemma rag zim-archives zim-wiki offline-agent wikipedia-offline turboquant turbovec ahx47 turborag gemma-embedding-300m wekipedia-agent kiwix-zim zim-rag vectors-search
-
Updated
Jun 7, 2026 - Python
A hyper-optimized, local RAG system built on Streamlit using Google's TurboQuant algorithm and Turbovec vector index for 4 GB RAM setups.
-
Updated
Jun 10, 2026 - Python
Lightweight, fast, secure, and free document chat system powered by Qwen AI and TurboVec search.
question-answering rag vector-search vector-database langchain local-llm document-qa open-source-llm rag-pipeline qwen3 qwen3-embeddings turboquant turbo-quant turbovec
-
Updated
Jun 12, 2026 - Python
Spectra is a document search console for teams that need to turn messy files into searchable knowledge.
-
Updated
Jun 12, 2026 - JavaScript
TurboQuant-compatible vector search plus graph memory for constrained RAG.
-
Updated
Jun 19, 2026 - Rust
Amadeus-AI is python framework for autonomous AI agents with planning, execution graphs, and plugins.
python workflow-engine clean-architecture multi-agent plugin-system autonomous-agents ai-agents fastapi local-first secure-ai graph-execution local-ai memory-system llm-runtime secure-ai-agents turbovec
-
Updated
Jul 1, 2026 - Python
Does TurboVec quantization hold up on exact-fact retrieval, or only on semantic similarity? Tests recall@k across bit_width 4/2 vs full precision on a synthetic report with 104 ground-truth facts. Finding: templated near-duplicate chunks (not "numbers" generally) are where compression breaks retrieval.
python benchmark offline-first embeddings semantic-search vector-quantization rag vector-database sentence-transformers llm retrieval-augmented-generation turbovec
-
Updated
Jul 29, 2026 - Python
World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated
swift rust privacy embeddings db gpu-acceleration image-search ann clip semantic-search onnx multimodal rag ivf local-first vector-database hybrid-search turbovec
-
Updated
Aug 13, 2026 - Python
ANN cache with a shrink-guard save so a dual-write cannot wipe RAG while SQL still has rows.
-
Updated
Aug 19, 2026 - Python
Run offline RAG engines on CPU and RAM using quantized vector indexing, LLM quantization tools, and multi-language support.
python embeddings archive simd avx512 gemma zim-archives vector-search kiwix-offline-wikipedia turboquant turbovec ahx47 turborag gemma-embedding-300m kiwix-zim zim-rag local-gguf
-
Updated
Aug 24, 2026 - Python
Improve this page
Add a description, image, and links to the turbovec topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the turbovec topic, visit your repo's landing page and select "manage topics."