Embeddable, in-memory, document-oriented database with a high-level Query builder interface.
VectorRAG.Net is a .NET-native high-performance vector database library for semantic search and RAG (Retrieval-Augmented Generation). Core search is based on Random Hyperplane LSH candidate generation with exact rerank by dot/cosine.
Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement
Embeded Vector Database for low performance devices
Code and results for "Revisiting RaBitQ and TurboQuant: a symmetric comparison of methods, theory, and experiments".
An embeddable vector database in Rust — no server, SQLite-style. HNSW + BM25 + hybrid + filtered search, in-process.
GenPark AI Agent Skill - Hierarchical Navigable Small World (HNSW) multi-layer vector index, greedy beam routing, and nearest neighbor search.
GenPark AI Agent Skill - Hierarchical Navigable Small World (HNSW) multi-layer vector index, greedy beam routing, and nearest neighbor search.
Random hyperplane Locality-Sensitive Hashing (LSH) for sub-linear cosine similarity candidate generation
Random hyperplane Locality-Sensitive Hashing (LSH) for sub-linear cosine similarity candidate generation
Inverted File Index with Flat Quantization (IVF-Flat) vector engine performing clustered Voronoi cell partitioning and fast top-K Euclidean ranking.
Inverted File Index with Flat Quantization (IVF-Flat) vector engine performing clustered Voronoi cell partitioning and fast top-K Euclidean ranking.
Inverted File (IVF) index routing vectors to Voronoi cell centroids for pruned sub-linear retrieval
Inverted File (IVF) index routing vectors to Voronoi cell centroids for pruned sub-linear retrieval
A (not very) frequently updated list of ANN vector search papers on declarative recall through early termination, published in top data management venues.
A production-grade vector database built from scratch in Rust — Flat, IVF, HNSW & PQ indexes, self-hostable via Docker, benchmarked against FAISS.
A basic RAG pipeline which uses gpt-oss-20b model to answer the user query with the external knowledge stored in a vector database.
Production-ready multimodal retrieval system built with OpenCLIP, Qdrant, FastAPI and Streamlit. Includes full evaluation pipeline (Recall@K, mAP, nDCG) and Docker-based deployment.
Customer review triage: semantic search in pgvector, and three ways to guess which reviews are urgent
Build-time, multi-agent RAG pipeline that turns raw course materials into structured topic pages, prerequisite graphs, and QA reports
To associate your repository with the ann-search topic, visit your repo's landing page and select "manage topics."