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.
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.
High-performance distributed vector database & embedding search engine in Rust, Python, TypeScript, and Go with SIMD HNSW indexing.
Customer review triage: semantic search in pgvector, and three ways to guess which reviews are urgent
Production-ready multimodal retrieval system built with OpenCLIP, Qdrant, FastAPI and Streamlit. Includes full evaluation pipeline (Recall@K, mAP, nDCG) and Docker-based deployment.
An advanced implementation of billion-scale Approximate Nearest Neighbor (ANN) search. Features include a modular multi-quantizer pipeline (PQ/OPQ/AVQ), shared-memory safe Cuckoo filtering, and speculative 2-Hop CPU prefetching for zero-latency graph traversal
Build-time, multi-agent RAG pipeline that turns raw course materials into structured topic pages, prerequisite graphs, and QA reports
HNSW (Hierarchical Navigable Small World) vector index built from scratch in Python/NumPy: no FAISS, no hnswlib. recall@10 = 1.000, 20x speedup over brute force at n=8000.
C++ vector database with HNSW, KD-Tree, REST APIs, and local LLM-powered RAG using Ollama.
A framework for the implementation of candidate generation/retrieval algorithms for recommender systems.
Lightweight approximate nearest neighbor (ANN) vector search engine and embedding indexing pipeline.
App Store Search example using ReactiveSearch pipelines and aNN
To associate your repository with the ann-search topic, visit your repo's landing page and select "manage topics."