Awesome Vector Search Engine

• Cloud Service

  • Zilliz Cloud - Cloud-native service for Milvus
  • Relevance AI - Vector Platform From Experimentation To Deployment
  • DataStax Astra Vector - Multi-cloud, serverless vector DBaaS
  • MyScale - A managed vector database based on ClickHouse
  • MongoDB Atlas Vector Search - Multi-cloud vector search with filtering, horizontal scaling, etc.
  • Epsilla Cloud - The fully managed serverless vector database with 10X faster, cheaper and better.
  • Pinecone - Managed vector search with filtering, live index updates, horizontal scaling, and a lot more
  • Redis Cloud - Managed vector database in Redis
  • SemaDB Cloud - Easy-to-use managed vector database with a RESTful API
  • Rivestack - Managed PostgreSQL with pgvector for AI workloads. Built-in SQL editor lets you query your database with natural language (automatically converted to vector embeddings). Free tier includes 2GB storage.

• Library

  • ScaNN - A library efficient vector similarity search at scale.
  • JVector - A pure Java, zero dependency, embedded vector search engine used by some of the advanced distributed databases such as DataStax Astra DB & Apache Cassandra™
  • Faiss - A library for efficient similarity search and clustering of dense vectors
  • Distributed Faiss - Work with FAISS indexes which don't fit into a single server memory
  • Autofaiss - Automatically create Faiss knn indices
  • NMSLIB - Non-Metric Space Library, an efficient similarity search library for generic non-metric spaces
  • Annoy - C++ library with Python bindings to search for points
  • LLM App - Open-source Python library for a real-time data KNN (K-Nearest Neighbors) indexing
  • RPForest - Python library for approximate nearest neighbours search
  • pgvector - Open-source vector similarity search extension for Postgres
  • PASE - Ultra-High-Dimensional approximate nearest neighbor search extension for Postgres
  • Pyserini - Toolkit for reproducible information retrieval research with sparse and dense representations
  • NGT - Provides commands and a library for performing high-speed approximate nearest neighbor
  • TOROS N2 - lightweight approximate Nearest Neighbor library
  • PUFFINN - Parameterless and Universal Fast FInding of Nearest Neighbors
  • SPTAG - A distributed approximate nearest neighborhood search (ANN) library
  • PyNNDescent - A python nearest neighbor descent for approximate k nearest neighbors
  • TarsosLSH - A Java library implementing practical nearest neighbour search algorithm for multidimensional vectors
  • TorchPQ - Efficient implementations of Product Quantization and its variants using Pytorch and CUDA
  • Granne - Graph-based retrieval of approximate nearest neighbors witten in rust
  • Hora - Efficient approximate nearest neighbor search algorithm collections library written in Rust
  • Voy - A WASM vector similarity search engine written in Rust
  • Chroma - The open-source embedding database for building LLM apps in Python or JavaScript with memory
  • USearch - Smaller & Faster Vector Search Engine for C++, Python, JavaScript, Rust, Java, GoLang, Wolfram
  • Golang vector stores collection - Chroma, PGVector interfaces
  • CassIO - CassIO is the ultimate solution for seamlessly integrating Apache Cassandra® with generative artificial intelligence and other machine learning workloads
  • LangStream - LangStream is an open-source project that combines the best of event-based architectures with the latest Gen AI technologies.
  • NearPy - Approximate search using different locality-sensitive hashing methods
  • SimSIMD - Hardware-accelerated mixed-precision numerics library for dense and sparse vector math and search
  • altor-vec - In-browser HNSW vector search in JavaScript. 54KB WASM, sub-millisecond queries, no server required. npm install altor-vec
  • chromem-go - Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence.
  • CocoIndex - An open-source ETL framework with realtime incremental processing to keep index fresh
  • Moss - Sub-10ms semantic search engine for Voice & Conversational AI, built in Rust/WebAssembly for on-device / in-browser retrieval
  • MRPT - Fast nearest neighbor search with random projection
  • Scalable Vector Search (SVS) - A performance library for vector similarity search

• Research Papers

  • SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search - NEURIPS 2021
  • Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors - ECCV 2018
  • Accelerating Large-Scale Inference with Anisotropic Vector Quantization
  • Billion-scale similarity search with GPUs
  • Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs
  • Optimization of Indexing Based on k-Nearest Neighbor Graph for Proximity Search in High-dimensional Data
  • On Approximately Searching for Similar Word Embeddings - ACL 2016
  • ![CC0

• Standalone Service

  • TensorDB - High Performance Vector Database Supporting Heterogeneous Computing
  • Vespa.ai - Text search engine and ... fast approximate vector search (ANN)
  • Vespa's large-scale ANN search using HNSW-IF indexes is described here
  • Qdrant - Vector Similarity Search Engine with extended filtering support
  • Vald - A Highly Scalable Distributed Vector Search Engine
  • Milvus - A cloud-native vector database with high-performance and high scalability.
  • OpenDistro Elasticsearch KNN - A machine learning plugin which supports an approximate k-NN search algorithm for Open Distro for Elasticsearch
  • Elastiknn - Elasticsearch plugin for nearest neighbor search
  • Epsilla - A High Performance Vector Database Management System, Hippocampus For AI
  • Vearch - A scalable distributed system for efficient similarity search of deep learning vectors
  • pgANN - Fast Approximate Nearest Neighbor (ANN) searches with a PostgreSQL database
  • Infinity - The AI-native database built for LLM applications, providing incredibly fast vector and full-text search
  • Redis HNSW - A redis module for similarity search based on HNSW
  • Solr - Apache Solr - [has a Dense Vector Search feature as of Solr 9.0](https://solr.apache.org/guide/solr/latest/query-guide/dense-vector-search.html)
  • Marqo - A semantic search engine which supports tensor search (sequence of vectors)
  • txtai - Build semantic search applications and workflows
  • Semantra - A multipurpose tool for semantically searching documents.
  • VQLite - Simple and Lightweight Vector Search Engine
  • Vexvault - 100% browser based, open source, scalable, simple, zero-cost vector search
  • Weaviate - A cloud-native, real-time vector search engine
  • Aquila DB - Distribution focused k-NN search algorithm
  • Jina - Jina allows you to build deep learning-powered search-as-a-service.
  • Omnigraph - Typed graph database where agents branch and merge like Git. S3-native, Rust, traversal + vector + BM25 in one runtime
  • JVector - a pure Java, zero dependency, embedded vector search engine, used by DataStax Astra DB and Apache Cassandra.