vector similarity search
pgvector is a PostgreSQL extension for storing and performing exact and approximate nearest-neighbor search on vectors, supporting multiple distance metrics and quantization.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose for a standalone horizontally scalable vector database with object storage, avoiding Postgres.
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
choose for a ~2KB in-browser/edge vector search library with no server.
🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.
choose for full-text and vector search in one Postgres extension, but its API differs from pgvector.
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.
choose for large-scale AI search with ML serving and distributed deployment.
The AI search platform
choose for high-performance hybrid search on dense/sparse/tensor vectors in a purpose-built database.
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
choose for an AI-native database unifying vector/text/structured data, but it's a new engine.
The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.
choose when you already use Redis and want vector search via modules, but not SQL.
For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.
choose for an easy-to-deploy search API with typo-tolerant full-text and vector search.
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
choose for a dedicated high-throughput vector database with rich filtering and clustering.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
choose for a lightweight in-process vector database with low overhead.
A lightweight, lightning-fast, in-process vector database
choose for an embedded multimodal retrieval library over your existing data.
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
choose for a graph-vector database on object storage, but it's new and non-Postgres.
HelixDB is an OLTP graph-vector database built in Rust on Object Storage.
choose for typo-tolerant full-text and vector search in a single fast search server.
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
choose for SQL-capable full-text and vector search in a dedicated search database.
Open-source search database for full-text, vector, and hybrid search with real-time indexing and SQL.
choose for an in-process Rust vector search library or multi-tenant server.
SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.
choose for a standalone vector database management system, but with GPL license and less adoption.
Epsilla is a high performance Vector Database Management System
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
previous-generation Postgres vector extension with no recent maintenance; choose only if you need its specific API.
PostgreSQL vector database extension for building AI applications
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
choose when you want a self-hosted enterprise search server with a GUI and crawler; it's an end-user app, not a library.
Open-source, self-hosted enterprise & site search server built on OpenSearch. Crawls web / file / DB / cloud sources, 20+ languages, REST API, and AI/RAG & semantic search. Apache-2.0.
These projects were analysed and named pgvector among their alternatives. The relationship is not symmetric — how pgvector rates them is a separate judgement, made when pgvector is analysed in its own right.
calls pgvector “Choose when you want vector search inside Postgres, avoiding a separate in-memory server.”
For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.
calls pgvector “Choose pgvector when you want to add vector search inside your existing PostgreSQL database without running a separate search service.”
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
calls pgvector “choose when you already live in Postgres and want basic vector search without introducing a new database service.”
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
calls pgvector “Choose when you want vector search inside Postgres without a separate service, leveraging SQL and transactional consistency.”
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
calls pgvector “Choose when you want vector search as a Postgres extension and don't want to operate a separate database service.”
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
calls pgvector “Postgres extension for vector similarity; choose when staying with Postgres and want SQL vector search.”
A lightweight, lightning-fast, in-process vector database
calls pgvector “Postgres extension for vector similarity; choose it to keep vectors alongside relational data in Postgres.”
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
calls pgvector “choose when you want vector search inside Postgres, but it lacks Typesense's full-text and typo-tolerance features”
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
calls pgvector “Choose when you want vector search inside an existing Postgres database; no full-text search or SQL search features beyond vectors.”
Open-source search database for full-text, vector, and hybrid search with real-time indexing and SQL.
calls pgvector “Postgres vector similarity extension; choose when you already use Postgres and only need vector search, not full-text/hybrid from Orama.”
🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.
calls pgvector “Choose it when you want a minimal, widely supported Postgres extension for vector search only, without BM25 full-text or columnar analytics.”
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.
calls pgvector “Choose if you run Postgres and need only vector similarity; lacks full-text ranking/ML inference of Vespa.”
The AI search platform