Vector databases

A vector database stores embeddings, the numeric vectors that represent text, images, or other data, and returns the entries closest to a query vector using approximate nearest neighbor indexes. In retrieval-augmented generation, the vector database supplies the passages a model reads before it answers.

The options fall into four groups: purpose-built engines such as Pinecone, Weaviate, Qdrant, Milvus, and Chroma; embedded libraries such as LanceDB, Faiss, and sqlite-vec that run inside an application process; extensions to existing systems, such as pgvector for PostgreSQL, Redis, MongoDB, and Elasticsearch; and cloud services such as Amazon S3 Vectors, Azure AI Search, and Google Cloud Vector Search.

Most now combine vector similarity with keyword or sparse search and metadata filtering, because hybrid retrieval finds exact terms, such as product codes, that pure embedding search can miss. The right choice depends on where the data already lives, the expected corpus size, and how much infrastructure the team wants to run.

Vector databases compared

PlatformOpen sourceDeploymentBest for
Amazon S3 VectorsNoManaged cloud, APILarge, infrequently queried vector sets on AWS
Astra DBNoManaged cloud, Self-hostedVector search on Cassandra-based infrastructure
Azure AI SearchNoManaged cloud, APIRetrieval for Azure and Microsoft Foundry applications
ChromaYes (Apache-2.0)Library, Self-hosted, Managed cloudPrototyping retrieval locally, then moving to a hosted service
Cloudflare VectorizeNoManaged cloud, APIRetrieval inside Cloudflare Workers applications
ElasticsearchYes (AGPL-3.0-only OR SSPL-1.0 OR Elastic-2.0)Self-hosted, Managed cloudAdding vector search to existing Elasticsearch deployments
FaissYes (MIT)LibraryBuilding custom vector indexes in-process
InfinityYes (Apache-2.0)Self-hosted, LibraryHybrid retrieval with tensor and full-text ranking
LanceDBYes (Apache-2.0)Library, Managed cloudEmbedded and multimodal retrieval on object storage
MeilisearchYes (MIT AND BUSL-1.1)Self-hosted, Managed cloudDeveloper-friendly hybrid search for apps and sites
MilvusYes (Apache-2.0)Library, Self-hosted, Managed cloudLarge deployments that need horizontal scaling
MongoDB Vector SearchNoManaged cloud, Self-hostedVector search inside an existing MongoDB deployment
OpenSearchYes (Apache-2.0)Self-hosted, Managed cloudApache-licensed search with vector and keyword retrieval
pgvectorYes (PostgreSQL)Self-hosted, Managed cloudTeams already running PostgreSQL
pgvectorscaleYes (PostgreSQL)Self-hostedScaling pgvector workloads beyond memory
PineconeNoManaged cloud, APIManaged vector search without running infrastructure
QdrantYes (Apache-2.0)Self-hosted, Managed cloudFiltered vector search with detailed performance tuning
RedisYes (AGPL-3.0-only OR SSPL-1.0 OR RSALv2)Self-hosted, Managed cloudLow-latency vector search alongside caching
SingleStoreNoManaged cloud, Self-hostedVector search combined with real-time SQL analytics
sqlite-vecYes (MIT OR Apache-2.0)Library, LocalLocal and on-device vector search with SQLite
Supabase VectorYes (Apache-2.0)Managed cloud, Self-hostedApps already built on Supabase Postgres
turbopufferNoManaged cloud, APILarge multi-tenant indexes on object storage
TypesenseYes (GPL-3.0)Self-hosted, Managed cloudSite and app search with added vector retrieval
Upstash VectorNoManaged cloud, APIServerless and edge apps that need a hosted index
ValdYes (Apache-2.0)Self-hostedKubernetes-native vector search at scale
Vector Search (Gemini Enterprise Agent Platform)NoManaged cloud, APITeams building retrieval on Google Cloud
VectorChordYes (AGPL-3.0-only OR Elastic-2.0)Self-hostedLarge vector indexes inside PostgreSQL
VespaYes (Apache-2.0)Self-hosted, Managed cloudLarge-scale search with custom ranking logic
WeaviateYes (BSD-3-Clause (enterprise code under the Weaviate License))Self-hosted, Managed cloudHybrid search with built-in embedding integrations

Profiles

  • Amazon S3 Vectors logo

    Amazon S3 Vectors

    Amazon Web Services · aws.amazon.com

    Amazon S3 Vectors adds vector buckets and vector indexes to Amazon S3 for storing and querying embeddings without provisioning servers, and works as a vector store for Amazon Bedrock Knowledge Bases and alongside Amazon OpenSearch Service.

    • Managed cloud
    • API
  • Astra DB logo

    Astra DB

    IBM (DataStax) · ibm.com

    Astra DB is a serverless database built on Apache Cassandra that supports vector search alongside NoSQL data, offered by IBM with the Hyper-Converged Database for self-managed deployments and Langflow for building RAG applications.

    IBM completed its acquisition of DataStax in May 2025, and Astra DB now sits within IBM's watsonx data portfolio.

    • Managed cloud
    • Self-hosted
  • Chroma logo

    Chroma

    trychroma.com

    Chroma is open-source search infrastructure for AI that supports vector, full-text, regex, sparse, and metadata search, runs embedded in an application or on a team's own servers, and offers Chroma Cloud as a managed service.

    • Open source · Apache-2.0
    • Library
    • Self-hosted
    • Managed cloud
    • Rust
    • Python
    • TypeScript
  • Cloudflare Vectorize logo

    Cloudflare Vectorize

    Cloudflare · developers.cloudflare.com

    Vectorize is Cloudflare's globally distributed vector database for applications built on Cloudflare Workers, storing embeddings with metadata filtering and pairing with Workers AI embedding models for retrieval close to users.

    • Managed cloud
    • API
  • Elasticsearch

    Elastic · elastic.co

    Elasticsearch is a distributed search and analytics engine built on Apache Lucene that combines dense and sparse vector search with BM25 keyword search for hybrid retrieval, and runs self-managed or on Elastic Cloud with hosted Jina embedding models.

    • Open source · AGPL-3.0-only OR SSPL-1.0 OR Elastic-2.0
    • Self-hosted
    • Managed cloud
    • Java
  • Faiss logo

    Faiss

    Meta · faiss.ai

    Faiss is an open-source library from Meta for similarity search and clustering of dense vectors, with CPU and GPU implementations of flat, IVF, HNSW, and product quantization indexes, and it serves as the index engine inside several vector databases.

    • Open source · MIT
    • Library
    • C++
    • Python
  • Infinity logo

    Infinity

    InfiniFlow · infiniflow.org

    Infinity is an open-source database from InfiniFlow, the team behind RAGFlow, that combines dense vector, sparse vector, tensor, and full-text search with fused ranking such as reciprocal rank fusion for RAG workloads.

    • Open source · Apache-2.0
    • Self-hosted
    • Library
    • C++
    • Python
  • LanceDB logo

    LanceDB

    lancedb.com

    LanceDB is an open-source embedded retrieval library built on the Lance columnar format that stores vectors, metadata, and multimodal data on local disk or object storage, with a managed multimodal lakehouse for distributed production search.

    • Open source · Apache-2.0
    • Library
    • Managed cloud
    • Rust
    • Python
    • TypeScript
  • Meilisearch

    meilisearch.com

    Meilisearch is a search engine written in Rust that merges full-text and vector results in hybrid search through configurable embedders, with an MIT-licensed community edition, a BUSL-licensed enterprise edition, and Meilisearch Cloud.

    • Open source · MIT AND BUSL-1.1
    • Self-hosted
    • Managed cloud
    • Rust
  • Milvus

    Zilliz · milvus.io

    Milvus is an open-source vector database that runs as Milvus Lite inside a Python process, as a standalone server, or as a distributed cluster for billions of vectors, with Zilliz Cloud from the same team as its fully managed service.

    • Open source · Apache-2.0
    • Library
    • Self-hosted
    • Managed cloud
    • Go
    • C++
    • Python
  • OpenSearch

    opensearch.org

    OpenSearch is an Apache-2.0 search and analytics suite run as a Linux Foundation project, with a k-NN plugin for approximate vector search, neural and hybrid search features, and a managed version in Amazon OpenSearch Service.

    • Open source · Apache-2.0
    • Self-hosted
    • Managed cloud
    • Java
  • pgvector logo

    pgvector

    github.com

    pgvector is an open-source PostgreSQL extension that adds a vector type with exact and approximate nearest neighbor search through HNSW and IVFFlat indexes, and major managed PostgreSQL services support it, so embeddings live beside application data.

    • Open source · PostgreSQL
    • Self-hosted
    • Managed cloud
    • C
  • pgvectorscale logo

    pgvectorscale

    Tiger Data (formerly Timescale) · github.com

    pgvectorscale is an open-source PostgreSQL extension from Tiger Data that complements pgvector with a StreamingDiskANN index, statistical binary quantization, and label-based filtering, aimed at vector workloads too large to keep fully in memory.

    • Open source · PostgreSQL
    • Self-hosted
    • Rust
  • Pinecone logo

    Pinecone

    Pinecone Systems · pinecone.io

    Pinecone is a managed vector database with serverless indexes, dense and sparse vectors, metadata filtering, and Dedicated Read Nodes, sold as part of a knowledge platform that also includes Pinecone Assistant and the Nexus knowledge engine for agents.

    • Managed cloud
    • API
    • Python
    • TypeScript
    • Go
  • Qdrant

    qdrant.tech

    Qdrant is an open-source vector search engine written in Rust that supports payload filtering, dense and sparse vectors for hybrid search, multi-vector representations, and vector quantization, and runs self-hosted or on Qdrant Cloud.

    • Open source · Apache-2.0
    • Self-hosted
    • Managed cloud
    • Rust
    • Python
    • TypeScript
  • SingleStore

    singlestore.com

    SingleStore is a distributed SQL database for transactions and analytics with a native vector type, indexed approximate nearest neighbor search, and full-text search, so vector queries can join relational data; it runs as the managed Helios service or self-managed.

    • Managed cloud
    • Self-hosted
  • sqlite-vec logo

    sqlite-vec

    alexgarcia.xyz

    sqlite-vec is an open-source SQLite extension written in C that stores and queries float and binary vectors in virtual tables, and runs wherever SQLite does, including mobile devices, browsers through WebAssembly, and servers.

    • Open source · MIT OR Apache-2.0
    • Library
    • Local
    • C
  • Supabase Vector logo

    Supabase Vector

    Supabase · supabase.com

    Supabase Vector is the vector toolkit in Supabase's Postgres platform, using pgvector to store, index, and query embeddings next to application data, with client libraries and Edge Functions for generating embeddings and building AI features.

    • Open source · Apache-2.0
    • Managed cloud
    • Self-hosted
  • turbopuffer logo

    turbopuffer

    turbopuffer.com

    turbopuffer is a managed search engine that stores vector and BM25 full-text indexes on object storage with caching in front, organizing data into namespaces so applications can keep separate indexes per user or tenant.

    • Managed cloud
    • API
  • Typesense logo

    Typesense

    typesense.org

    Typesense is an open-source, typo-tolerant search engine written in C++ that adds vector, semantic, and hybrid search, can generate embeddings with built-in or external models, and runs self-hosted or on Typesense Cloud.

    • Open source · GPL-3.0
    • Self-hosted
    • Managed cloud
    • C++
  • Upstash Vector

    Upstash · upstash.com

    Upstash Vector is a serverless vector database for RAG and semantic search with built-in embedding models, hybrid search, metadata filtering, and namespaces, accessed over a REST API that also works from edge runtimes.

    • Managed cloud
    • API
  • Vald logo

    Vald

    vald.vdaas.org

    Vald is an open-source distributed vector search engine written in Go that runs on Kubernetes, uses the NGT approximate nearest neighbor library, and spreads indexes across agent pods with automatic indexing and index backups.

    • Open source · Apache-2.0
    • Self-hosted
    • Go
  • VectorChord logo

    VectorChord

    TensorChord · vectorchord.ai

    VectorChord is a PostgreSQL extension for disk-friendly vector search that succeeds pgvecto.rs, combines IVF indexing with RaBitQ quantization, and stays compatible with pgvector data types so existing schemas can move over.

    • Open source · AGPL-3.0-only OR Elastic-2.0
    • Self-hosted
    • Rust
  • Vespa

    Vespa.ai · vespa.ai

    Vespa is an open-source AI search platform that combines vector search, full-text search, structured filtering, and tensor-based ranking in one engine for search, recommendation, and RAG, and runs self-hosted or on Vespa Cloud.

    • Open source · Apache-2.0
    • Self-hosted
    • Managed cloud
    • Java
    • C++
  • Weaviate logo

    Weaviate

    weaviate.io

    Weaviate is an open-source vector database written in Go that stores objects alongside their vectors, combines keyword and vector search in hybrid queries, and connects to embedding providers through modules, with Weaviate Cloud as the managed option.

    • Open source · BSD-3-Clause (enterprise code under the Weaviate License)
    • Self-hosted
    • Managed cloud
    • Go
    • Python
    • TypeScript

How to choose

01Deployment
A fully managed service, a self-hosted server or cluster, an embedded library, or an extension to a database you already operate.
02Search features
Hybrid dense and sparse retrieval, full-text search, metadata filtering, multi-vector support, and built-in reranking.
03Scale and indexing
Index types such as HNSW, IVF, or disk-based DiskANN, plus vector quantization, determine memory use, cost, and recall at large corpus sizes.
04Operations
Backups, replication, multi-tenancy, and how inserts, updates, and deletes affect index freshness.
05License
Permissive licenses such as Apache-2.0 or MIT, copyleft or source-available terms such as AGPL-3.0 or SSPL, or a proprietary managed service.
06Ecosystem
Client SDKs and integrations with frameworks such as LangChain and LlamaIndex, and with embedding providers, reduce glue code.

Frequently asked questions

What is a vector database used for?

A vector database is used to find items that are semantically similar to a query. Common uses include retrieval for RAG applications, semantic and hybrid search, recommendations, deduplication, and long-term memory for AI agents. It stores embeddings alongside metadata and uses approximate nearest neighbor indexes to return the closest matches quickly, even across millions of records.

Do I need a vector database for RAG?

Not always. A small corpus can be searched in memory with a library such as Faiss, and teams already running PostgreSQL, MongoDB, or Elasticsearch can add vector search there. A dedicated vector database becomes useful when the corpus reaches millions of chunks, when you need hybrid search and filtering at low latency, or when retrieval must scale independently of the main application database.

Is Postgres a vector database?

PostgreSQL is a relational database, but extensions turn it into a capable vector store. pgvector adds a vector type with exact search and HNSW and IVFFlat indexes, while pgvectorscale and VectorChord add disk-friendly indexes for larger workloads. Embeddings then sit in the same tables as application data and use SQL joins, transactions, and backups.

What is the difference between a vector database and a relational database?

A relational database stores rows in tables and answers exact queries, such as all orders from a given customer, using indexes on column values. A vector database stores high-dimensional embeddings and answers similarity queries, such as the passages closest in meaning to a question. Many relational and document databases now include vector indexes, so the two roles often share one system.

What is the best open source vector database for RAG?

No single open-source vector database fits every RAG system. Qdrant, Weaviate, and Milvus are standalone engines with hybrid search and horizontal scaling, Chroma and LanceDB suit embedded and local use, and pgvector fits teams already on PostgreSQL. Check the license as well: some projects are Apache-2.0 or MIT, while others use AGPL-3.0, SSPL, or source-available terms.

Other categories

Product details change quickly; check each vendor’s site for current features, licensing and pricing.