pgvector

PostgreSQL extension storing vectors in tables, exact search by default with optional HNSW and IVFFlat indexes.

Provider: default
Kind: Vector database
Category: Data
Official docs: https://github.com/pgvector/pgvector

Properties · 4 set by this component

property	type	values	required	kind default	this component
annIndex · component property	enum	none \| hnsw \| ivfflat	no	none	inherited
dimensions	integer	—	no	—	inherited
distanceMetric	enum	cosine \| euclidean \| dot-product	no	—	inherited
hybridSearch	boolean	—	no	false	inherited
indexType	enum	flat \| hnsw \| ivf \| disk-ann \| lsh	no	—	▸ flat
managed	boolean	—	no	false	▸ false
maxDimensions · component property	integer	—	no	16000	inherited
metadataFiltering	boolean	—	no	false	▸ true
namespaces	boolean	—	no	false	inherited
quantization	enum	none \| scalar \| product \| binary	no	none	▸ none
replicas	integer	—	no	—	inherited
vectorType · component property	enum	vector \| halfvec \| bit \| sparsevec	no	vector	inherited

Rules that apply · 0

Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.

No rule reads this kind yet. That is a gap, not a guarantee.

Use it in a design

nodes:
  - { id: "pgvector", component: "pgvector" }

Other Vector database products · 23

Alibaba Cloud Milvusalibaba-milvusalibabacloudvector-database Amazon S3 Vectorsaws-s3-vectorsawsvector-database Agent Memorycloudflare-agent-memorycloudflarevector-database Cloudflare Vectorizecloudflare-vectorizecloudflarevector-database Chromachromavector-database Deep Lakedeeplakevector-database Epsillaepsillavector-database KDB.AIkdb-aivector-database LanceDBlancedbvector-database Marqomarqovector-database Milvusmilvusvector-database MyScalemyscalevector-database pgvectorscalepgvectorscalevector-database Pineconepineconevector-database Qdrantqdrantvector-database turbopufferturbopuffervector-database Valdvaldvector-database Generic vector databasevector-databasevector-database Vespa Cloudvespa-cloudvector-database Weaviateweaviatevector-database Zilliz Cloudzilliz-cloudvector-database DigitalOcean Vector Databasesdigitalocean-vector-databasedigitaloceanvector-database Vertex AI Vector Searchgoogle-vertex-ai-vector-searchgcpvector-database

Source

1# yaml-language-server: $schema=../../schema/component.schema.json
2# pgvector: PostgreSQL extension storing vectors in ordinary tables. README: exact nearest neighbour
3# search with perfect recall is the default, HNSW and IVFFlat indexes are opt-in; L2, inner product,
4# cosine, L1, Hamming and Jaccard operators; vector and halfvec hold up to 16000 dimensions.
5schemaVersion: "1"
6type: "component"
7id: "pgvector"
8kind: "vector-database"
9provider: "default"
10docs: "https://github.com/pgvector/pgvector"
11defaults:
12  indexType: "flat"
13  quantization: "none"
14  metadataFiltering: true
15  managed: false
16properties:
17  annIndex:
18    type: "enum"
19    values: ["none", "hnsw", "ivfflat"]
20    default: "none"
21  vectorType:
22    type: "enum"
23    values: ["vector", "halfvec", "bit", "sparsevec"]
24    default: "vector"
25  maxDimensions:
26    type: "integer"
27    default: 16000

The same page as markdown, for an agent: /catalogue/components/pgvector.md