pgvectorscale
Vector databasepgvectorscale
Postgres extension adding a StreamingDiskANN index and binary quantization on top of pgvector.
- Provider
- default
- Kind
- Vector database
- Category
- Data
- Official docs
- https://github.com/timescale/pgvectorscale
| property | type | values | required | kind default | this component |
|---|---|---|---|---|---|
| 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 | — | ▸ disk-ann |
| labelFiltering | boolean | — | no | false | inherited |
| managed | boolean | — | no | false | ▸ false |
| metadataFiltering | boolean | — | no | false | ▸ true |
| namespaces | boolean | — | no | false | inherited |
| quantization | enum | none | scalar | product | binary | no | none | ▸ binary |
| replicas | integer | — | no | — | inherited |
| storageLayout | enum | memory-optimized | plain | no | memory-optimized | inherited |
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.
nodes:
- { id: "pgvectorscale", component: "pgvectorscale" }Alibaba Cloud Milvusalibaba-milvusAmazon S3 Vectorsaws-s3-vectorsAgent Memorycloudflare-agent-memoryCloudflare Vectorizecloudflare-vectorizeChromachromaDeep LakedeeplakeEpsillaepsillaKDB.AIkdb-aiLanceDBlancedbMarqomarqoMilvusmilvusMyScalemyscalepgvectorpgvectorPineconepineconeQdrantqdrantturbopufferturbopufferValdvaldGeneric vector databasevector-databaseVespa Cloudvespa-cloudWeaviateweaviateZilliz Cloudzilliz-cloudDigitalOcean Vector Databasesdigitalocean-vector-databaseVertex AI Vector Searchgoogle-vertex-ai-vector-search
# yaml-language-server: $schema=../../schema/component.schema.json # pgvectorscale: Postgres extension from Timescale (now Tiger Data) that adds a StreamingDiskANN index on top of pgvector. # Per the pgvectorscale README, the index compresses vectors with Statistical Binary Quantization, supports cosine, L2 and # inner product distance, and filters by labels inside the index. schemaVersion: "1" type: "component" id: "pgvectorscale" kind: "vector-database" provider: "default" docs: "https://github.com/timescale/pgvectorscale" defaults: indexType: "disk-ann" quantization: "binary" metadataFiltering: true managed: false properties: storageLayout: type: "enum" values: ["memory-optimized", "plain"] default: "memory-optimized" labelFiltering: type: "boolean" default: false