Vector database

datavector-database

Stores embeddings and answers nearest-neighbour queries over them.

Category: Data
Properties: 9
Components: 24
Rules: 0

Properties · 9 defined by this kind

A node of this kind resolves each property from its own props, then the component's defaults, then the default below.

property	type	values	required	default
dimensions	integer	—	no	—
distanceMetric	enum	cosine \| euclidean \| dot-product	no	—
hybridSearch	boolean	—	no	false
indexType	enum	flat \| hnsw \| ivf \| disk-ann \| lsh	no	—
managed	boolean	—	no	false
metadataFiltering	boolean	—	no	false
namespaces	boolean	—	no	false
quantization	enum	none \| scalar \| product \| binary	no	none
replicas	integer	—	no	—

Rules for this kind · 0

No rule selects this kind or its category. Governance calls that a recorded gap.

Components · 24

vendor-neutral

Generic vector databasevector-databasegenericthe kind itself

alibabacloud

Alibaba Cloud Milvusalibaba-milvus2 defaults

aws

Amazon S3 Vectorsaws-s3-vectors3 defaults

cloudflare

Agent Memorycloudflare-agent-memory3 defaults Cloudflare Vectorizecloudflare-vectorize4 defaults

default

Chromachroma6 defaults Deep Lakedeeplake2 defaults Epsillaepsilla3 defaults KDB.AIkdb-ai2 defaults LanceDBlancedb4 defaults Marqomarqo5 defaults Milvusmilvus5 defaults MyScalemyscale2 defaults pgvectorpgvector4 defaults pgvectorscalepgvectorscale4 defaults Pineconepinecone4 defaults Qdrantqdrant6 defaults turbopufferturbopuffer4 defaults Valdvald4 defaults Vespa Cloudvespa-cloud4 defaults Weaviateweaviate8 defaults Zilliz Cloudzilliz-cloud4 defaults

digitalocean

DigitalOcean Vector Databasesdigitalocean-vector-database2 defaults

gcp

Vertex AI Vector Searchgoogle-vertex-ai-vector-search4 defaults

Source

1# yaml-language-server: $schema=../schema/kind.schema.json
2# Abstract kind: Stores fixed-dimension embeddings and answers nearest-neighbour queries (Pinecone, Milvus, Qdrant, pgvector, S3 Vectors, Vertex Vector Search).
3schemaVersion: "1"
4type: "kind"
5id: "vector-database"
6category: "data"
7properties:
8  dimensions:
9    type: "integer"
10  distanceMetric:
11    type: "enum"
12    values: ["cosine", "euclidean", "dot-product"]
13  indexType:
14    type: "enum"
15    values: ["flat", "hnsw", "ivf", "disk-ann", "lsh"]
16  quantization:
17    type: "enum"
18    values: ["none", "scalar", "product", "binary"]
19    default: "none"
20  metadataFiltering:
21    type: "boolean"
22    default: false
23  hybridSearch:
24    type: "boolean"
25    default: false
26  namespaces:
27    type: "boolean"
28    default: false
29  replicas:
30    type: "integer"
31  managed:
32    type: "boolean"
33    default: false

The same page as markdown, for an agent: /catalogue/kinds/vector-database.md