Weaviate

Open-source vector database with an HNSW index, cosine distance and built-in BM25 hybrid search.

Provider: default
Kind: Vector database
Category: Data
Official docs: https://docs.weaviate.io/weaviate/config-refs/indexing/vector-index

Properties · 8 set by this component

property	type	values	required	kind default	this component
dimensions	integer	—	no	—	inherited
distanceFunction · component property	enum	cosine \| dot \| l2-squared \| manhattan \| hamming	no	cosine	inherited
distanceMetric	enum	cosine \| euclidean \| dot-product	no	—	▸ cosine
hybridSearch	boolean	—	no	false	▸ true
indexType	enum	flat \| hnsw \| ivf \| disk-ann \| lsh	no	—	▸ hnsw
managed	boolean	—	no	false	▸ false
metadataFiltering	boolean	—	no	false	▸ true
multiTenancy · component property	boolean	—	no	false	inherited
namespaces	boolean	—	no	false	▸ false
quantization	enum	none \| scalar \| product \| binary	no	none	▸ none
replicas	integer	—	no	—	▸ 1
vectorIndexAlgorithm · component property	enum	hnsw \| flat \| dynamic	no	hnsw	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: "weaviate", component: "weaviate" }

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 pgvectorpgvectorvector-database pgvectorscalepgvectorscalevector-database Pineconepineconevector-database Qdrantqdrantvector-database turbopufferturbopuffervector-database Valdvaldvector-database Generic vector databasevector-databasevector-database Vespa Cloudvespa-cloudvector-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# Weaviate: open-source vector database with built-in hybrid (BM25 plus vector) search.
3# "Vector index" and "Distance metrics": HNSW is the default index and cosine the default distance.
4# "Collection definition": multi-tenancy is off unless enabled, quantization is not applied unless
5# configured, and the replication factor of a new collection is 1.
6schemaVersion: "1"
7type: "component"
8id: "weaviate"
9kind: "vector-database"
10provider: "default"
11docs: "https://docs.weaviate.io/weaviate/config-refs/indexing/vector-index"
12defaults:
13  indexType: "hnsw"
14  distanceMetric: "cosine"
15  quantization: "none"
16  metadataFiltering: true
17  hybridSearch: true
18  namespaces: false
19  replicas: 1
20  managed: false
21properties:
22  multiTenancy:
23    type: "boolean"
24    default: false
25  vectorIndexAlgorithm:
26    type: "enum"
27    values: ["hnsw", "flat", "dynamic"]
28    default: "hnsw"
29  distanceFunction:
30    type: "enum"
31    values: ["cosine", "dot", "l2-squared", "manhattan", "hamming"]
32    default: "cosine"

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