Cloudflare Vectorize
Managed vector index with namespaces and metadata filtering for Workers AI applications.
- Provider
- cloudflare
- Kind
- Vector database
- Category
- Data
| 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 | — | inherited |
| managed | boolean | — | no | false | ▸ true |
| maxDimensions | integer | — | no | 1536 | inherited |
| maxMetadataIndexes | integer | — | no | 10 | inherited |
| maxNamespacesPerIndex | integer | — | no | 50000 | inherited |
| maxTopK | integer | — | no | 100 | inherited |
| maxVectorsPerIndex | integer | — | no | 20000000 | inherited |
| metadataFiltering | boolean | — | no | false | ▸ true |
| namespaces | boolean | — | no | false | ▸ true |
| quantization | enum | none | scalar | product | binary | no | none | ▸ none |
| replicas | integer | — | no | — | 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: "vectorize", component: "cloudflare-vectorize" }Alibaba Cloud Milvusalibaba-milvusAmazon S3 Vectorsaws-s3-vectorsAgent Memorycloudflare-agent-memoryChromachromaDeep LakedeeplakeEpsillaepsillaKDB.AIkdb-aiLanceDBlancedbMarqomarqoMilvusmilvusMyScalemyscalepgvectorpgvectorpgvectorscalepgvectorscalePineconepineconeQdrantqdrantturbopufferturbopufferValdvaldGeneric 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 # Vectorize index: Cloudflare's managed vector database for Workers. "Create indexes" states the # dimensions and the distance metric must be chosen at creation and cannot change afterwards, so # neither is defaulted here; "Vectorize - Limits" gives 1,536 dimensions, 20M vectors and namespaces. schemaVersion: "1" type: "component" id: "cloudflare-vectorize" kind: "vector-database" provider: "cloudflare" docs: "https://developers.cloudflare.com/vectorize/platform/limits/" defaults: managed: true metadataFiltering: true namespaces: true quantization: "none" properties: maxDimensions: type: "integer" default: 1536 maxVectorsPerIndex: type: "integer" default: 20000000 maxNamespacesPerIndex: type: "integer" default: 50000 maxMetadataIndexes: type: "integer" default: 10 maxTopK: type: "integer" default: 100