KDB.AI

KX vector database on kdb+ for contextual and time-series similarity search, now self-hosted.

Provider
default
Category
Data
Also known as
KDB.AI Server
Properties · 2 set by this component
propertytypevaluesrequiredkind defaultthis component
dimensionsinteger—no—inherited
distanceMetricenumcosine | euclidean | dot-productno—inherited
hybridSearchboolean—nofalseinherited
indexTypeenumflat | hnsw | ivf | disk-ann | lshno—inherited
licence · component propertyenumcommunity | kdb-xnocommunityinherited
managedboolean—nofalse▸ false
metadataFilteringboolean—nofalse▸ true
namespacesboolean—nofalseinherited
quantizationenumnone | scalar | product | binarynononeinherited
replicasinteger—no—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: "kdb-ai", component: "kdb-ai" }
Other Vector database products · 23
Source
# yaml-language-server: $schema=../../schema/component.schema.json
# KDB.AI: KX vector database on kdb+ for contextual and time-series similarity search. KDB.AI Cloud closed to registration
# and was sunset; per "KDB.AI Server Setup" the product now runs as the self-hosted kdbai-db container, and upgrading users
# need a KDB-X licence while community licence holders use theirs directly.
schemaVersion: "1"
type: "component"
id: "kdb-ai"
kind: "vector-database"
provider: "default"
docs: "https://code.kx.com/kdbai/latest/gettingStarted/kdb-ai-server-setup.html"
aliases: ["KDB.AI Server"]
defaults:
  managed: false
  metadataFiltering: true
properties:
  licence:
    type: "enum"
    values: ["community", "kdb-x"]
    default: "community"

The same page as markdown, for an agent: /catalogue/components/kdb-ai.md