Create Knowledge Base

Kafka source configuration for the knowledge base pipeline.

Exactly one of topic or topicPattern must be set:

• topic — exact Kafka topic name. This is what the Streamkap app sets.
• topicPattern — a regex for reading several topics (e.g. fan-in of a sharded topic family). Available through the API only.

Setting neither or both returns 422.

Text template configuration for composing the embedding input from record fields.

Embedding-side configuration for a knowledge base.

Carries a reference to a saved AgentLlmConnection plus optional per-KB overrides of the connection's defaults. Credentials, provider, and the default model live on the connection — a KB cannot carry an inline apiKey / baseUrl. At deploy time Streamkap reads the referenced connection's embedding defaults and applies any per-KB overrides.

The referenced connection must carry 'embedding' in its capabilities list and have a non-empty embedding.model; otherwise the deploy fails with 422 naming the cause.

Vector store configuration for the knowledge base.

References a saved AgentVectorStoreConnection by id; Streamkap resolves its credentials server-side at deploy time. A KB cannot carry inline vector-store credentials.

Processing configuration for the knowledge base pipeline.