Update Knowledge Base
Updates a knowledge base. Every field is optional; omitting a field leaves it unchanged.
embedding_model and vector_backend cannot be changed after creation and are not accepted here. Changes to chunk_size and chunking_strategy apply at index time, affecting material ingested after the change - nothing already indexed is re-chunked.
Path Parameters
Knowledge Base ID.
Body
Request body for updating a knowledge base. Every field is optional and nullable; omitting a field leaves it unchanged. embedding_model and vector_backend are absent by design - both are fixed at creation and cannot be changed afterwards.
New name for the knowledge base. Omit to leave it unchanged.
New description. Omit to leave it unchanged.
New primary language. A free-form string, not an enum: an unrecognised value is accepted and stored rather than rejected.
Strategy used to split source material into chunks before embedding.
fixed_size, semantic, sentence, paragraph, recursive New chunk size. Applied at index time; nothing already indexed is re-chunked.
100 <= x <= 4096New chunk overlap. Applied at index time.
0 <= x <= 500New persona. Because omitting a field means 'leave unchanged', null is indistinguishable from not sending the field at all - send an empty string to reset the persona to its name-derived default.
280Response
The updated knowledge base.
Response model for a knowledge base.
Unique identifier of the knowledge base.
The name of the knowledge base.
UTC timestamp indicating when this knowledge base was created.
UTC timestamp indicating when this knowledge base was last modified.
Description of the knowledge base's purpose and contents.
Primary language of the material in this knowledge base.
Number of documents stored in this knowledge base.
Chunking strategy currently in effect for new material.
fixed_size, semantic, sentence, paragraph, recursive Vector database backing this knowledge base's index.
pinecone, qdrant, weaviate, milvus, pgvector Embedding model in use. Note the asymmetry with the create request, which defaults to text-embedding-3-large: this schema's default is text-embedding-3-small because knowledge bases created before the field existed are on small. Read the value off the response rather than assuming it.
text-embedding-3-small, text-embedding-3-large Target chunk size for new material.
Overlap between consecutive chunks.
How an assistant built on this knowledge base introduces itself.
Aggregate processing state of the knowledge base's documents.
processing, completed, failed Workspace this knowledge base belongs to.
Organization this knowledge base belongs to, resolved from your token.
User this knowledge base belongs to, resolved from your token.

