Update Knowledge Base

Endpoint

PUT /apiops/projects/{projectName}/knowledge-bases/{name}/

Authentication

Requires a Personal API Access Token.

Header

Authorization: Bearer YOUR_TOKEN

Request

Headers

Header	Value	Required
Authorization	Bearer {token}	Yes
Content-Type	application/json	Yes

Path Parameters

Parameter	Type	Required	Description
projectName	string	Yes	Project name
name	string	Yes	Knowledge base name (must already exist)

Query Parameters

None

Request Body

Full JSON Body Example

{
  "name": "product-docs",
  "description": "Updated product documentation knowledge base",
  "vectorDbRef": "qdrant-main",
  "embeddingProviderRef": "openai-embeddings",
  "collectionName": "product_docs",
  "chunkSize": 800,
  "chunkOverlap": 150,
  "embeddingModelId": "text-embedding-3-large"
}

Request Body Fields

Field	Type	Required	Default	Description
name	string	No	path name	Knowledge base name. May be omitted (falls back to the path variable). If provided, it must match the path name (case-insensitive).
description	string	No	-	Free-text description
vectorDbRef	string	No	-	Name reference to the VectorDB connection backing this knowledge base
embeddingProviderRef	string	No	-	Name reference to the LLM provider used for embeddings
collectionName	string	No	-	Vector store collection/index name
chunkSize	integer	No	1000	Token count per chunk. An omitted/zero value keeps the default.
chunkOverlap	integer	No	200	Overlap tokens between consecutive chunks. An omitted/zero value keeps the default.
embeddingModelId	string	No	-	Embedding model identifier

Notes

• projectId in the body is ignored — the project is always taken from the URL path.
• id, status, docCount, chunkCount, createdAt and updatedAt are server-controlled. Counter and status fields are preserved and are not overwritten by the request body.
• The knowledge base must already exist; otherwise a 400 Bad Request is returned. To create-or-update in one call, use the upsert POST.

Response

Success Response (200 OK)

{
  "status": "SUCCESS",
  "deploymentResult": {
    "success": true
  }
}

Error Response (400 Bad Request)

{
  "status": "FAILURE",
  "resultMessage": "Knowledge base (name: product-docs) was not found!"
}

or

{
  "status": "FAILURE",
  "resultMessage": "Knowledge base name in path (product-docs) does not match name in body (other-name)!"
}

Error Response (401 Unauthorized)

{
  "status": "FAILURE",
  "resultMessage": "Token is not valid!"
}

cURL Example

curl -X PUT \
  "https://demo.apinizer.com/apiops/projects/MyProject/knowledge-bases/product-docs/" \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "product-docs",
    "description": "Updated product documentation knowledge base",
    "vectorDbRef": "qdrant-main",
    "embeddingProviderRef": "openai-embeddings",
    "collectionName": "product_docs",
    "chunkSize": 800,
    "chunkOverlap": 150,
    "embeddingModelId": "text-embedding-3-large"
  }'

Notes and Warnings

• Must Exist: PUT only updates an existing knowledge base. A non-existent name returns 400 Bad Request. Use the upsert POST to create-or-update.
• Name Match: If the body contains a name, it must match the path name (case-insensitive).
• Project From Path Only: The body projectId is never trusted.
• Server-Controlled Fields: status, docCount and chunkCount remain server-maintained and are not affected by the request body.
• Changing Embedding Settings: Changing vectorDbRef, embeddingProviderRef, collectionName or chunking settings does not automatically re-embed existing documents. Trigger a reindex to rebuild the vector index against the new configuration.
• Permissions: Requires AI_DEVELOPMENT + MANAGE permission in the project.

Related Documentation

• Create Knowledge Base - Create or update a knowledge base (upsert)
• Reindex Knowledge Base - Rebuild the vector index
• Get Knowledge Base - Get a single knowledge base by name
• Knowledge Bases API - Resource overview