Get Knowledge Base

Endpoint

GET /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

Path Parameters

Parameter	Type	Required	Description
projectName	string	Yes	Project name
name	string	Yes	Knowledge base name

Query Parameters

None

Response

Success Response (200 OK)

{
  "status": "SUCCESS",
  "resultList": [
    {
      "id": "6650a1f2e4b0c3a2d1f09876",
      "projectId": "6650a1f2e4b0c3a2d1f01234",
      "name": "product-docs",
      "description": "Product documentation knowledge base",
      "vectorDbRef": "qdrant-main",
      "embeddingProviderRef": "openai-embeddings",
      "collectionName": "product_docs",
      "chunkSize": 1000,
      "chunkOverlap": 200,
      "embeddingModelId": "text-embedding-3-small",
      "status": "ACTIVE",
      "docCount": 12,
      "chunkCount": 340,
      "createdAt": "2026-07-01T09:15:00Z",
      "updatedAt": "2026-07-10T14:32:00Z"
    }
  ],
  "resultCount": 1
}

Response Fields

Field	Type	Description
status	string	Response status: SUCCESS or FAILURE
resultList	array	Single-element list containing the knowledge base object
resultCount	integer	Number of knowledge bases returned (1)

Knowledge Base Object Fields

Field	Type	Description
id	string	Server-generated identifier of the knowledge base
projectId	string	Internal id of the owning project
name	string	Knowledge base name (unique per project)
description	string	Free-text description
vectorDbRef	string	Name reference to the VectorDB connection backing this knowledge base
embeddingProviderRef	string	Name reference to the LLM provider used for embeddings
collectionName	string	Vector store collection/index name
chunkSize	integer	Token count per chunk (default 1000)
chunkOverlap	integer	Overlap tokens between consecutive chunks (default 200)
embeddingModelId	string	Embedding model identifier
status	string	Lifecycle status (server-controlled): ACTIVE, INDEXING, ERROR
docCount	integer	Number of documents (read-only, server-maintained)
chunkCount	integer	Number of indexed chunks (read-only, server-maintained)
createdAt	string	ISO-8601 creation timestamp
updatedAt	string	ISO-8601 last-update timestamp

Knowledge Base Status Values

• ACTIVE - Operational; can answer queries
• INDEXING - An async index/reindex job is running
• ERROR - The last index job failed

EnumStatus

• SUCCESS - Operation successful
• FAILURE - Operation failed

Error Response (400 Bad Request)

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

or

{
  "status": "FAILURE",
  "resultMessage": "Knowledge base name can not be empty!"
}

Error Response (401 Unauthorized)

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

cURL Example

curl -X GET \
  "https://demo.apinizer.com/apiops/projects/MyProject/knowledge-bases/product-docs/" \
  -H "Authorization: Bearer YOUR_TOKEN"

Notes and Warnings

• Name-Based: The knowledge base is resolved by name (case-insensitive exact match) within the project.
• Not Found: A non-existent name returns 400 Bad Request with resultMessage "Knowledge base (name: ...) was not found!".
• No Secrets: The knowledge base payload carries no secret fields; vectorDbRef and embeddingProviderRef are name-based references, not credentials.
• Read-Only Counters: docCount, chunkCount and status are server-maintained.
• Permissions: Requires AI_DEVELOPMENT + VIEW permission in the project.

Related Documentation

• List Knowledge Bases - List all knowledge bases in a project
• Update Knowledge Base - Update an existing knowledge base
• List Documents - List documents in this knowledge base
• Knowledge Bases API - Resource overview