Clone Index | VMware Private AI Service API

Clone Index

Clone an index and all currently stored data.

Trigger the cloning of an index from one knowledge base into another.

Cloning creates a new index in the target knowledge base with the same configuration as the source, then starts a background task to copy all documents, metadata, and embeddings. The cloned index functions independently of the original.

If an indexing is already active for the target knowledge base, the request will fail with a conflict error.

Request

URI

POST

https://{api_host}/api/v1/control/knowledge-bases/{knowledge_base_id}/indexes/{index_id}/clone

COPY

Path Parameters

string

knowledge_base_id

Required

knowledge_base_id

string

index_id

Required

index_id

Request Body

IndexCloneRequest of type(s) application/json

Required

{
    "clone_into_knowledge_base_id": "string"
}

string As uuid As uuid

clone_into_knowledge_base_id

Required

ID of the knowledge base to clone into.

Authentication

This operation uses the following authentication methods.

openId

Responses

201

Successful Response

Returns Index of type(s) application/json

{
    "id": "string",
    "name": "string",
    "description": "string",
    "embeddings_model_endpoint": "string",
    "text_splitting": "string",
    "chunk_size": 0,
    "chunk_overlap": 0,
    "hybrid_search": false,
    "text_search_config": "simple",
    "knowledge_base_id": "string",
    "object": "string",
    "created_at": 0,
    "last_indexed_at": 0,
    "last_indexed_by_id": "string",
    "num_documents": 0,
    "status": "string",
    "status_errors": [
        "string"
    ]
}

string As uuid As uuid

Required

ID of the index.

string

name

Optional

Constraints: maxLength: 256

Name of the index.

string

description

Optional

Description of the index.

string

embeddings_model_endpoint

Required

ID of the model to be used by the index for generating embeddings.

string

text_splitting

Required

Method for chunking text for embedding

integer

chunk_size

Required

Constraints: minimum: 100

Maximum size (in tokens) of the text chunks. This must be at least 100 to accommodate for content metadata embedded alongside each chunk of text.

integer

chunk_overlap

Optional

Constraints: minimum: 0 default: 0

Size of the chunk overlap (in tokens) when splitting text.

boolean

hybrid_search

Optional

Enable or disable hybrid search. If enabled, text_search_config must be provided.

string

text_search_config

Optional

The text search configuration to use for hybrid search. The available values depend on the version of the database server used by this Private AI Services instances. Please refer to the PostgreSQL server documentation for available values. For example: 'simple', 'english', 'french'.

string As uuid As uuid

knowledge_base_id

Required

ID of the knowledge base of the index.

string

object

Optional

Constraints: default: index

Object type, which is always index.

integer

created_at

Required

Unix timestamp (in seconds) when the index was created.

integer

last_indexed_at

Optional

Unix timestamp (in seconds) when the index contents were last indexed.

string As uuid As uuid

last_indexed_by_id

Optional

ID of the most recent indexing job that affected this index.

integer

num_documents

Optional

Constraints: minimum: 0 default: 0

Total number of documents in the index.

string

status

Required

Availability status of the index.

Possible values are : AVAILABLE, ERROR,

array of string

status_errors

Optional

Details of the index error status, if the index is not available.

Possible values are : AGENT_ID_NOT_FOUND, FAILED_TO_PAGINATE_LIST, AGENT_SESSION_ID_NOT_FOUND, INDEX_NOT_FOUND, INDEX_NOT_REACHABLE, ROUTE_TO_MODEL_NOT_FOUND, INVALID_MODEL_TYPE_FOR_AGENT, AGENT_SESSION_EXPIRED, UNEXPECTED_MODEL, INVALID_RESPONSE_FROM_MODEL_ENDPOINT, INVALID_INFERENCE_REQUEST_FOR_MODEL_TYPE, VALIDATION_ERROR, MAX_LENGTH_METADATA_REACHED, INVALID_AGENT_ATTRIBUTE, KNOWLEDGE_BASE_INVALID_STATE, DATA_SOURCE_NOT_FOUND, DATA_SOURCE_STILL_LINKED_TO_KNOWLEDGE_BASE, KNOWLEDGE_BASE_NOT_FOUND, DOCUMENT_NOT_FOUND, EMPTY_DOCUMENT_FILE, DOCUMENT_EXCEEDS_MAX_UPLOAD_SIZE, INDEXING_NOT_FOUND, NO_ACTIVE_INDEXING, ERROR_NOT_FOUND, INDEX_FOR_KNOWLEDGE_BASE_ALREADY_EXISTS, UNSUPPORTED_CONFIGURATION, PENDING_INDEXING_ALREADY_EXISTS_FOR_KB, CREATING_INDEXING_FOR_LOCAL_FILES_KB_NOT_ALLOWED, KNOWLEDGE_BASE_DATA_SOURCE_NOT_UNLINKING, KNOWLEDGE_BASE_DATA_SOURCE_NOT_FOUND, KNOWLEDGE_BASE_DATA_SOURCE_ALREADY_EXISTS, KNOWLEDGE_BASE_LINK_DATA_SOURCE_NOT_SUPPORTED, KNOWLEDGE_BASE_UPLOAD_NOT_SUPPORTED_FOR_DATA_SOURCE, KNOWLEDGE_BASE_DELETE_NOT_SUPPORTED_FOR_DATA_SOURCE, KNOWLEDGE_BASE_DELETE_NOT_SUPPORTED_WHILE_AGENT_IS_LINKED, KNOWLEDGE_BASE_DELETE_CONFLICT, DOCUMENT_NOT_IN_DELETABLE_STATE, COMPLETION_MODEL_ENDPOINT_UNAVAILABLE, EMBEDDING_MODEL_ENDPOINT_UNAVAILABLE, EMBEDDING_MODEL_ENDPOINT_BAD_TYPE, MCP_SERVER_NOT_FOUND, MCP_TOOLS_IN_USE, TOOL_NOT_FOUND, INVALID_MODEL_CONFIGURATION, TOOL_NOT_APPROVED, TOOL_NOT_AVAILABLE, INVALID_TOOL_CONFIGURATION, MCP_SERVER_HEADER_NOT_FOUND, AGENT_COMPLETION_FAILED, DISALLOWED_ROLE,

404

Invalid knowledge base or index ID.

Operation doesn't return any data structure

409

An active Indexing already exists for this knowledge base ID.

Operation doesn't return any data structure

422

Validation Error

Returns HTTPValidationError of type(s) application/json

{
    "detail": [
        {
            "loc": [
                {}
            ],
            "msg": "string",
            "type": "string"
        }
    ]
}

array of object

detail

Optional

detail

Code Samples

COPY

                    curl -X POST -H 'Authorization: <value>' -H 'Content-Type: application/json' -d '{"clone_into_knowledge_base_id":"string"}' https://{api_host}/api/v1/control/knowledge-bases/{knowledge_base_id}/indexes/{index_id}/clone

On This Page

Description

Request

Path Parameters

Request Body

Authentication

Response

201 Response Body

Errors

Indexes Operations

GET

List All Indexes