Endpoint

View as Markdown

Get

GET /api/2.0/vector-search/endpoints/{name}

Get details for a single AI Search endpoint.

API scopes: vector-search

Parameters

namestringpath: Name of the endpoint

Response

namestring: Name of the AI Search endpoint
Example: docs-endpoint

creatorstring: Creator of the endpoint
Example: john@example.com

creation_timestampint64: Timestamp of endpoint creation
Example: 1702013512061

last_updated_timestampint64: Timestamp of last update to the endpoint
Example: 1702013512061

endpoint_typestring: Type of endpoint
Values: STORAGE_OPTIMIZED, STANDARD

last_updated_userstring: User who last updated the endpoint
Example: john@example.com

idstring: Unique identifier of the endpoint
Example: c56bf0a9-4929-4bd4-8bd5-d82ca62f9c76

endpoint_statusobject

Current status of the endpoint

Show child attributesHide child attributes

statestring: Current state of the endpoint
Values: PROVISIONING, ONLINE, OFFLINE, RED_STATE, YELLOW_STATE, DELETED
Example: PROVISIONING

messagestring: Additional status message

num_indexesint32: Number of indexes on the endpoint

budget_policy_idstring: The user-selected budget policy id for the endpoint.

effective_budget_policy_idstring: The budget policy id applied to the endpoint
Example: 8b0444ff-8b60-48b0-9d31-e391f6126e0f

scaling_infoobject

Scaling information for the endpoint

Show child attributesHide child attributes

statestring: The current state of the scaling change request.
Values: SCALING_CHANGE_UNSPECIFIED, SCALING_CHANGE_APPLIED, SCALING_CHANGE_IN_PROGRESS
Example: SCALING_CHANGE_APPLIED

requested_target_qpsint64: The requested QPS target for the endpoint. Best-effort; the system does not guarantee this QPS will be achieved.
Example: 500

View as Markdown

Response

{
  "name": "docs-endpoint",
  "creator": "john@example.com",
  "creation_timestamp": 1702013512061,
  "last_updated_timestamp": 1702013512061,
  "endpoint_type": "string",
  "last_updated_user": "john@example.com",
  "id": "c56bf0a9-4929-4bd4-8bd5-d82ca62f9c76",
  "endpoint_status": {
    "state": "PROVISIONING",
    "message": "string"
  },
  "num_indexes": 0,
  "budget_policy_id": "string",
  "effective_budget_policy_id": "8b0444ff-8b60-48b0-9d31-e391f6126e0f",
  "scaling_info": {
    "state": "SCALING_CHANGE_APPLIED",
    "requested_target_qps": 500
  }
}

Create

POST /api/2.0/vector-search/endpoints

Create a new endpoint.

API scopes: vector-search

Request body

namestring: Name of the AI Search endpoint
Example: docs-endpoint

endpoint_typestring: Type of endpoint
Values: STORAGE_OPTIMIZED, STANDARD

budget_policy_idstring: The budget policy id to be applied
Example: 8b0444ff-8b60-48b0-9d31-e391f6126e0f

target_qpsint64: Target QPS for the endpoint. Mutually exclusive with num_replicas. The actual replica count is calculated at index creation/sync time based on this value. Best-effort target; the system does not guarantee this QPS will be achieved.
Example: 100

Response

namestring: Name of the AI Search endpoint
Example: docs-endpoint

creatorstring: Creator of the endpoint
Example: john@example.com

creation_timestampint64: Timestamp of endpoint creation
Example: 1702013512061

last_updated_timestampint64: Timestamp of last update to the endpoint
Example: 1702013512061

endpoint_typestring: Type of endpoint
Values: STORAGE_OPTIMIZED, STANDARD

last_updated_userstring: User who last updated the endpoint
Example: john@example.com

idstring: Unique identifier of the endpoint
Example: c56bf0a9-4929-4bd4-8bd5-d82ca62f9c76

endpoint_statusobject

Current status of the endpoint

Show child attributesHide child attributes

statestring: Current state of the endpoint
Values: PROVISIONING, ONLINE, OFFLINE, RED_STATE, YELLOW_STATE, DELETED
Example: PROVISIONING

messagestring: Additional status message

num_indexesint32: Number of indexes on the endpoint

budget_policy_idstring: The user-selected budget policy id for the endpoint.

effective_budget_policy_idstring: The budget policy id applied to the endpoint
Example: 8b0444ff-8b60-48b0-9d31-e391f6126e0f

scaling_infoobject

Scaling information for the endpoint

Show child attributesHide child attributes

statestring: The current state of the scaling change request.
Values: SCALING_CHANGE_UNSPECIFIED, SCALING_CHANGE_APPLIED, SCALING_CHANGE_IN_PROGRESS
Example: SCALING_CHANGE_APPLIED

requested_target_qpsint64: The requested QPS target for the endpoint. Best-effort; the system does not guarantee this QPS will be achieved.
Example: 500

View as Markdown

Request

Create a Standard endpoint

{
  "budget_policy_id": "8b0444ff-8b60-48b0-9d31-e391f6126e0f",
  "endpoint_type": "STANDARD",
  "name": "docs-endpoint"
}

Response

Successful response

{
  "creation_timestamp": 1702013512061,
  "creator": "john@example.com",
  "effective_budget_policy_id": "8b0444ff-8b60-48b0-9d31-e391f6126e0f",
  "endpoint_status": {
    "state": "PROVISIONING"
  },
  "endpoint_type": "STANDARD",
  "id": "c56bf0a9-4929-4bd4-8bd5-d82ca62f9c76",
  "last_updated_timestamp": 1702013512061,
  "last_updated_user": "john@example.com",
  "name": "docs-endpoint"
}

Update

PATCH /api/2.0/vector-search/endpoints/{name}/budget-policy

Update the budget policy of an endpoint

API scopes: vector-search

Parameters

namestringpath: Name of the AI Search endpoint

Request body

budget_policy_idstring: The budget policy id to be applied
Example: 8b0444ff-8b60-48b0-9d31-e391f6126e0f

Response

budget_policy_idstring

effective_budget_policy_idstring: The budget policy applied to the AI Search endpoint.

Delete

DELETE /api/2.0/vector-search/endpoints/{name}

Delete an AI Search endpoint.

API scopes: vector-search

Parameters

namestringpath: Name of the AI Search endpoint

Patch Endpoint

PATCH /api/2.0/vector-search/endpoints/{name}

Update an endpoint

API scopes: vector-search

Parameters

namestringpath: Name of the AI Search endpoint
Example: docs-endpoint

Request body

target_qpsint64: Target QPS for the endpoint. Best-effort; the system does not guarantee this QPS will be achieved.
Example: 100

Response

namestring: Name of the AI Search endpoint
Example: docs-endpoint

creatorstring: Creator of the endpoint
Example: john@example.com

creation_timestampint64: Timestamp of endpoint creation
Example: 1702013512061

last_updated_timestampint64: Timestamp of last update to the endpoint
Example: 1702013512061

endpoint_typestring: Type of endpoint
Values: STORAGE_OPTIMIZED, STANDARD

last_updated_userstring: User who last updated the endpoint
Example: john@example.com

idstring: Unique identifier of the endpoint
Example: c56bf0a9-4929-4bd4-8bd5-d82ca62f9c76

endpoint_statusobject

Current status of the endpoint

Show child attributesHide child attributes

statestring: Current state of the endpoint
Values: PROVISIONING, ONLINE, OFFLINE, RED_STATE, YELLOW_STATE, DELETED
Example: PROVISIONING

messagestring: Additional status message

num_indexesint32: Number of indexes on the endpoint

budget_policy_idstring: The user-selected budget policy id for the endpoint.

effective_budget_policy_idstring: The budget policy id applied to the endpoint
Example: 8b0444ff-8b60-48b0-9d31-e391f6126e0f

scaling_infoobject

Scaling information for the endpoint

Show child attributesHide child attributes

statestring: The current state of the scaling change request.
Values: SCALING_CHANGE_UNSPECIFIED, SCALING_CHANGE_APPLIED, SCALING_CHANGE_IN_PROGRESS
Example: SCALING_CHANGE_APPLIED

requested_target_qpsint64: The requested QPS target for the endpoint. Best-effort; the system does not guarantee this QPS will be achieved.
Example: 500

View as Markdown

Request

{
  "target_qps": 100
}

Response

{
  "name": "docs-endpoint",
  "creator": "john@example.com",
  "creation_timestamp": 1702013512061,
  "last_updated_timestamp": 1702013512061,
  "endpoint_type": "string",
  "last_updated_user": "john@example.com",
  "id": "c56bf0a9-4929-4bd4-8bd5-d82ca62f9c76",
  "endpoint_status": {
    "state": "PROVISIONING",
    "message": "string"
  },
  "num_indexes": 0,
  "budget_policy_id": "string",
  "effective_budget_policy_id": "8b0444ff-8b60-48b0-9d31-e391f6126e0f",
  "scaling_info": {
    "state": "SCALING_CHANGE_APPLIED",
    "requested_target_qps": 500
  }
}

Retrieve User Visible Metrics

POST /api/2.0/vector-search/endpoints/{name}/metrics

Retrieve user-visible metrics for an endpoint

API scopes: vector-search

Parameters

namestringpath: AI Search endpoint name

Request body

start_timestring: Start time for metrics query

end_timestring: End time for metrics query

granularity_in_secondsint32: Granularity in seconds

metricsarray of object

List of metrics to retrieve

Show child attributesHide child attributes

namestring: Metric name

labelsarray of object

Metric labels

Show child attributesHide child attributes

namestring: Label name

valuestring: Label value

percentiledouble: Percentile for the metric

page_tokenstring: Token for pagination

Response

metric_valuesarray of object

Collection of metric values

Show child attributesHide child attributes

metricobject

Metric specification

Show child attributesHide child attributes

namestring: Metric name

labelsarray of object

Metric labels

Show child attributesHide child attributes

namestring: Label name

valuestring: Label value

percentiledouble: Percentile for the metric

valuesarray of object

Time series of metric values

Show child attributesHide child attributes

timestampint64: Timestamp of the metric value (milliseconds since epoch)

valuedouble: Metric value

next_page_tokenstring: A token that can be used to get the next page of results. If not present, there are no more results to show.

View as Markdown

Request

{
  "start_time": "string",
  "end_time": "string",
  "granularity_in_seconds": 0,
  "metrics": [
    {
      "name": "string",
      "labels": [
        {}
      ],
      "percentile": 0
    }
  ],
  "page_token": "string"
}

Response

{
  "metric_values": [
    {
      "metric": {},
      "values": [
        {}
      ]
    }
  ],
  "next_page_token": "string"
}

Get​

Parameters​

Response​

Create​

Request body​

Response​

Update​

Parameters​

Request body​

Response​

Delete​

Parameters​

Patch Endpoint​

Parameters​

Request body​

Response​

Retrieve User Visible Metrics​

Parameters​

Request body​

Response​

Get

Parameters

Response

Create

Request body

Response

Update

Parameters

Request body

Response

Delete

Parameters

Patch Endpoint

Parameters

Request body

Response

Retrieve User Visible Metrics

Parameters

Request body

Response