Endpoint
Endpoint object
- namestring
Name of the AI Search endpoint
- creatorstring
User or service principal that created the endpoint. Users are identified by username and service principals by application ID.
- creation_timestampint64
Time at which the endpoint was created, in milliseconds since the Unix epoch.
- last_updated_timestampint64
Time at which the endpoint was last updated, in milliseconds since the Unix epoch.
- endpoint_typestring
Type of the endpoint. See https://docs.databricks.com/aws/en/ai-search/ai-search#endpoint-options for how the types differ.
STORAGE_OPTIMIZEDSTANDARD
- last_updated_userstring
User or service principal that last updated the endpoint, in the same form as creator.
- idstring
Unique identifier of the endpoint
- endpoint_statusobject
Current status of the endpoint
Show child attributesHide child attributes
- statestring
Current state of the endpoint
PROVISIONINGONLINEOFFLINERED_STATEYELLOW_STATEDELETED
- messagestring
Additional detail about the state, such as the reason the endpoint is OFFLINE. Absent when there is nothing to report.
- num_indexesint32
Number of indexes on the endpoint
- budget_policy_idstringPublic Preview
The user-selected budget policy id for the endpoint.
- effective_budget_policy_idstringPublic Preview
Budget policy ID in effect for the endpoint. This is the policy set on the endpoint when one was set, and otherwise the default budget policy.
- scaling_infoobject
Scaling information for the endpoint. Present only for STANDARD endpoints that have a Target QPS set.
Show child attributesHide child attributes
- statestringBeta
The current state of the scaling change request.
SCALING_CHANGE_UNSPECIFIEDSCALING_CHANGE_APPLIEDSCALING_CHANGE_IN_PROGRESS
- requested_target_qpsint64
The requested QPS target for the endpoint. Best-effort; the system does not guarantee this QPS will be achieved.
- estimated_completion_timestampint64Beta
Estimated time at which the in-progress scaling change will complete, in milliseconds since the Unix epoch. The estimate may change as the scaling change progresses. Unset when no scaling change is in progress, when no estimate is available, or when the change is delayed (see
delayed_reason).
- phasestringBeta
Current phase of the in-progress scaling change. Unset when no scaling change is in progress or the phase is not available.
ADJUSTING_CAPACITYINITIALIZING_INDEXESTIMATING
- index_initialization_percentageint32Beta
Percentage of index initialization completed, from 0 to 100. Set only during the
INITIALIZING_INDEXphase; unset in other phases or when progress is not available.
- delayed_reasonstringBeta
Reason the in-progress scaling change is delayed. When set,
estimated_completion_timestampis unset. Unset when the change is not delayed or no scaling change is in progress.CAPACITY_UNAVAILABLESCALE_DOWN_BLOCKEDTAKING_LONGER_THAN_EXPECTED
- target_qps_change_allowed_after_timestampint64Beta
Earliest time a new Target QPS change is accepted, in milliseconds since the Unix epoch. Set only while a scaling change is in progress, the change lock is on, and the endpoint has a recorded last throughput change; may be in the past once the lock has expired.
Get an endpoint GA
GET
Get details for a single AI Search endpoint.
API scopes: vector-search
Parameters
- namestringRequiredpath
Name of the endpoint
Response
Returns the Endpoint object.
List all endpoints GA
GET
List all AI Search endpoints in the workspace.
API scopes: vector-search
Parameters
- page_tokenstringquery
Token for pagination
Response
Returns a list of Endpoint objects.
Create an endpoint GA
POST
Create a new endpoint.
API scopes: vector-search
Request body
- namestringRequired
Name of the AI Search endpoint. The name must be unique within the workspace, have at most 50 characters, contain only lowercase letters, digits, hyphens, underscores and periods, and start and end with a letter or digit.
- endpoint_typestringRequired
Type of endpoint to create. STANDARD endpoints are optimized for low-latency queries and support Target QPS scaling. STORAGE_OPTIMIZED endpoints hold much larger indexes and index faster, with higher query latency. See https://docs.databricks.com/aws/en/ai-search/ai-search#endpoint-options.
STORAGE_OPTIMIZEDSTANDARD
- budget_policy_idstringPublic Preview
Budget policy to attribute the endpoint's usage to. If omitted, the default budget policy applies.
- target_qpsint64
Target queries per second (QPS) for the endpoint. Supported for STANDARD endpoints only. 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.
Response
Returns the Endpoint object.
Update the budget policy of an endpoint Public Preview
PATCH
Update the budget policy that the endpoint's usage is attributed to.
API scopes: vector-search
Parameters
- namestringRequiredpath
Name of the AI Search endpoint
Request body
- budget_policy_idstringRequired
The budget policy id to be applied
Response
- budget_policy_idstring
The requested budget policy ID, returned when the endpoint was already using it.
- effective_budget_policy_idstring
The budget policy applied to the AI Search endpoint.
Delete an endpoint GA
DELETE
Delete an AI Search endpoint.
API scopes: vector-search
Parameters
- namestringRequiredpath
Name of the AI Search endpoint
Update an endpoint Public Preview
PATCH
Update the Target QPS of a STANDARD endpoint. The response is the updated endpoint; its scaling_info shows whether the resulting scaling change is applied or still in progress.
API scopes: vector-search
Parameters
- namestringRequiredpath
Name of the AI Search endpoint
Request body
- target_qpsint64
Target QPS for the endpoint. Best-effort; the system does not guarantee this QPS will be achieved. Set to -1 to clear the Target QPS, as if it had never been set.
Response
Returns the Endpoint object.