serving_endpoints

Creates, updates, deletes, gets or lists a serving_endpoints resource.

Overview

Name	serving_endpoints
Type	Resource
Id	databricks_workspace.realtimeserving.serving_endpoints

Fields

The following fields are returned by SELECT queries:

get

Serving endpoint was retrieved successfully.

Name	Datatype	Description
id	string
name	string
config	object
creation_timestamp	integer
creator	string
last_updated_timestamp	integer
permission_level	string
route_optimized	boolean
state	object
tags	array

list

List of serving endpoints was retrieved successfully.

Name	Datatype	Description
id	string
name	string
ai_gateway	object
config	object
creation_timestamp	integer
creator	string
last_updated_timestamp	integer
state	object
tags	array
task	string

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get	select	deployment_name		Retrieves the details for a single serving endpoint.
list	select	deployment_name
create	insert	deployment_name
updateconfig	update	deployment_name		Updates any combination of the serving endpoint's served entities, the compute configuration of those served entities, and the endpoint's traffic config. An endpoint that already has an update in progress can not be updated until the current update completes or fails.
patch	update	deployment_name		Used to batch add and delete tags from a serving endpoint with a single API call.
put	replace	deployment_name		Used to update the rate limits of a serving endpoint. NOTE: Only foundation model endpoints are currently supported. For external models, use AI Gateway to manage rate limits.
delete	delete	deployment_name
query	exec	deployment_name

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
deployment_name	string	The Databricks Workspace Deployment Name (default: dbc-abcd0123-a1bc)

SELECT examples

get

Retrieves the details for a single serving endpoint.

SELECT
id,
name,
config,
creation_timestamp,
creator,
last_updated_timestamp,
permission_level,
route_optimized,
state,
tags
FROM databricks_workspace.realtimeserving.serving_endpoints
WHERE deployment_name = '{{ deployment_name }}' -- required;

list

List of serving endpoints was retrieved successfully.

SELECT
id,
name,
ai_gateway,
config,
creation_timestamp,
creator,
last_updated_timestamp,
state,
tags,
task
FROM databricks_workspace.realtimeserving.serving_endpoints
WHERE deployment_name = '{{ deployment_name }}' -- required;

INSERT examples

create

No description available.

INSERT INTO databricks_workspace.realtimeserving.serving_endpoints (
data__name,
data__route_optimized,
data__config,
data__tags,
data__rate_limits,
data__ai_gateway,
deployment_name
)
SELECT 
'{{ name }}',
'{{ route_optimized }}',
'{{ config }}',
'{{ tags }}',
'{{ rate_limits }}',
'{{ ai_gateway }}',
'{{ deployment_name }}'
RETURNING
id,
name,
ai_gateway,
config,
creation_timestamp,
creator,
last_updated_timestamp,
permission_level,
route_optimized,
state,
tags
;

Manifest

# Description fields are for documentation purposes
- name: serving_endpoints
  props:
    - name: deployment_name
      value: string
      description: Required parameter for the serving_endpoints resource.
    - name: name
      value: required
    - name: route_optimized
      value: string
    - name: config
      value: required
    - name: tags
      value: object
    - name: rate_limits
      value: Array of object
    - name: ai_gateway
      value: Array of object

UPDATE examples

updateconfig

Updates any combination of the serving endpoint's served entities, the compute configuration of those served entities, and the endpoint's traffic config. An endpoint that already has an update in progress can not be updated until the current update completes or fails.

UPDATE databricks_workspace.realtimeserving.serving_endpoints
SET 
data__served_entities = '{{ served_entities }}',
data__served_models = '{{ served_models }}',
data__traffic_config = '{{ traffic_config }}',
data__auto_capture_config = '{{ auto_capture_config }}'
WHERE 
deployment_name = '{{ deployment_name }}' --required
RETURNING
id,
name,
config,
creation_timestamp,
creator,
last_updated_timestamp,
permission_level,
route_optimized,
state;

patch

Used to batch add and delete tags from a serving endpoint with a single API call.

UPDATE databricks_workspace.realtimeserving.serving_endpoints
SET 
data__delete_tags = '{{ delete_tags }}',
data__add_tags = '{{ add_tags }}'
WHERE 
deployment_name = '{{ deployment_name }}' --required
RETURNING
key,
value;

REPLACE examples

put

Used to update the rate limits of a serving endpoint. NOTE: Only foundation model endpoints are currently supported. For external models, use AI Gateway to manage rate limits.

REPLACE databricks_workspace.realtimeserving.serving_endpoints
SET 
data__rate_limits = '{{ rate_limits }}'
WHERE 
deployment_name = '{{ deployment_name }}' --required
RETURNING
rate_limits;

DELETE examples

delete

No description available.

DELETE FROM databricks_workspace.realtimeserving.serving_endpoints
WHERE deployment_name = '{{ deployment_name }}' --required;

Lifecycle Methods

query

Serving endpoint was queried successfully and returned predictions.

EXEC databricks_workspace.realtimeserving.serving_endpoints.query 
@deployment_name='{{ deployment_name }}' --required 
@@json=
'{
"prompt": "{{ prompt }}", 
"input": "{{ input }}", 
"temperature": "{{ temperature }}", 
"stop": "{{ stop }}", 
"max_tokens": {{ max_tokens }}, 
"n": {{ n }}, 
"stream": {{ stream }}, 
"dataframe_records": "{{ dataframe_records }}", 
"instances": "{{ instances }}", 
"inputs": "{{ inputs }}", 
"messages": "{{ messages }}", 
"extra_params": "{{ extra_params }}", 
"dataframe_split": "{{ dataframe_split }}"
}';