serving_endpoints

Operations on a serving_endpoints resource.

Overview

Name	serving_endpoints
Type	Resource
Id	databricks_workspace.realtimeserving.serving_endpoints

Fields

Name	Datatype
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

Methods

Name	Accessible by	Required Params	Description
get	SELECT	name, deployment_name	Retrieves the details for a single serving endpoint.
list	SELECT	deployment_name
create	INSERT	deployment_name
delete	DELETE	name, deployment_name
patch	UPDATE	name, deployment_name	Used to batch add and delete tags from a serving endpoint with a single API call.
updateconfig	UPDATE	name, 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.
put	REPLACE	name, 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.
query	EXEC	name, deployment_name

SELECT examples

serving_endpoints (list)

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 }}';

serving_endpoints (get)

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

INSERT example

Use the following StackQL query and manifest file to create a new serving_endpoints resource.

serving_endpoints

/*+ create */
INSERT INTO databricks_workspace.realtimeserving.serving_endpoints (
deployment_name,
data__name,
data__config,
data__ai_gateway,
data__tags
)
SELECT 
'{{ deployment_name }}',
'{{ name }}',
'{{ config }}',
'{{ ai_gateway }}',
'{{ tags }}'
;

Manifest

- name: your_resource_model_name
  props:
  - name: name
    value: openai_endpoint
  - name: config
    value:
      served_entities:
      - name: openai_embeddings
        external_model:
          name: text-embedding-ada-002
          provider: openai
          task: llm/v1/embeddings
          openai_config:
            openai_api_key: '{{secrets/my_scope/my_openai_api_key}}'
  - name: ai_gateway
    value:
      usage_tracking_config:
        enabled: true
      inference_table_config:
        catalog_name: my-catalog
        schema_name: my-schema
        table_name_prefix: my-prefix
        enabled: true
      rate_limits:
      - calls: 100
        key: user
        renewal_period: minute
      guardrails:
        input:
          safety: true
          pii:
            behavior: BLOCK
          valid_topics:
          - topic1
          - topic2
          invalid_keywords:
          - keyword1
          - keyword2
        output:
          safety: true
          pii:
            behavior: BLOCK
          valid_topics:
          - topic1
          - topic2
          invalid_keywords:
          - keyword1
          - keyword2
  - name: tags
    value:
    - key: team
      value: gen-ai

UPDATE example

Updates a serving_endpoints resource.

patch

/*+ update */
-- replace field1, field2, etc. with the fields you want to update        
UPDATE databricks_workspace.realtimeserving.serving_endpoints
SET field1 = '{{ value1 }}',
field2 = '{{ value2 }}', ...
WHERE name = '{{ name }}' AND
deployment_name = '{{ deployment_name }}';

updateconfig

/*+ update */
-- replace field1, field2, etc. with the fields you want to update        
UPDATE databricks_workspace.realtimeserving.serving_endpoints
SET field1 = '{{ value1 }}',
field2 = '{{ value2 }}', ...
WHERE name = '{{ name }}' AND
deployment_name = '{{ deployment_name }}';

REPLACE example

Replaces a serving_endpoints resource.

/*+ update */
-- replace field1, field2, etc. with the fields you want to update
REPLACE databricks_workspace.realtimeserving.serving_endpoints
SET field1 = '{ value1 }',
field2 = '{ value2 }', ...
WHERE name = '{{ name }}' AND
deployment_name = '{{ deployment_name }}';

DELETE example

Deletes a serving_endpoints resource.

/*+ delete */
DELETE FROM databricks_workspace.realtimeserving.serving_endpoints
WHERE name = '{{ name }}' AND
deployment_name = '{{ deployment_name }}';