serving_endpoints_pt

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

Overview

Name	serving_endpoints_pt
Type	Resource
Id	databricks_workspace.serving.serving_endpoints_pt

Fields

The following fields are returned by SELECT queries:

SELECT not supported for this resource, use SHOW METHODS to view available operations for the resource.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
create	insert	deployment_name, name, config		Create a new PT serving endpoint.
update_config	replace	name, deployment_name, config		Updates any combination of the pt endpoint's served entities, the compute configuration of those

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)
name	string	The name of the pt endpoint to update. This field is required.

INSERT examples

create

Create a new PT serving endpoint.

INSERT INTO databricks_workspace.serving.serving_endpoints_pt (
name,
config,
ai_gateway,
budget_policy_id,
email_notifications,
tags,
deployment_name
)
SELECT 
'{{ name }}' /* required */,
'{{ config }}' /* required */,
'{{ ai_gateway }}',
'{{ budget_policy_id }}',
'{{ email_notifications }}',
'{{ tags }}',
'{{ deployment_name }}'
RETURNING
id,
name,
budget_policy_id,
ai_gateway,
config,
creation_timestamp,
creator,
data_plane_info,
description,
email_notifications,
endpoint_url,
last_updated_timestamp,
pending_config,
permission_level,
route_optimized,
state,
tags,
task
;

Manifest

# Description fields are for documentation purposes
- name: serving_endpoints_pt
props:
  - name: deployment_name
    value: "{{ deployment_name }}"
    description: Required parameter for the serving_endpoints_pt resource.
  - name: name
    value: "{{ name }}"
    description: |
      The name of the serving endpoint. This field is required and must be unique across a Databricks workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores.
  - name: config
    description: |
      The core config of the serving endpoint.
    value:
      served_entities:
        - entity_name: "{{ entity_name }}"
          provisioned_model_units: {{ provisioned_model_units }}
          burst_scaling_enabled: {{ burst_scaling_enabled }}
          entity_version: "{{ entity_version }}"
          name: "{{ name }}"
      traffic_config:
        routes:
          - traffic_percentage: {{ traffic_percentage }}
            served_entity_name: "{{ served_entity_name }}"
            served_model_name: "{{ served_model_name }}"
  - name: ai_gateway
    description: |
      The AI Gateway configuration for the serving endpoint.
    value:
      fallback_config:
        enabled: {{ enabled }}
      guardrails:
        input:
          invalid_keywords:
            - "{{ invalid_keywords }}"
          pii:
            behavior: "{{ behavior }}"
          safety: {{ safety }}
          valid_topics:
            - "{{ valid_topics }}"
        output:
          invalid_keywords:
            - "{{ invalid_keywords }}"
          pii:
            behavior: "{{ behavior }}"
          safety: {{ safety }}
          valid_topics:
            - "{{ valid_topics }}"
      inference_table_config:
        catalog_name: "{{ catalog_name }}"
        enabled: {{ enabled }}
        schema_name: "{{ schema_name }}"
        table_name_prefix: "{{ table_name_prefix }}"
      rate_limits:
        - renewal_period: "{{ renewal_period }}"
          calls: {{ calls }}
          key: "{{ key }}"
          principal: "{{ principal }}"
          tokens: {{ tokens }}
      usage_tracking_config:
        enabled: {{ enabled }}
  - name: budget_policy_id
    value: "{{ budget_policy_id }}"
    description: |
      The budget policy associated with the endpoint.
  - name: email_notifications
    description: |
      Email notification settings.
    value:
      on_update_failure:
        - "{{ on_update_failure }}"
      on_update_success:
        - "{{ on_update_success }}"
  - name: tags
    description: |
      Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    value:
      - key: "{{ key }}"
        value: "{{ value }}"

REPLACE examples

update_config

Updates any combination of the pt endpoint's served entities, the compute configuration of those

REPLACE databricks_workspace.serving.serving_endpoints_pt
SET 
config = '{{ config }}'
WHERE 
name = '{{ name }}' --required
AND deployment_name = '{{ deployment_name }}' --required
AND config = '{{ config }}' --required
RETURNING
id,
name,
budget_policy_id,
ai_gateway,
config,
creation_timestamp,
creator,
data_plane_info,
description,
email_notifications,
endpoint_url,
last_updated_timestamp,
pending_config,
permission_level,
route_optimized,
state,
tags,
task;