serving-endpoints command group
Databricks CLI use is subject to the Databricks License and Databricks Privacy Notice, including any Usage Data provisions.
The serving-endpoints command group within the Databricks CLI allows you to create, update, and delete model serving endpoints. See Manage model serving endpoints.
databricks serving-endpoints build-logs
Retrieve the build logs associated with the provided served model.
databricks serving-endpoints build-logs NAME SERVED_MODEL_NAME [flags]
Arguments
NAME
The name of the serving endpoint that the served model belongs to. This field is required.
SERVED_MODEL_NAME
The name of the served model that build logs will be retrieved for. This field is required.
Options
databricks serving-endpoints create
Create a new serving endpoint.
databricks serving-endpoints create NAME [flags]
Arguments
NAME
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.
Options
--budget-policy-id string
The budget policy to be applied to the serving endpoint.
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
--no-wait
do not wait to reach NOT_UPDATING state
--route-optimized
Enable route optimization for the serving endpoint.
--timeout duration
maximum amount of time to reach NOT_UPDATING state (default 20m0s)
databricks serving-endpoints create-provisioned-throughput-endpoint
Create a new provisioned throughput serving endpoint.
databricks serving-endpoints create-provisioned-throughput-endpoint [flags]
Options
--budget-policy-id string
The budget policy associated with the endpoint.
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
--no-wait
Do not wait to reach NOT_UPDATING state.
--timeout duration
Maximum amount of time to reach NOT_UPDATING state (default 20m0s).
Examples
The following example creates a provisioned throughput endpoint:
databricks serving-endpoints create-provisioned-throughput-endpoint --json @endpoint-config.json
databricks serving-endpoints delete
Delete a serving endpoint.
databricks serving-endpoints delete NAME [flags]
Arguments
NAME
The name of the serving endpoint to delete.
Options
databricks serving-endpoints export-metrics
Retrieve the metrics associated with the provided serving endpoint in either Prometheus or OpenMetrics exposition format.
databricks serving-endpoints export-metrics NAME [flags]
Arguments
NAME
The name of the serving endpoint to retrieve metrics for. This field is required.
Options
databricks serving-endpoints get
Retrieve the details for a single serving endpoint.
databricks serving-endpoints get NAME [flags]
Arguments
NAME
The name of the serving endpoint. This field is required.
Options
databricks serving-endpoints get-open-api
Get the query schema of the serving endpoint in OpenAPI format. The schema contains information for the supported paths, input and output format and datatypes.
databricks serving-endpoints get-open-api NAME [flags]
Arguments
NAME
The name of the serving endpoint that the served model belongs to. This field is required.
Options
databricks serving-endpoints list
Get all serving endpoints.
databricks serving-endpoints list [flags]
Arguments
None
Options
databricks serving-endpoints logs
Retrieve the service logs associated with the provided served model.
databricks serving-endpoints logs NAME SERVED_MODEL_NAME [flags]
Arguments
NAME
The name of the serving endpoint that the served model belongs to. This field is required.
SERVED_MODEL_NAME
The name of the served model that logs will be retrieved for. This field is required.
Options
databricks serving-endpoints patch
Add or delete tags of a serving endpoint.
databricks serving-endpoints patch NAME [flags]
Arguments
NAME
The name of the serving endpoint who's tags to patch. This field is required.
Options
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
databricks serving-endpoints put
Deprecated. Use AI Gateway to manage rate limits instead.
Update rate limits of a serving endpoint.
databricks serving-endpoints put NAME [flags]
Arguments
NAME
The name of the serving endpoint whose rate limits are being updated. This field is required.
Options
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
databricks serving-endpoints put-ai-gateway
Update the AI Gateway of a serving endpoint. External model, provisioned throughput, and pay-per-token endpoints are fully supported; agent endpoints currently only support inference tables.
databricks serving-endpoints put-ai-gateway NAME [flags]
Arguments
NAME
The name of the serving endpoint whose AI Gateway is being updated. This field is required.
Options
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
databricks serving-endpoints query
Query a serving endpoint.
databricks serving-endpoints query NAME [flags]
Arguments
NAME
The name of the serving endpoint. This field is required.
Options
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
--max-tokens int
The max tokens field used ONLY for completions and chat external & foundation model serving endpoints.
--n int
The n (number of candidates) field used ONLY for completions and chat external & foundation model serving endpoints.
--stream
The stream field used ONLY for completions and chat external & foundation model serving endpoints.
--temperature float
The temperature field used ONLY for completions and chat external & foundation model serving endpoints.
databricks serving-endpoints update-config
Update 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.
databricks serving-endpoints update-config NAME [flags]
Arguments
NAME
The name of the serving endpoint to update. This field is required.
Options
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
--no-wait
do not wait to reach NOT_UPDATING state
--timeout duration
maximum amount of time to reach NOT_UPDATING state (default 20m0s)
databricks serving-endpoints update-notifications
Update the email and webhook notification settings for a serving endpoint.
databricks serving-endpoints update-notifications NAME [flags]
Arguments
NAME
The name of the serving endpoint whose notifications are being updated.
Options
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
Examples
The following example updates notification settings for an endpoint:
databricks serving-endpoints update-notifications my-endpoint --json '{"email_notifications": {"on_failure": ["user@example.com"]}}'
databricks serving-endpoints update-provisioned-throughput-endpoint-config
Update the config of a provisioned throughput serving endpoint. Updates are instantaneous.
databricks serving-endpoints update-provisioned-throughput-endpoint-config NAME [flags]
Arguments
NAME
The name of the provisioned throughput endpoint to update.
Options
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
--no-wait
Do not wait to reach NOT_UPDATING state.
--timeout duration
Maximum amount of time to reach NOT_UPDATING state (default 20m0s).
Examples
The following example updates the config of a provisioned throughput endpoint:
databricks serving-endpoints update-provisioned-throughput-endpoint-config my-pt-endpoint --json @updated-config.json
databricks serving-endpoints get-permission-levels
Get serving endpoint permission levels.
databricks serving-endpoints get-permission-levels SERVING_ENDPOINT_ID [flags]
Arguments
SERVING_ENDPOINT_ID
The serving endpoint for which to get or manage permissions.
Options
databricks serving-endpoints get-permissions
Get serving endpoint permissions.
Gets the permissions of a serving endpoint. Serving endpoints can inherit permissions from their root object.
databricks serving-endpoints get-permissions SERVING_ENDPOINT_ID [flags]
Arguments
SERVING_ENDPOINT_ID
The serving endpoint for which to get or manage permissions.
Options
databricks serving-endpoints set-permissions
Set serving endpoint permissions.
databricks serving-endpoints set-permissions SERVING_ENDPOINT_ID [flags]
Arguments
SERVING_ENDPOINT_ID
The serving endpoint for which to get or manage permissions.
Options
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
databricks serving-endpoints update-permissions
Update the permissions on a serving endpoint. Serving endpoints can inherit permissions from their root object.
databricks serving-endpoints update-permissions SERVING_ENDPOINT_ID [flags]
Arguments
SERVING_ENDPOINT_ID
The serving endpoint for which to get or manage permissions.
Options
--json JSON
The inline JSON string or the @path to the JSON file with the request body.
Global flags
--debug
Whether to enable debug logging.
-h or --help
Display help for the Databricks CLI or the related command group or the related command.
--log-file string
A string representing the file to write output logs to. If this flag is not specified then the default is to write output logs to stderr.
--log-format format
The log format type, text or json. The default value is text.
--log-level string
A string representing the log format level. If not specified then the log format level is disabled.
-o, --output type
The command output type, text or json. The default value is text.
-p, --profile string
The name of the profile in the ~/.databrickscfg file to use to run the command. If this flag is not specified then if it exists, the profile named DEFAULT is used.
--progress-format format
The format to display progress logs: default, append, inplace, or json
-t, --target string
If applicable, the bundle target to use