ferruzzi commented on code in PR #38693:
URL: https://github.com/apache/airflow/pull/38693#discussion_r1554216885
##########
airflow/providers/amazon/aws/operators/bedrock.py:
##########
@@ -91,3 +96,155 @@ def execute(self, context: Context) -> dict[str, str | int]:
self.log.info("Bedrock %s prompt: %s", self.model_id, self.input_data)
self.log.info("Bedrock model response: %s", response_body)
return response_body
+
+
+class BedrockCustomizeModelOperator(AwsBaseOperator[BedrockHook]):
+ """
+ Create a fine-tuning job to customize a base model.
+
+ .. seealso::
+ For more information on how to use this operator, take a look at the
guide:
+ :ref:`howto/operator:BedrockCustomizeModelOperator`
+
+ :param job_name: A unique name for the fine-tuning job.
+ :param custom_model_name: A name for the custom model being created.
+ :param role_arn: The Amazon Resource Name (ARN) of an IAM role that Amazon
Bedrock can assume
+ to perform tasks on your behalf.
+ :param base_model_id: Name of the base model.
+ :param training_data_uri: The S3 URI where the training data is stored.
+ :param output_data_uri: The S3 URI where the output data is stored.
+ :param hyperparameters: Parameters related to tuning the model.
+ :param check_if_job_exists: If set to true, operator will check whether a
model customization
+ job already exists for the name in the config. (Default: True)
+ :param action_if_job_exists: Behavior if the job name already exists.
Options are "timestamp" (default),
Review Comment:
Alright, I decided to tweak this. Let's leave this comment open as a
failsafe against merging for now.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@airflow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
