google-cloud-pipeline-components 2.14.0__py3-none-any.whl → 2.15.0__py3-none-any.whl

google_cloud_pipeline_components/_implementation/llm/deployment_graph.py

@@ -37,8 +37,10 @@ def pipeline(
     policy_model_reference: str,
     model_display_name: Optional[str] = None,
     deploy_model: bool = True,
+    upload_model: bool = True,
     encryption_spec_key_name: str = '',
     upload_location: str = _placeholders.LOCATION_PLACEHOLDER,
+    regional_endpoint: str = '',
 ) -> PipelineOutput:
   # fmt: off
   """Uploads a tuned language model and (optionally) deploys it to an endpoint.
@@ -51,50 +53,32 @@ def pipeline(
     deploy_model: Whether to deploy the model to an endpoint in `us-central1`. Default is True.
     encryption_spec_key_name: Customer-managed encryption key. If this is set, then all resources created by the CustomJob will be encrypted with the provided encryption key. Note that this is not supported for TPU at the moment.
     upload_location: Region to upload and deploy the model to. Default is the location used to run the pipeline components.
+    regional_endpoint: Regional endpoint to upload the model.
 
   Returns:
     model_resource_name: Path to the model uploaded to the Model Registry. This will be an empty string if the model was not deployed.
     endpoint_resource_name: Path the Online Prediction Endpoint. This will be an empty string if the model was not deployed.
   """
   # fmt: on
-  regional_endpoint = function_based.resolve_regional_endpoint(
-      upload_location=upload_location
-  ).set_display_name('Resolve Regional Endpoint')
-
-  display_name = (
-      function_based.resolve_model_display_name(
-          large_model_reference=large_model_reference,
-          model_display_name=model_display_name,
-      )
-      .set_caching_options(False)
-      .set_display_name('Resolve Model Display Name')
-  )
-
-  upload_model = function_based.resolve_upload_model(
-      large_model_reference=policy_model_reference,
-  ).set_display_name('Resolve Upload Model')
   upload_task = upload_llm_model.refined_upload_llm_model(
       project=_placeholders.PROJECT_ID_PLACEHOLDER,
       location=upload_location,
-      regional_endpoint=regional_endpoint.output,
+      regional_endpoint=regional_endpoint,
       artifact_uri=output_adapter_path,
-      model_display_name=display_name.output,
+      model_display_name=model_display_name,
       model_reference_name=large_model_reference,
-      upload_model=upload_model.output,
+      upload_model=upload_model,
       encryption_spec_key_name=encryption_spec_key_name,
       tune_type='rlhf',
   ).set_display_name('Upload Model')
-  deploy_model = function_based.resolve_deploy_model(
-      deploy_model=deploy_model,
-      large_model_reference=policy_model_reference,
-  ).set_display_name('Resolve Deploy Model')
+
   deploy_task = deploy_llm_model.deploy_llm_model(
       project=_placeholders.PROJECT_ID_PLACEHOLDER,
       location=upload_location,
       model_resource_name=upload_task.outputs['model_resource_name'],
-      display_name=display_name.output,
-      regional_endpoint=regional_endpoint.output,
-      deploy_model=deploy_model.output,
+      display_name=model_display_name,
+      regional_endpoint=regional_endpoint,
+      deploy_model=deploy_model,
       encryption_spec_key_name=encryption_spec_key_name,
   ).set_display_name('Deploy Model')
   return PipelineOutput(

google_cloud_pipeline_components/_implementation/llm/generated/refined_image_versions.py

@@ -17,4 +17,4 @@
 DO NOT EDIT - This file is generated, manual changes will be overridden.
 """
 
-IMAGE_TAG = '20240425_1027_RC00'
+IMAGE_TAG = '20240623_1707'

google_cloud_pipeline_components/_implementation/llm/infer_preprocessor.py

@@ -0,0 +1,109 @@
+# Copyright 2024 The Kubeflow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Component that preprocesses inputs for infer pipeline."""
+
+from google_cloud_pipeline_components import _placeholders
+from google_cloud_pipeline_components import utils as gcpc_utils
+from google_cloud_pipeline_components._implementation.llm import utils
+from kfp import dsl
+
+
+@dsl.container_component
+def infer_preprocessor(
+    large_model_reference: str,
+    accelerator_type: str,
+    use_test_spec: bool,
+    project: str,
+    location: str,
+    artifact_registry: str,
+    tag: str,
+    gcp_resources: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_large_model_reference: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_reference_model_path: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_reward_model_reference: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_reward_model_path: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_machine_type: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_tuning_location: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_accelerator_type: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_accelerator_count: dsl.OutputPath(int),  # pytype: disable=invalid-annotation
+    metadata_instruction: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_refined_image_uri: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    use_experimental_image: bool = False,
+    input_reference_model_path: str = '',
+    instruction: str = '',
+    image_uri: str = utils.get_default_image_uri('refined_cpu', ''),
+) -> dsl.ContainerSpec:  # pylint: disable=g-doc-args
+  # fmt: off
+  """Preprocess infer pipeline inputs.
+
+  Args:
+    large_model_reference: The model for fine tuning.
+    accelerator_type: Specific accelerator type for the job.
+    use_test_spec: Whether to use a lower resource machine for testing.
+    project: Project that contains the artifact registry.
+    location: Region that contains the artifact registry.
+    artifact_registry: Registry that contains Docker images.
+    tag: Image tag.
+    use_experimental_image:  Whether to use refined experimental image.
+    input_reference_model_path: The model checkpoint path for the reference model
+    instruction: The instruction to let the model know what task it needs to perform.
+    image_uri: Docker image URI to use for the custom job.
+
+  Returns:
+    gcp_resources: GCP resources that can be used to track the custom job.
+    metadata_large_model_reference: The base model for fine tuning. The name should be in capitalized snake case format.
+    metadata_reference_model_path: The model checkpoint path for the reinforcer model
+    metadata_reward_model_reference:  The base model for training reward model. The name should be in capitalized snake case format.
+    metadata_reward_model_path: The model checkpoint path for the reward model.
+    metadata_machine_type: The type of the machine to provision for the custom job.
+    metadata_tuning_location: The GCP region to run the custom job.
+    metadata_accelerator_type: Specific accelerator type for the custom job.
+    metadata_accelerator_count: The number of accelerator.
+    metadata_instruction: The instruction to let the model know what task it needs to perform.
+    metadata_refined_image_uri: Docker image URI to use for the custom job.
+  """
+  # fmt: on
+  return gcpc_utils.build_serverless_customjob_container_spec(
+      project=_placeholders.PROJECT_ID_PLACEHOLDER,
+      location=_placeholders.LOCATION_PLACEHOLDER,
+      custom_job_payload=utils.build_payload(
+          display_name='infer_preprocessor',
+          machine_type='n1-standard-4',
+          image_uri=image_uri,
+          args=[
+              '--app_name=infer_preprocessor',
+              f'--large_model_reference={large_model_reference}',
+              f'--input_reference_model_path={input_reference_model_path}',
+              f'--accelerator_type={accelerator_type}',
+              f'--use_test_spec={use_test_spec}',
+              f'--project={project}',
+              f'--location={location}',
+              f'--artifact_registry={artifact_registry}',
+              f'--tag={tag}',
+              f'--use_experimental_image={use_experimental_image}',
+              f'--instruction={instruction}',
+              f'--metadata_large_model_reference_path={metadata_large_model_reference}',
+              f'--metadata_reference_model_path_path={metadata_reference_model_path}',
+              f'--metadata_reward_model_reference_path={metadata_reward_model_reference}',
+              f'--metadata_reward_model_path_path={metadata_reward_model_path}',
+              f'--metadata_machine_type_path={metadata_machine_type}',
+              f'--metadata_tuning_location_path={metadata_tuning_location}',
+              f'--metadata_accelerator_type_path={metadata_accelerator_type}',
+              f'--metadata_accelerator_count_path={metadata_accelerator_count}',
+              f'--metadata_instruction_path={metadata_instruction}',
+              f'--metadata_refined_image_uri_path={metadata_refined_image_uri}',
+          ],
+      ),
+      gcp_resources=gcp_resources,
+  )

google_cloud_pipeline_components/_implementation/llm/online_evaluation_pairwise.py

@@ -52,6 +52,7 @@ def online_evaluation_pairwise(
     project: str = _placeholders.PROJECT_ID_PLACEHOLDER,
     location: str = _placeholders.LOCATION_PLACEHOLDER,
     encryption_spec_key_name: str = '',
+    autorater_prompt_parameters: Dict[str, Dict[str, str]] = {},
 ) -> dsl.ContainerSpec:  # pylint: disable=g-doc-args
   """Evaluate two models using an autorater.
 
@@ -73,6 +74,8 @@ def online_evaluation_pairwise(
     encryption_spec_key_name: Customer-managed encryption key options. If this
       is set, then all resources created by the component will be encrypted with
       the provided encryption key.
+    autorater_prompt_parameters: Map of autorater prompt template parameters to
+      columns or templates.
 
   Returns:
     judgments: Individual judgments used to calculate the win rates.
@@ -112,6 +115,11 @@ def online_evaluation_pairwise(
               '--executor_input={{$.json_escape[1]}}',
               f'--kms_key_name={encryption_spec_key_name}',
               f'--metadata_path={metadata}',
+              (
+                  '--autorater_prompt_parameters='
+                  "{{$.inputs.parameters['autorater_prompt_parameters']"
+                  '.json_escape[0]}}'
+              ),
           ],
           encryption_spec_key_name=encryption_spec_key_name,
       ),

google_cloud_pipeline_components/_implementation/llm/reward_model_graph.py

@@ -21,6 +21,7 @@ from google_cloud_pipeline_components._implementation.llm import function_based
 from google_cloud_pipeline_components._implementation.llm import preprocess_chat_dataset
 from google_cloud_pipeline_components._implementation.llm import private_text_comparison_importer
 from google_cloud_pipeline_components._implementation.llm import reward_model_trainer
+from google_cloud_pipeline_components._implementation.llm import rlhf_preprocessor
 from google_cloud_pipeline_components._implementation.llm import upload_tensorboard_metrics
 import kfp
 
@@ -45,6 +46,7 @@ def pipeline(
     accelerator_type: str,
     accelerator_count: int,
     reward_model_image_uri: str,
+    comma_separated_candidates_field_names: str,
     prompt_sequence_length: int = 512,
     target_sequence_length: int = 64,
     batch_size: int = 64,
@@ -72,6 +74,7 @@ def pipeline(
     accelerator_type: Specific accelerator type for the custom job.
     accelerator_count: The number of accelerator.
     reward_model_image_uri: Docker image URI to use for the reward model training job.
+    comma_separated_candidates_field_names: Comma separated list of fields that contain candidate text, e.g. ``'field_1,field_2,field_3'``.
     prompt_sequence_length: Maximum tokenized sequence length for input text. Higher values increase memory overhead. This value should be at most 8192. Default value is 512.
     target_sequence_length:  Maximum tokenized sequence length for target text. Higher values increase memory overhead. This value should be at most 1024. Default value is 64.
     batch_size: Number of examples in each finetuning step. Default is 64.
@@ -91,7 +94,6 @@ def pipeline(
   """
   # fmt: on
   prompt_column = 'input_text'
-  candidate_columns = ['candidate_0', 'candidate_1']
   choice_column = 'choice'
 
   processed_preference_dataset = (
@@ -103,9 +105,6 @@ def pipeline(
       ).set_display_name('Preprocess Prompt Dataset')
   )
 
-  comma_separated_candidates_field_names = (
-      function_based.convert_to_delimited_string(items=candidate_columns)
-  )
   preference_dataset_importer = (
       private_text_comparison_importer.private_text_comparison_importer(
           project=project,
@@ -114,7 +113,7 @@ def pipeline(
               'processed_dataset_uri'
           ],
           inputs_field_name=prompt_column,
-          comma_separated_candidates_field_names=comma_separated_candidates_field_names.output,
+          comma_separated_candidates_field_names=comma_separated_candidates_field_names,
           choice_field_name=choice_column,
           split=env.TRAIN_SPLIT,
           large_model_reference=reward_model_reference,
@@ -131,7 +130,7 @@ def pipeline(
           location=location,
           input_text=eval_dataset,
           inputs_field_name=prompt_column,
-          comma_separated_candidates_field_names=comma_separated_candidates_field_names.output,
+          comma_separated_candidates_field_names=comma_separated_candidates_field_names,
           choice_field_name=choice_column,
           split=env.TRAIN_SPLIT,
           large_model_reference=reward_model_reference,

google_cloud_pipeline_components/_implementation/llm/rlhf_preprocessor.py

@@ -14,6 +14,7 @@
 """Component that preprocesses inputs for Reinforcement Learning from Human Feedback (RLHF)."""
 
 import os
+from typing import List
 
 from google_cloud_pipeline_components import _placeholders
 from google_cloud_pipeline_components import utils as gcpc_utils
@@ -33,6 +34,7 @@ def rlhf_preprocessor(
     gcp_resources: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
     has_tensorboard_id: dsl.OutputPath(bool),  # pytype: disable=invalid-annotation
     has_inference_dataset: dsl.OutputPath(bool),  # pytype: disable=invalid-annotation
+    metadata_candidate_columns_string: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
     metadata_large_model_reference: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
     metadata_reference_model_path: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
     metadata_reward_model_reference: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
@@ -43,11 +45,18 @@ def rlhf_preprocessor(
     metadata_accelerator_count: dsl.OutputPath(int),  # pytype: disable=invalid-annotation
     metadata_refined_image_uri: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
     metadata_num_microbatches: dsl.OutputPath(int),  # pytype: disable=invalid-annotation
+    metadata_upload_location: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_deploy_model: dsl.OutputPath(bool),  # pytype: disable=invalid-annotation
+    metadata_model_display_name: dsl.OutputPath(str),  # pytype: disable=invalid-annotation
+    metadata_upload_model: dsl.OutputPath(bool),  # pytype: disable=invalid-annotation
     use_experimental_image: bool = False,
     evaluation_dataset: str = '',
     tensorboard_resource_id: str = '',
     input_reference_model_path: str = '',
     image_uri: str = utils.get_default_image_uri('refined_cpu', ''),
+    upload_location: str = '',
+    model_display_name: str = '',
+    deploy_model: bool = True,
 ) -> dsl.ContainerSpec:  # pylint: disable=g-doc-args
   # fmt: off
   """Preprocess RLHF pipeline inputs.
@@ -68,6 +77,9 @@ def rlhf_preprocessor(
     metadata_reward_model_reference:  The base model for training reward model. The name should be in capitalized snake case format.
     metadata_reward_model_path: The model checkpoint path for the reward model.
     image_uri: Docker image URI to use for the custom job.
+    upload_location: Region where the model will be uploaded.
+    model_display_name: Display name of the model.
+    deploy_model: Whether to deploy the model.
 
   Returns:
     gcp_resources: GCP resources that can be used to track the custom job.
@@ -80,6 +92,10 @@ def rlhf_preprocessor(
     metadata_refined_image_uri: Docker image URI to use for the custom job.
     metadata_num_microbatches: Number of microbatches to break the total batch
       size into during training.
+    metadata_upload_location: Regional endpoint.
+    metadata_deploy_model: Whether to deploy the model.
+    metadata_model_display_name: Display name of the model.
+    metadata_upload_model: Whether to upload the model.
   """
   # fmt: on
   return gcpc_utils.build_serverless_customjob_container_spec(
@@ -102,8 +118,12 @@ def rlhf_preprocessor(
               f'--artifact_registry={artifact_registry}',
               f'--tag={tag}',
               f'--use_experimental_image={use_experimental_image}',
+              f'--upload_location={upload_location}',
+              f'--deploy_model={deploy_model}',
+              f'--model_display_name={model_display_name}',
               f'--has_tensorboard_id_path={has_tensorboard_id}',
               f'--has_inference_dataset_path={has_inference_dataset}',
+              f'--metadata_candidate_columns_string_path={metadata_candidate_columns_string}',
               f'--metadata_large_model_reference_path={metadata_large_model_reference}',
               f'--metadata_reference_model_path_path={metadata_reference_model_path}',
               f'--metadata_reward_model_reference_path={metadata_reward_model_reference}',
@@ -114,6 +134,10 @@ def rlhf_preprocessor(
               f'--metadata_accelerator_count_path={metadata_accelerator_count}',
               f'--metadata_refined_image_uri_path={metadata_refined_image_uri}',
               f'--metadata_num_microbatches_path={metadata_num_microbatches}',
+              f'--metadata_upload_location_path={metadata_upload_location}',
+              f'--metadata_deploy_model_path={metadata_deploy_model}',
+              f'--metadata_model_display_name_path={metadata_model_display_name}',
+              f'--metadata_upload_model_path={metadata_upload_model}',
           ],
       ),
       gcp_resources=gcp_resources,

google_cloud_pipeline_components/_implementation/model_evaluation/__init__.py

@@ -25,27 +25,18 @@ from google_cloud_pipeline_components._implementation.model_evaluation.feature_a
 from google_cloud_pipeline_components._implementation.model_evaluation.feature_attribution.feature_attribution_graph_component import feature_attribution_graph_component as FeatureAttributionGraphComponentOp
 from google_cloud_pipeline_components._implementation.model_evaluation.feature_extractor.component import feature_extractor_error_analysis as FeatureExtractorOp
 from google_cloud_pipeline_components._implementation.model_evaluation.import_evaluated_annotation.component import evaluated_annotation_import as ModelImportEvaluatedAnnotationOp
-from google_cloud_pipeline_components._implementation.model_evaluation.import_evaluation.component import model_evaluation_import as ModelImportEvaluationOp
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_classification_postprocessor.component import llm_classification_predictions_postprocessor_graph_component as LLMEvaluationClassificationPredictionsPostprocessorOp
-from google_cloud_pipeline_components._implementation.model_evaluation.llm_embedding.evaluation_llm_embedding_pipeline import evaluation_llm_embedding_pipeline
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_embedding_retrieval.component import llm_embedding_retrieval as LLMEmbeddingRetrievalOp
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_evaluation.component import model_evaluation_text_generation as LLMEvaluationTextGenerationOp
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_evaluation_preprocessor.component import llm_evaluation_dataset_preprocessor_graph_component as LLMEvaluationPreprocessorOp
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_information_retrieval_preprocessor.component import llm_information_retrieval_preprocessor as LLMInformationRetrievalPreprocessorOp
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_retrieval_metrics.component import llm_retrieval_metrics as LLMRetrievalMetricsOp
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_safety_bias.component import llm_safety_bias_metrics as LLMSafetyBiasMetricsOp
-from google_cloud_pipeline_components._implementation.model_evaluation.llm_safety_bias.evaluation_llm_safety_bias_pipeline import evaluation_llm_safety_bias_pipeline
-from google_cloud_pipeline_components._implementation.model_evaluation.model_inference.component import model_inference_and_evaluation_component
-from google_cloud_pipeline_components._implementation.model_evaluation.model_inference.component import model_inference_component
 from google_cloud_pipeline_components._implementation.model_evaluation.model_name_preprocessor.component import model_name_preprocessor as ModelNamePreprocessorOp
 from google_cloud_pipeline_components._implementation.model_evaluation.target_field_data_remover.component import target_field_data_remover as TargetFieldDataRemoverOp
-from google_cloud_pipeline_components._implementation.model_evaluation.text2sql.evaluation_llm_text2sql_pipeline import evaluation_llm_text2sql_pipeline
 
 
 __all__ = [
-    'evaluation_llm_safety_bias_pipeline',
-    'evaluation_llm_embedding_pipeline',
-    'evaluation_llm_text2sql_pipeline',
     'evaluation_llm_endpoint_batch_predict_pipeline_graph_component',
     'ChunkingOp',
     'EvaluationDataSamplerOp',
@@ -63,9 +54,6 @@ __all__ = [
     'LLMSafetyBiasMetricsOp',
     'ModelEvaluationFeatureAttributionOp',
     'ModelImportEvaluatedAnnotationOp',
-    'ModelImportEvaluationOp',
     'ModelNamePreprocessorOp',
     'TargetFieldDataRemoverOp',
-    'model_inference_component',
-    'model_inference_and_evaluation_component',
 ]

google_cloud_pipeline_components/_implementation/model_evaluation/llm_embedding/evaluation_llm_embedding_pipeline.py

@@ -14,11 +14,12 @@
 """LLM embedding evaluation pipeline based on information retrieval (IR) task."""
 
 from typing import Dict, Optional, Union
+
 from google_cloud_pipeline_components._implementation.model_evaluation.endpoint_batch_predict.component import evaluation_llm_endpoint_batch_predict_pipeline_graph_component as LLMEndpointBatchPredictOp
-from google_cloud_pipeline_components._implementation.model_evaluation.import_evaluation.component import model_evaluation_import as ModelImportEvaluationOp
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_embedding_retrieval.component import llm_embedding_retrieval as LLMEmbeddingRetrievalOp
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_information_retrieval_preprocessor.component import llm_information_retrieval_preprocessor as LLMInformationRetrievalPreprocessorOp
 from google_cloud_pipeline_components._implementation.model_evaluation.llm_retrieval_metrics.component import llm_retrieval_metrics as LLMRetrievalMetricsOp
+from google_cloud_pipeline_components.preview.model_evaluation.model_evaluation_import_component import model_evaluation_import as ModelImportEvaluationOp
 from google_cloud_pipeline_components.types.artifact_types import VertexModel
 from google_cloud_pipeline_components.v1.batch_predict_job import ModelBatchPredictOp
 import kfp

google_cloud_pipeline_components/_implementation/model_evaluation/llm_evaluation_preprocessor/component.py

@@ -38,6 +38,8 @@ def evaluation_dataset_preprocessor_internal(
     output_dirs: dsl.OutputPath(list),
     gcp_resources: dsl.OutputPath(str),
     input_field_name: str = 'input_text',
+    role_field_name: str = 'role',
+    model_name: str = 'publishers/google/model/text-bison@002',
     display_name: str = 'llm_evaluation_dataset_preprocessor_component',
     machine_type: str = 'e2-highmem-16',
     service_account: str = '',
@@ -56,6 +58,9 @@ def evaluation_dataset_preprocessor_internal(
       gcs_source_uris: A json escaped list of GCS URIs of the input eval dataset.
       input_field_name: The field name of the input eval dataset instances that
         contains the input prompts to the LLM.
+      role_field_name: The field name of the role for input eval dataset instances
+        that contains the input prompts to the LLM.
+      model_name: Name of the model being used to create model-specific schemas.
       machine_type: The machine type of this custom job. If not set, defaulted
         to `e2-highmem-16`. More details:
         https://cloud.google.com/compute/docs/machine-resource
@@ -92,6 +97,8 @@ def evaluation_dataset_preprocessor_internal(
               f'--eval_dataset_preprocessor={True}',
               f'--gcs_source_uris={gcs_source_uris}',
               f'--input_field_name={input_field_name}',
+              f'--role_field_name={role_field_name}',
+              f'--model_name={model_name}',
               f'--output_dirs={output_dirs}',
               '--executor_input={{$.json_escape[1]}}',
           ],
@@ -109,6 +116,8 @@ def llm_evaluation_dataset_preprocessor_graph_component(
     location: str,
     gcs_source_uris: List[str],
     input_field_name: str = 'input_text',
+    role_field_name: str = 'role',
+    model_name: str = 'publishers/google/model/text-bison@002',
     display_name: str = 'llm_evaluation_dataset_preprocessor_component',
     machine_type: str = 'e2-standard-4',
     service_account: str = '',
@@ -126,6 +135,9 @@ def llm_evaluation_dataset_preprocessor_graph_component(
       gcs_source_uris: A list of GCS URIs of the input eval dataset.
       input_field_name: The field name of the input eval dataset instances that
         contains the input prompts to the LLM.
+      role_field_name: The field name of the role for input eval dataset
+        instances that contains the input prompts to the LLM.
+      model_name: Name of the model being used to create model-specific schemas.
       display_name: The name of the Evaluation job.
       machine_type: The machine type of this custom job. If not set, defaulted
         to `e2-standard-4`. More details:
@@ -163,6 +175,8 @@ def llm_evaluation_dataset_preprocessor_graph_component(
           input_list=gcs_source_uris
       ).output,
       input_field_name=input_field_name,
+      role_field_name=role_field_name,
+      model_name=model_name,
       display_name=display_name,
       machine_type=machine_type,
       service_account=service_account,

google_cloud_pipeline_components/_implementation/starry_net/__init__.py

@@ -0,0 +1,41 @@
+# Copyright 2024 The Kubeflow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from google_cloud_pipeline_components._implementation.starry_net.dataprep.component import dataprep as DataprepOp
+from google_cloud_pipeline_components._implementation.starry_net.evaluation.component import evaluation as EvaluationOp
+from google_cloud_pipeline_components._implementation.starry_net.get_training_artifacts.component import get_training_artifacts as GetTrainingArtifactsOp
+from google_cloud_pipeline_components._implementation.starry_net.maybe_set_tfrecord_args.component import maybe_set_tfrecord_args as MaybeSetTfrecordArgsOp
+from google_cloud_pipeline_components._implementation.starry_net.set_dataprep_args.component import set_dataprep_args as SetDataprepArgsOp
+from google_cloud_pipeline_components._implementation.starry_net.set_eval_args.component import set_eval_args as SetEvalArgsOp
+from google_cloud_pipeline_components._implementation.starry_net.set_test_set.component import set_test_set as SetTestSetOp
+from google_cloud_pipeline_components._implementation.starry_net.set_tfrecord_args.component import set_tfrecord_args as SetTfrecordArgsOp
+from google_cloud_pipeline_components._implementation.starry_net.set_train_args.component import set_train_args as SetTrainArgsOp
+from google_cloud_pipeline_components._implementation.starry_net.train.component import train as TrainOp
+from google_cloud_pipeline_components._implementation.starry_net.upload_decomposition_plots.component import upload_decomposition_plots as UploadDecompositionPlotsOp
+from google_cloud_pipeline_components._implementation.starry_net.upload_model.component import upload_model as UploadModelOp
+
+
+__all__ = [
+    'DataprepOp',
+    'EvaluationOp',
+    'GetTrainingArtifactsOp',
+    'MaybeSetTfrecordArgsOp',
+    'SetDataprepArgsOp',
+    'SetEvalArgsOp',
+    'SetTestSetOp',
+    'SetTfrecordArgsOp',
+    'SetTrainArgsOp',
+    'TrainOp',
+    'UploadDecompositionPlotsOp',
+    'UploadModelOp',
+]

google_cloud_pipeline_components/_implementation/{model_evaluation/import_evaluation → starry_net/dataprep}/__init__.py

@@ -1,4 +1,4 @@
-# Copyright 2023 The Kubeflow Authors. All Rights Reserved.
+# Copyright 2024 The Kubeflow Authors. All Rights Reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,4 +11,3 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Google Cloud Pipeline Evaluation Import Evaluation Component."""