fix(components): Fix model eval import error in text generation/class…

…ification eval pipeline

PiperOrigin-RevId: 621326276

components/google-cloud/RELEASE.md

@@ -1,5 +1,8 @@
 ## Upcoming release
 
+## Release 2.14.0
+* Fix model name preprocess error, pass correct model to `ModelImportEvaluationOp` component in `v1.model_evaluation.evaluation_llm_text_generation_pipeline` and `v1.model_evaluation.evaluation_llm_classification_pipeline`.
+
 ## Release 2.13.0
 * Add support for `text-bison@002` to `preview.llm.rlhf_pipeline`.
 * Apply latest GCPC image vulnerability resolutions (base OS and software updates).

components/google-cloud/google_cloud_pipeline_components/v1/model_evaluation/evaluation_llm_classification_pipeline.py

@@ -176,9 +176,18 @@ def evaluation_llm_classification_pipeline(  # pylint: disable=dangerous-default
       encryption_spec_key_name=encryption_spec_key_name,
   )
 
+  get_vertex_eval_model_task = dsl.importer(
+      artifact_uri=(
+          f'https://{location}-aiplatform.googleapis.com/v1/{model_name}'
+      ),
+      artifact_class=VertexModel,
+      metadata={'resourceName': model_name},
+  )
+  get_vertex_eval_model_task.set_display_name('get-vertex-eval-model')
+
   import_evaluation_task = ModelImportEvaluationOp(
       classification_metrics=eval_task.outputs['evaluation_metrics'],
-      model=get_vertex_model_task.outputs['artifact'],
+      model=get_vertex_eval_model_task.outputs['artifact'],
       dataset_type=batch_predict_instances_format,
       dataset_paths=batch_predict_gcs_source_uris,
       display_name=evaluation_display_name,

components/google-cloud/google_cloud_pipeline_components/v1/model_evaluation/evaluation_llm_text_generation_pipeline.py

@@ -34,7 +34,6 @@ def evaluation_llm_text_generation_pipeline(  # pylint: disable=dangerous-defaul
     location: str,
     batch_predict_gcs_source_uris: List[str],
     batch_predict_gcs_destination_output_uri: str,
-    service_account: str,
     model_name: str = 'publishers/google/models/text-bison@002',
     evaluation_task: str = 'text-generation',
     input_field_name: str = 'input_text',
@@ -44,6 +43,7 @@ def evaluation_llm_text_generation_pipeline(  # pylint: disable=dangerous-defaul
     batch_predict_model_parameters: Dict[str, str] = {},
     enable_row_based_metrics: bool = False,
     machine_type: str = 'e2-standard-4',
+    service_account: str = '',
     network: str = '',
     encryption_spec_key_name: str = '',
     evaluation_display_name: str = 'evaluation-llm-text-generation-pipeline-{{$.pipeline_job_uuid}}',
@@ -72,7 +72,6 @@ def evaluation_llm_text_generation_pipeline(  # pylint: disable=dangerous-defaul
           "output_text": "your ground truth output text"
         }
     batch_predict_gcs_destination_output_uri: Required. The Google Cloud Storage location of the directory where the eval pipeline output is to be written to.
-    service_account: Required. Sets the default service account for workload run-as account. The service account running the pipeline (https://cloud.google.com/vertex-ai/docs/pipelines/configure-project#service-account) submitting jobs must have act-as permission on this run-as account.
     model_name: The Model name used to run evaluation. Must be a publisher Model or a managed Model sharing the same ancestor location. Starting this job has no impact on any existing deployments of the Model and their resources.
     evaluation_task: The task that the large language model will be evaluated on. The evaluation component computes a set of metrics relevant to that specific task. Currently supported tasks are: `summarization`, `question-answering`, `text-generation`.
     input_field_name: The field name of the input eval dataset instances that contains the input prompts to the LLM.
@@ -82,6 +81,7 @@ def evaluation_llm_text_generation_pipeline(  # pylint: disable=dangerous-defaul
     batch_predict_model_parameters: A map of parameters that govern the predictions. Some acceptable parameters include: maxOutputTokens, topK, topP, and temperature.
     enable_row_based_metrics: Flag of if row based metrics is enabled, default value is false.
     machine_type: The machine type of this custom job. If not set, defaulted to `e2-standard-4`. More details: https://cloud.google.com/compute/docs/machine-resource
+    service_account: Sets the default service account for workload run-as account. The service account running the pipeline (https://cloud.google.com/vertex-ai/docs/pipelines/configure-project#service-account) submitting jobs must have act-as permission on this run-as account. If unspecified, the Vertex AI Custom Code Service Agent(https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) for the CustomJob's project.
     network: The full name of the Compute Engine network to which the job should be peered. For example, `projects/12345/global/networks/myVPC`. Format is of the form `projects/{project}/global/networks/{network}`. Where `{project}` is a project number, as in `12345`, and `{network}` is a network name, as in `myVPC`. To specify this field, you must have already configured VPC Network Peering for Vertex AI (https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If left unspecified, the job is not peered with any network.
     encryption_spec_key_name:  Customer-managed encryption key options. If set, resources created by this pipeline will be encrypted with the provided encryption key. Has the form: `projects/my-project/locations/my-location/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
     evaluation_display_name: The display name of the uploaded evaluation resource to the Vertex AI model.
@@ -158,11 +158,20 @@ def evaluation_llm_text_generation_pipeline(  # pylint: disable=dangerous-defaul
       encryption_spec_key_name=encryption_spec_key_name,
   )
 
+  get_vertex_eval_model_task = dsl.importer(
+      artifact_uri=(
+          f'https://{location}-aiplatform.googleapis.com/v1/{model_name}'
+      ),
+      artifact_class=VertexModel,
+      metadata={'resourceName': model_name},
+  )
+  get_vertex_eval_model_task.set_display_name('get-vertex-eval-model')
+
   with dsl.If(enable_row_based_metrics == True):
     import_evaluation_task_with_row_based_metrics = ModelImportEvaluationOp(
         metrics=eval_task.outputs['evaluation_metrics'],
         row_based_metrics=eval_task.outputs['row_based_metrics'],
-        model=get_vertex_model_task.outputs['artifact'],
+        model=get_vertex_eval_model_task.outputs['artifact'],
         problem_type=evaluation_task,
         dataset_type=batch_predict_predictions_format,
         dataset_paths=batch_predict_gcs_source_uris,
@@ -171,7 +180,7 @@ def evaluation_llm_text_generation_pipeline(  # pylint: disable=dangerous-defaul
   with dsl.Else():
     import_evaluation_task = ModelImportEvaluationOp(
         metrics=eval_task.outputs['evaluation_metrics'],
-        model=get_vertex_model_task.outputs['artifact'],
+        model=get_vertex_eval_model_task.outputs['artifact'],
         problem_type=evaluation_task,
         dataset_type=batch_predict_predictions_format,
         dataset_paths=batch_predict_gcs_source_uris,