google-genai 1.59.0__py3-none-any.whl → 1.61.0__py3-none-any.whl

google/genai/tunings.py

@@ -188,6 +188,14 @@ def _CreateTuningJobConfig_to_mldev(
   if getv(from_object, ['adapter_size']) is not None:
     raise ValueError('adapter_size parameter is not supported in Gemini API.')
 
+  if getv(from_object, ['tuning_mode']) is not None:
+    raise ValueError('tuning_mode parameter is not supported in Gemini API.')
+
+  if getv(from_object, ['custom_base_model']) is not None:
+    raise ValueError(
+        'custom_base_model parameter is not supported in Gemini API.'
+    )
+
   if getv(from_object, ['batch_size']) is not None:
     setv(
         parent_object,
@@ -213,6 +221,24 @@ def _CreateTuningJobConfig_to_mldev(
   if getv(from_object, ['beta']) is not None:
     raise ValueError('beta parameter is not supported in Gemini API.')
 
+  if getv(from_object, ['base_teacher_model']) is not None:
+    raise ValueError(
+        'base_teacher_model parameter is not supported in Gemini API.'
+    )
+
+  if getv(from_object, ['tuned_teacher_model_source']) is not None:
+    raise ValueError(
+        'tuned_teacher_model_source parameter is not supported in Gemini API.'
+    )
+
+  if getv(from_object, ['sft_loss_weight_multiplier']) is not None:
+    raise ValueError(
+        'sft_loss_weight_multiplier parameter is not supported in Gemini API.'
+    )
+
+  if getv(from_object, ['output_uri']) is not None:
+    raise ValueError('output_uri parameter is not supported in Gemini API.')
+
   return to_object
 
 
@@ -246,6 +272,16 @@ def _CreateTuningJobConfig_to_vertex(
           ),
       )
 
+  elif discriminator == 'DISTILLATION':
+    if getv(from_object, ['validation_dataset']) is not None:
+      setv(
+          parent_object,
+          ['distillationSpec'],
+          _TuningValidationDataset_to_vertex(
+              getv(from_object, ['validation_dataset']), to_object, root_object
+          ),
+      )
+
   if getv(from_object, ['tuned_model_display_name']) is not None:
     setv(
         parent_object,
@@ -275,6 +311,14 @@ def _CreateTuningJobConfig_to_vertex(
           getv(from_object, ['epoch_count']),
       )
 
+  elif discriminator == 'DISTILLATION':
+    if getv(from_object, ['epoch_count']) is not None:
+      setv(
+          parent_object,
+          ['distillationSpec', 'hyperParameters', 'epochCount'],
+          getv(from_object, ['epoch_count']),
+      )
+
   discriminator = getv(root_object, ['config', 'method'])
   if discriminator is None:
     discriminator = 'SUPERVISED_FINE_TUNING'
@@ -298,6 +342,14 @@ def _CreateTuningJobConfig_to_vertex(
           getv(from_object, ['learning_rate_multiplier']),
       )
 
+  elif discriminator == 'DISTILLATION':
+    if getv(from_object, ['learning_rate_multiplier']) is not None:
+      setv(
+          parent_object,
+          ['distillationSpec', 'hyperParameters', 'learningRateMultiplier'],
+          getv(from_object, ['learning_rate_multiplier']),
+      )
+
   discriminator = getv(root_object, ['config', 'method'])
   if discriminator is None:
     discriminator = 'SUPERVISED_FINE_TUNING'
@@ -317,6 +369,14 @@ def _CreateTuningJobConfig_to_vertex(
           getv(from_object, ['export_last_checkpoint_only']),
       )
 
+  elif discriminator == 'DISTILLATION':
+    if getv(from_object, ['export_last_checkpoint_only']) is not None:
+      setv(
+          parent_object,
+          ['distillationSpec', 'exportLastCheckpointOnly'],
+          getv(from_object, ['export_last_checkpoint_only']),
+      )
+
   discriminator = getv(root_object, ['config', 'method'])
   if discriminator is None:
     discriminator = 'SUPERVISED_FINE_TUNING'
@@ -336,11 +396,53 @@ def _CreateTuningJobConfig_to_vertex(
           getv(from_object, ['adapter_size']),
       )
 
-  if getv(from_object, ['batch_size']) is not None:
-    raise ValueError('batch_size parameter is not supported in Vertex AI.')
+  elif discriminator == 'DISTILLATION':
+    if getv(from_object, ['adapter_size']) is not None:
+      setv(
+          parent_object,
+          ['distillationSpec', 'hyperParameters', 'adapterSize'],
+          getv(from_object, ['adapter_size']),
+      )
 
-  if getv(from_object, ['learning_rate']) is not None:
-    raise ValueError('learning_rate parameter is not supported in Vertex AI.')
+  discriminator = getv(root_object, ['config', 'method'])
+  if discriminator is None:
+    discriminator = 'SUPERVISED_FINE_TUNING'
+  if discriminator == 'SUPERVISED_FINE_TUNING':
+    if getv(from_object, ['tuning_mode']) is not None:
+      setv(
+          parent_object,
+          ['supervisedTuningSpec', 'tuningMode'],
+          getv(from_object, ['tuning_mode']),
+      )
+
+  if getv(from_object, ['custom_base_model']) is not None:
+    setv(
+        parent_object,
+        ['customBaseModel'],
+        getv(from_object, ['custom_base_model']),
+    )
+
+  discriminator = getv(root_object, ['config', 'method'])
+  if discriminator is None:
+    discriminator = 'SUPERVISED_FINE_TUNING'
+  if discriminator == 'SUPERVISED_FINE_TUNING':
+    if getv(from_object, ['batch_size']) is not None:
+      setv(
+          parent_object,
+          ['supervisedTuningSpec', 'hyperParameters', 'batchSize'],
+          getv(from_object, ['batch_size']),
+      )
+
+  discriminator = getv(root_object, ['config', 'method'])
+  if discriminator is None:
+    discriminator = 'SUPERVISED_FINE_TUNING'
+  if discriminator == 'SUPERVISED_FINE_TUNING':
+    if getv(from_object, ['learning_rate']) is not None:
+      setv(
+          parent_object,
+          ['supervisedTuningSpec', 'hyperParameters', 'learningRate'],
+          getv(from_object, ['learning_rate']),
+      )
 
   discriminator = getv(root_object, ['config', 'method'])
   if discriminator is None:
@@ -365,6 +467,16 @@ def _CreateTuningJobConfig_to_vertex(
           ),
       )
 
+  elif discriminator == 'DISTILLATION':
+    if getv(from_object, ['evaluation_config']) is not None:
+      setv(
+          parent_object,
+          ['distillationSpec', 'evaluationConfig'],
+          _EvaluationConfig_to_vertex(
+              getv(from_object, ['evaluation_config']), to_object, root_object
+          ),
+      )
+
   if getv(from_object, ['labels']) is not None:
     setv(parent_object, ['labels'], getv(from_object, ['labels']))
 
@@ -375,6 +487,30 @@ def _CreateTuningJobConfig_to_vertex(
         getv(from_object, ['beta']),
     )
 
+  if getv(from_object, ['base_teacher_model']) is not None:
+    setv(
+        parent_object,
+        ['distillationSpec', 'baseTeacherModel'],
+        getv(from_object, ['base_teacher_model']),
+    )
+
+  if getv(from_object, ['tuned_teacher_model_source']) is not None:
+    setv(
+        parent_object,
+        ['distillationSpec', 'tunedTeacherModelSource'],
+        getv(from_object, ['tuned_teacher_model_source']),
+    )
+
+  if getv(from_object, ['sft_loss_weight_multiplier']) is not None:
+    setv(
+        parent_object,
+        ['distillationSpec', 'hyperParameters', 'sftLossWeightMultiplier'],
+        getv(from_object, ['sft_loss_weight_multiplier']),
+    )
+
+  if getv(from_object, ['output_uri']) is not None:
+    setv(parent_object, ['outputUri'], getv(from_object, ['output_uri']))
+
   return to_object
 
 
@@ -920,6 +1056,14 @@ def _TuningDataset_to_vertex(
           getv(from_object, ['gcs_uri']),
       )
 
+  elif discriminator == 'DISTILLATION':
+    if getv(from_object, ['gcs_uri']) is not None:
+      setv(
+          parent_object,
+          ['distillationSpec', 'promptDatasetUri'],
+          getv(from_object, ['gcs_uri']),
+      )
+
   discriminator = getv(root_object, ['config', 'method'])
   if discriminator is None:
     discriminator = 'SUPERVISED_FINE_TUNING'
@@ -939,6 +1083,14 @@ def _TuningDataset_to_vertex(
           getv(from_object, ['vertex_dataset_resource']),
       )
 
+  elif discriminator == 'DISTILLATION':
+    if getv(from_object, ['vertex_dataset_resource']) is not None:
+      setv(
+          parent_object,
+          ['distillationSpec', 'promptDatasetUri'],
+          getv(from_object, ['vertex_dataset_resource']),
+      )
+
   if getv(from_object, ['examples']) is not None:
     raise ValueError('examples parameter is not supported in Vertex AI.')
 
@@ -1066,6 +1218,13 @@ def _TuningJob_from_vertex(
         getv(from_object, ['preferenceOptimizationSpec']),
     )
 
+  if getv(from_object, ['distillationSpec']) is not None:
+    setv(
+        to_object,
+        ['distillation_spec'],
+        getv(from_object, ['distillationSpec']),
+    )
+
   if getv(from_object, ['tuningDataStats']) is not None:
     setv(
         to_object, ['tuning_data_stats'], getv(from_object, ['tuningDataStats'])

google/genai/types.py

@@ -813,6 +813,8 @@ class TuningMethod(_common.CaseInSensitiveEnum):
   """Supervised fine tuning."""
   PREFERENCE_TUNING = 'PREFERENCE_TUNING'
   """Preference optimization tuning."""
+  DISTILLATION = 'DISTILLATION'
+  """Distillation tuning."""
 
 
 class DocumentState(_common.CaseInSensitiveEnum):
@@ -5003,6 +5005,38 @@ SpeechConfigUnion = Union[str, SpeechConfig]
 SpeechConfigUnionDict = Union[str, SpeechConfig, SpeechConfigDict]
 
 
+class ModelArmorConfig(_common.BaseModel):
+  """Configuration for Model Armor integrations of prompt and responses.
+
+  This data type is not supported in Gemini API.
+  """
+
+  prompt_template_name: Optional[str] = Field(
+      default=None,
+      description="""Optional. The name of the Model Armor template to use for prompt sanitization.""",
+  )
+  response_template_name: Optional[str] = Field(
+      default=None,
+      description="""Optional. The name of the Model Armor template to use for response sanitization.""",
+  )
+
+
+class ModelArmorConfigDict(TypedDict, total=False):
+  """Configuration for Model Armor integrations of prompt and responses.
+
+  This data type is not supported in Gemini API.
+  """
+
+  prompt_template_name: Optional[str]
+  """Optional. The name of the Model Armor template to use for prompt sanitization."""
+
+  response_template_name: Optional[str]
+  """Optional. The name of the Model Armor template to use for response sanitization."""
+
+
+ModelArmorConfigOrDict = Union[ModelArmorConfig, ModelArmorConfigDict]
+
+
 class GenerateContentConfig(_common.BaseModel):
   """Optional model configuration parameters.
 
@@ -5219,6 +5253,12 @@ class GenerateContentConfig(_common.BaseModel):
       models. This field is not supported in Vertex AI.
       """,
   )
+  model_armor_config: Optional[ModelArmorConfig] = Field(
+      default=None,
+      description="""Settings for prompt and response sanitization using the Model Armor
+      service. If supplied, safety_settings must not be supplied.
+      """,
+  )
 
   @pydantic.field_validator('response_schema', mode='before')
   @classmethod
@@ -5429,6 +5469,11 @@ class GenerateContentConfigDict(TypedDict, total=False):
       models. This field is not supported in Vertex AI.
       """
 
+  model_armor_config: Optional[ModelArmorConfigDict]
+  """Settings for prompt and response sanitization using the Model Armor
+      service. If supplied, safety_settings must not be supplied.
+      """
+
 
 GenerateContentConfigOrDict = Union[
     GenerateContentConfig, GenerateContentConfigDict
@@ -10503,6 +10548,114 @@ PreferenceOptimizationSpecOrDict = Union[
 ]
 
 
+class DistillationHyperParameters(_common.BaseModel):
+  """Hyperparameters for Distillation.
+
+  This data type is not supported in Gemini API.
+  """
+
+  adapter_size: Optional[AdapterSize] = Field(
+      default=None, description="""Optional. Adapter size for distillation."""
+  )
+  epoch_count: Optional[int] = Field(
+      default=None,
+      description="""Optional. Number of complete passes the model makes over the entire training dataset during training.""",
+  )
+  learning_rate_multiplier: Optional[float] = Field(
+      default=None,
+      description="""Optional. Multiplier for adjusting the default learning rate.""",
+  )
+
+
+class DistillationHyperParametersDict(TypedDict, total=False):
+  """Hyperparameters for Distillation.
+
+  This data type is not supported in Gemini API.
+  """
+
+  adapter_size: Optional[AdapterSize]
+  """Optional. Adapter size for distillation."""
+
+  epoch_count: Optional[int]
+  """Optional. Number of complete passes the model makes over the entire training dataset during training."""
+
+  learning_rate_multiplier: Optional[float]
+  """Optional. Multiplier for adjusting the default learning rate."""
+
+
+DistillationHyperParametersOrDict = Union[
+    DistillationHyperParameters, DistillationHyperParametersDict
+]
+
+
+class DistillationSpec(_common.BaseModel):
+  """Distillation tuning spec for tuning."""
+
+  prompt_dataset_uri: Optional[str] = Field(
+      default=None,
+      description="""The GCS URI of the prompt dataset to use during distillation.""",
+  )
+  base_teacher_model: Optional[str] = Field(
+      default=None,
+      description="""The base teacher model that is being distilled. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/tuning#supported_models).""",
+  )
+  hyper_parameters: Optional[DistillationHyperParameters] = Field(
+      default=None,
+      description="""Optional. Hyperparameters for Distillation.""",
+  )
+  pipeline_root_directory: Optional[str] = Field(
+      default=None,
+      description="""Deprecated. A path in a Cloud Storage bucket, which will be treated as the root output directory of the distillation pipeline. It is used by the system to generate the paths of output artifacts.""",
+  )
+  student_model: Optional[str] = Field(
+      default=None,
+      description="""The student model that is being tuned, e.g., "google/gemma-2b-1.1-it". Deprecated. Use base_model instead.""",
+  )
+  training_dataset_uri: Optional[str] = Field(
+      default=None,
+      description="""Deprecated. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file.""",
+  )
+  tuned_teacher_model_source: Optional[str] = Field(
+      default=None,
+      description="""The resource name of the Tuned teacher model. Format: `projects/{project}/locations/{location}/models/{model}`.""",
+  )
+  validation_dataset_uri: Optional[str] = Field(
+      default=None,
+      description="""Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file.""",
+  )
+
+
+class DistillationSpecDict(TypedDict, total=False):
+  """Distillation tuning spec for tuning."""
+
+  prompt_dataset_uri: Optional[str]
+  """The GCS URI of the prompt dataset to use during distillation."""
+
+  base_teacher_model: Optional[str]
+  """The base teacher model that is being distilled. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/tuning#supported_models)."""
+
+  hyper_parameters: Optional[DistillationHyperParametersDict]
+  """Optional. Hyperparameters for Distillation."""
+
+  pipeline_root_directory: Optional[str]
+  """Deprecated. A path in a Cloud Storage bucket, which will be treated as the root output directory of the distillation pipeline. It is used by the system to generate the paths of output artifacts."""
+
+  student_model: Optional[str]
+  """The student model that is being tuned, e.g., "google/gemma-2b-1.1-it". Deprecated. Use base_model instead."""
+
+  training_dataset_uri: Optional[str]
+  """Deprecated. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file."""
+
+  tuned_teacher_model_source: Optional[str]
+  """The resource name of the Tuned teacher model. Format: `projects/{project}/locations/{location}/models/{model}`."""
+
+  validation_dataset_uri: Optional[str]
+  """Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file."""
+
+
+DistillationSpecOrDict = Union[DistillationSpec, DistillationSpecDict]
+
+
 class GcsDestination(_common.BaseModel):
   """The Google Cloud Storage location where the output is to be written to."""
 
@@ -11699,6 +11852,9 @@ class TuningJob(_common.BaseModel):
   preference_optimization_spec: Optional[PreferenceOptimizationSpec] = Field(
       default=None, description="""Tuning Spec for Preference Optimization."""
   )
+  distillation_spec: Optional[DistillationSpec] = Field(
+      default=None, description="""Tuning Spec for Distillation."""
+  )
   tuning_data_stats: Optional[TuningDataStats] = Field(
       default=None,
       description="""Output only. The tuning data statistics associated with this TuningJob.""",
@@ -11802,6 +11958,9 @@ class TuningJobDict(TypedDict, total=False):
   preference_optimization_spec: Optional[PreferenceOptimizationSpecDict]
   """Tuning Spec for Preference Optimization."""
 
+  distillation_spec: Optional[DistillationSpecDict]
+  """Tuning Spec for Distillation."""
+
   tuning_data_stats: Optional[TuningDataStatsDict]
   """Output only. The tuning data statistics associated with this TuningJob."""
 
@@ -12090,7 +12249,7 @@ class CreateTuningJobConfig(_common.BaseModel):
   )
   method: Optional[TuningMethod] = Field(
       default=None,
-      description="""The method to use for tuning (SUPERVISED_FINE_TUNING or PREFERENCE_TUNING). If not set, the default method (SFT) will be used.""",
+      description="""The method to use for tuning (SUPERVISED_FINE_TUNING or PREFERENCE_TUNING or DISTILLATION). If not set, the default method (SFT) will be used.""",
   )
   validation_dataset: Optional[TuningValidationDataset] = Field(
       default=None,
@@ -12109,7 +12268,7 @@ class CreateTuningJobConfig(_common.BaseModel):
   )
   learning_rate_multiplier: Optional[float] = Field(
       default=None,
-      description="""Multiplier for adjusting the default learning rate.""",
+      description="""Multiplier for adjusting the default learning rate. 1P models only. Mutually exclusive with learning_rate.""",
   )
   export_last_checkpoint_only: Optional[bool] = Field(
       default=None,
@@ -12122,13 +12281,20 @@ class CreateTuningJobConfig(_common.BaseModel):
   adapter_size: Optional[AdapterSize] = Field(
       default=None, description="""Adapter size for tuning."""
   )
+  tuning_mode: Optional[TuningMode] = Field(
+      default=None, description="""Tuning mode for SFT tuning."""
+  )
+  custom_base_model: Optional[str] = Field(
+      default=None,
+      description="""Custom base model for tuning. This is only supported for OSS models in Vertex.""",
+  )
   batch_size: Optional[int] = Field(
       default=None,
-      description="""The batch size hyperparameter for tuning. If not set, a default of 4 or 16 will be used based on the number of training examples.""",
+      description="""The batch size hyperparameter for tuning. This is only supported for OSS models in Vertex.""",
   )
   learning_rate: Optional[float] = Field(
       default=None,
-      description="""The learning rate hyperparameter for tuning. If not set, a default of 0.001 or 0.0002 will be calculated based on the number of training examples.""",
+      description="""The learning rate for tuning. OSS models only. Mutually exclusive with learning_rate_multiplier.""",
   )
   evaluation_config: Optional[EvaluationConfig] = Field(
       default=None, description="""Evaluation config for the tuning job."""
@@ -12141,6 +12307,22 @@ class CreateTuningJobConfig(_common.BaseModel):
       default=None,
       description="""Weight for KL Divergence regularization, Preference Optimization tuning only.""",
   )
+  base_teacher_model: Optional[str] = Field(
+      default=None,
+      description="""The base teacher model that is being distilled. Distillation only.""",
+  )
+  tuned_teacher_model_source: Optional[str] = Field(
+      default=None,
+      description="""The resource name of the Tuned teacher model. Distillation only.""",
+  )
+  sft_loss_weight_multiplier: Optional[float] = Field(
+      default=None,
+      description="""Multiplier for adjusting the weight of the SFT loss. Distillation only.""",
+  )
+  output_uri: Optional[str] = Field(
+      default=None,
+      description="""The Google Cloud Storage location where the tuning job outputs are written.""",
+  )
 
 
 class CreateTuningJobConfigDict(TypedDict, total=False):
@@ -12150,7 +12332,7 @@ class CreateTuningJobConfigDict(TypedDict, total=False):
   """Used to override HTTP request options."""
 
   method: Optional[TuningMethod]
-  """The method to use for tuning (SUPERVISED_FINE_TUNING or PREFERENCE_TUNING). If not set, the default method (SFT) will be used."""
+  """The method to use for tuning (SUPERVISED_FINE_TUNING or PREFERENCE_TUNING or DISTILLATION). If not set, the default method (SFT) will be used."""
 
   validation_dataset: Optional[TuningValidationDatasetDict]
   """Validation dataset for tuning. The dataset must be formatted as a JSONL file."""
@@ -12165,7 +12347,7 @@ class CreateTuningJobConfigDict(TypedDict, total=False):
   """Number of complete passes the model makes over the entire training dataset during training."""
 
   learning_rate_multiplier: Optional[float]
-  """Multiplier for adjusting the default learning rate."""
+  """Multiplier for adjusting the default learning rate. 1P models only. Mutually exclusive with learning_rate."""
 
   export_last_checkpoint_only: Optional[bool]
   """If set to true, disable intermediate checkpoints and only the last checkpoint will be exported. Otherwise, enable intermediate checkpoints."""
@@ -12176,11 +12358,17 @@ class CreateTuningJobConfigDict(TypedDict, total=False):
   adapter_size: Optional[AdapterSize]
   """Adapter size for tuning."""
 
+  tuning_mode: Optional[TuningMode]
+  """Tuning mode for SFT tuning."""
+
+  custom_base_model: Optional[str]
+  """Custom base model for tuning. This is only supported for OSS models in Vertex."""
+
   batch_size: Optional[int]
-  """The batch size hyperparameter for tuning. If not set, a default of 4 or 16 will be used based on the number of training examples."""
+  """The batch size hyperparameter for tuning. This is only supported for OSS models in Vertex."""
 
   learning_rate: Optional[float]
-  """The learning rate hyperparameter for tuning. If not set, a default of 0.001 or 0.0002 will be calculated based on the number of training examples."""
+  """The learning rate for tuning. OSS models only. Mutually exclusive with learning_rate_multiplier."""
 
   evaluation_config: Optional[EvaluationConfigDict]
   """Evaluation config for the tuning job."""
@@ -12191,6 +12379,18 @@ class CreateTuningJobConfigDict(TypedDict, total=False):
   beta: Optional[float]
   """Weight for KL Divergence regularization, Preference Optimization tuning only."""
 
+  base_teacher_model: Optional[str]
+  """The base teacher model that is being distilled. Distillation only."""
+
+  tuned_teacher_model_source: Optional[str]
+  """The resource name of the Tuned teacher model. Distillation only."""
+
+  sft_loss_weight_multiplier: Optional[float]
+  """Multiplier for adjusting the weight of the SFT loss. Distillation only."""
+
+  output_uri: Optional[str]
+  """The Google Cloud Storage location where the tuning job outputs are written."""
+
 
 CreateTuningJobConfigOrDict = Union[
     CreateTuningJobConfig, CreateTuningJobConfigDict
@@ -13983,8 +14183,8 @@ class RegisterFilesConfigDict(TypedDict, total=False):
 RegisterFilesConfigOrDict = Union[RegisterFilesConfig, RegisterFilesConfigDict]
 
 
-class _RegisterFilesParameters(_common.BaseModel):
-  """Generates the parameters for the private _Register method."""
+class _InternalRegisterFilesParameters(_common.BaseModel):
+  """Parameters for the private _Register method."""
 
   uris: Optional[list[str]] = Field(
       default=None,
@@ -13996,8 +14196,8 @@ class _RegisterFilesParameters(_common.BaseModel):
   )
 
 
-class _RegisterFilesParametersDict(TypedDict, total=False):
-  """Generates the parameters for the private _Register method."""
+class _InternalRegisterFilesParametersDict(TypedDict, total=False):
+  """Parameters for the private _Register method."""
 
   uris: Optional[list[str]]
   """The Google Cloud Storage URIs to register. Example: `gs://bucket/object`."""
@@ -14006,8 +14206,8 @@ class _RegisterFilesParametersDict(TypedDict, total=False):
   """Used to override the default configuration."""
 
 
-_RegisterFilesParametersOrDict = Union[
-    _RegisterFilesParameters, _RegisterFilesParametersDict
+_InternalRegisterFilesParametersOrDict = Union[
+    _InternalRegisterFilesParameters, _InternalRegisterFilesParametersDict
 ]
 
 
@@ -14182,6 +14382,10 @@ class InlinedResponse(_common.BaseModel):
       description="""The response to the request.
       """,
   )
+  metadata: Optional[dict[str, str]] = Field(
+      default=None,
+      description="""The metadata to be associated with the request.""",
+  )
   error: Optional[JobError] = Field(
       default=None,
       description="""The error encountered while processing the request.
@@ -14196,6 +14400,9 @@ class InlinedResponseDict(TypedDict, total=False):
   """The response to the request.
       """
 
+  metadata: Optional[dict[str, str]]
+  """The metadata to be associated with the request."""
+
   error: Optional[JobErrorDict]
   """The error encountered while processing the request.
       """

google/genai/version.py

@@ -13,4 +13,4 @@
 # limitations under the License.
 #
 
-__version__ = '1.59.0' # x-release-please-version
+__version__ = '1.61.0' # x-release-please-version

{google_genai-1.59.0.dist-info → google_genai-1.61.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-genai
-Version: 1.59.0
+Version: 1.61.0
 Summary: GenAI Python SDK
 Author-email: Google LLC <googleapis-packages@google.com>
 License-Expression: Apache-2.0