google-genai 1.40.0__py3-none-any.whl → 1.42.0__py3-none-any.whl

google/genai/types.py

@@ -287,6 +287,8 @@ class FinishReason(_common.CaseInSensitiveEnum):
   """The tool call generated by the model is invalid."""
   IMAGE_PROHIBITED_CONTENT = 'IMAGE_PROHIBITED_CONTENT'
   """Image generation stopped because the generated images have prohibited content."""
+  NO_IMAGE = 'NO_IMAGE'
+  """The model was expected to generate an image, but none was generated."""
 
 
 class HarmProbability(_common.CaseInSensitiveEnum):
@@ -436,6 +438,17 @@ class AdapterSize(_common.CaseInSensitiveEnum):
   """Adapter size 32."""
 
 
+class TuningTask(_common.CaseInSensitiveEnum):
+  """Optional. The tuning task. Either I2V or T2V."""
+
+  TUNING_TASK_UNSPECIFIED = 'TUNING_TASK_UNSPECIFIED'
+  """Default value. This value is unused."""
+  TUNING_TASK_I2V = 'TUNING_TASK_I2V'
+  """Tuning task for image to video."""
+  TUNING_TASK_T2V = 'TUNING_TASK_T2V'
+  """Tuning task for text to video."""
+
+
 class JSONSchemaType(Enum):
   """The type of the data supported by JSON Schema.
 
@@ -1104,6 +1117,40 @@ class FunctionResponsePart(_common.BaseModel):
       default=None, description="""Optional. URI based data."""
   )
 
+  @classmethod
+  def from_bytes(cls, *, data: bytes, mime_type: str) -> 'FunctionResponsePart':
+    """Creates a FunctionResponsePart from bytes and mime type.
+
+    Args:
+      data (bytes): The bytes of the data
+      mime_type (str): mime_type: The MIME type of the data.
+    """
+    inline_data = FunctionResponseBlob(
+        data=data,
+        mime_type=mime_type,
+    )
+    return cls(inline_data=inline_data)
+
+  @classmethod
+  def from_uri(
+      cls, *, file_uri: str, mime_type: Optional[str] = None
+  ) -> 'FunctionResponsePart':
+    """Creates a FunctionResponsePart from a file uri.
+
+    Args:
+      file_uri (str): The uri of the file
+      mime_type (str): mime_type: The MIME type of the file. If not provided,
+        the MIME type will be automatically determined.
+    """
+    if mime_type is None:
+      import mimetypes
+
+      mime_type, _ = mimetypes.guess_type(file_uri)
+      if not mime_type:
+        raise ValueError(f'Failed to determine mime type for file: {file_uri}')
+    file_data = FunctionResponseFileData(file_uri=file_uri, mime_type=mime_type)
+    return cls(file_data=file_data)
+
 
 class FunctionResponsePartDict(TypedDict, total=False):
   """A datatype containing media that is part of a `FunctionResponse` message.
@@ -1261,7 +1308,7 @@ class Part(_common.BaseModel):
 
     Args:
       file_uri (str): The uri of the file
-      mime_type (str): mime_type: The MIME type of the image. If not provided,
+      mime_type (str): mime_type: The MIME type of the file. If not provided,
         the MIME type will be automatically determined.
     """
     if mime_type is None:
@@ -1292,9 +1339,15 @@ class Part(_common.BaseModel):
 
   @classmethod
   def from_function_response(
-      cls, *, name: str, response: dict[str, Any]
+      cls,
+      *,
+      name: str,
+      response: dict[str, Any],
+      parts: Optional[list[FunctionResponsePart]] = None,
   ) -> 'Part':
-    function_response = FunctionResponse(name=name, response=response)
+    function_response = FunctionResponse(
+        name=name, response=response, parts=parts
+    )
     return cls(function_response=function_response)
 
   @classmethod
@@ -4309,8 +4362,10 @@ class GenerateContentConfig(_common.BaseModel):
   @pydantic.field_validator('image_config', mode='before')
   @classmethod
   def _check_image_config_type(cls, value: Any) -> Any:
-    if not isinstance(value, ImageConfig):
-      raise ValueError('image_config must be an instance of ImageConfig.')
+    if isinstance(value, GenerateImagesConfig):
+      raise ValueError(
+          'image_config must be an instance of ImageConfig or compatible dict.'
+      )
     return value
 
 
@@ -6244,6 +6299,10 @@ class GenerateImagesConfig(_common.BaseModel):
       default=None,
       description="""Whether to add a watermark to the generated images.""",
   )
+  labels: Optional[dict[str, str]] = Field(
+      default=None,
+      description="""User specified labels to track billing usage.""",
+  )
   image_size: Optional[str] = Field(
       default=None,
       description="""The size of the largest dimension of the generated image.
@@ -6309,6 +6368,9 @@ class GenerateImagesConfigDict(TypedDict, total=False):
   add_watermark: Optional[bool]
   """Whether to add a watermark to the generated images."""
 
+  labels: Optional[dict[str, str]]
+  """User specified labels to track billing usage."""
+
   image_size: Optional[str]
   """The size of the largest dimension of the generated image.
       Supported sizes are 1K and 2K (not supported for Imagen 3 models)."""
@@ -6886,6 +6948,10 @@ class EditImageConfig(_common.BaseModel):
       default=None,
       description="""Whether to add a watermark to the generated images.""",
   )
+  labels: Optional[dict[str, str]] = Field(
+      default=None,
+      description="""User specified labels to track billing usage.""",
+  )
   edit_mode: Optional[EditMode] = Field(
       default=None,
       description="""Describes the editing mode for the request.""",
@@ -6952,6 +7018,9 @@ class EditImageConfigDict(TypedDict, total=False):
   add_watermark: Optional[bool]
   """Whether to add a watermark to the generated images."""
 
+  labels: Optional[dict[str, str]]
+  """User specified labels to track billing usage."""
+
   edit_mode: Optional[EditMode]
   """Describes the editing mode for the request."""
 
@@ -7067,6 +7136,10 @@ class _UpscaleImageAPIConfig(_common.BaseModel):
       output image will have be more different from the input image, but
       with finer details and less noise.""",
   )
+  labels: Optional[dict[str, str]] = Field(
+      default=None,
+      description="""User specified labels to track billing usage.""",
+  )
   number_of_images: Optional[int] = Field(default=None, description="""""")
   mode: Optional[str] = Field(default=None, description="""""")
 
@@ -7106,6 +7179,9 @@ class _UpscaleImageAPIConfigDict(TypedDict, total=False):
       output image will have be more different from the input image, but
       with finer details and less noise."""
 
+  labels: Optional[dict[str, str]]
+  """User specified labels to track billing usage."""
+
   number_of_images: Optional[int]
   """"""
 
@@ -7282,6 +7358,10 @@ class RecontextImageConfig(_common.BaseModel):
   enhance_prompt: Optional[bool] = Field(
       default=None, description="""Whether to use the prompt rewriting logic."""
   )
+  labels: Optional[dict[str, str]] = Field(
+      default=None,
+      description="""User specified labels to track billing usage.""",
+  )
 
 
 class RecontextImageConfigDict(TypedDict, total=False):
@@ -7323,6 +7403,9 @@ class RecontextImageConfigDict(TypedDict, total=False):
   enhance_prompt: Optional[bool]
   """Whether to use the prompt rewriting logic."""
 
+  labels: Optional[dict[str, str]]
+  """User specified labels to track billing usage."""
+
 
 RecontextImageConfigOrDict = Union[
     RecontextImageConfig, RecontextImageConfigDict
@@ -7473,6 +7556,10 @@ class SegmentImageConfig(_common.BaseModel):
       can be set to a decimal value between 0 and 255 non-inclusive.
       Set to -1 for no binary color thresholding.""",
   )
+  labels: Optional[dict[str, str]] = Field(
+      default=None,
+      description="""User specified labels to track billing usage.""",
+  )
 
 
 class SegmentImageConfigDict(TypedDict, total=False):
@@ -7503,6 +7590,9 @@ class SegmentImageConfigDict(TypedDict, total=False):
       can be set to a decimal value between 0 and 255 non-inclusive.
       Set to -1 for no binary color thresholding."""
 
+  labels: Optional[dict[str, str]]
+  """User specified labels to track billing usage."""
+
 
 SegmentImageConfigOrDict = Union[SegmentImageConfig, SegmentImageConfigDict]
 
@@ -8965,6 +9055,7 @@ class GenerateVideosOperation(_common.BaseModel, Operation):
       cls, api_response: Any, is_vertex_ai: bool = False
   ) -> Self:
     """Instantiates a GenerateVideosOperation from an API response."""
+
     if is_vertex_ai:
       response_dict = _GenerateVideosOperation_from_vertex(api_response)
     else:
@@ -10173,6 +10264,71 @@ PartnerModelTuningSpecOrDict = Union[
 ]
 
 
+class VeoHyperParameters(_common.BaseModel):
+  """Hyperparameters for Veo."""
+
+  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.""",
+  )
+  tuning_task: Optional[TuningTask] = Field(
+      default=None,
+      description="""Optional. The tuning task. Either I2V or T2V.""",
+  )
+
+
+class VeoHyperParametersDict(TypedDict, total=False):
+  """Hyperparameters for Veo."""
+
+  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."""
+
+  tuning_task: Optional[TuningTask]
+  """Optional. The tuning task. Either I2V or T2V."""
+
+
+VeoHyperParametersOrDict = Union[VeoHyperParameters, VeoHyperParametersDict]
+
+
+class VeoTuningSpec(_common.BaseModel):
+  """Tuning Spec for Veo Model Tuning."""
+
+  hyper_parameters: Optional[VeoHyperParameters] = Field(
+      default=None, description="""Optional. Hyperparameters for Veo."""
+  )
+  training_dataset_uri: Optional[str] = Field(
+      default=None,
+      description="""Required. Training dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset.""",
+  )
+  validation_dataset_uri: Optional[str] = Field(
+      default=None,
+      description="""Optional. Validation dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset.""",
+  )
+
+
+class VeoTuningSpecDict(TypedDict, total=False):
+  """Tuning Spec for Veo Model Tuning."""
+
+  hyper_parameters: Optional[VeoHyperParametersDict]
+  """Optional. Hyperparameters for Veo."""
+
+  training_dataset_uri: Optional[str]
+  """Required. Training dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset."""
+
+  validation_dataset_uri: Optional[str]
+  """Optional. Validation dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset."""
+
+
+VeoTuningSpecOrDict = Union[VeoTuningSpec, VeoTuningSpecDict]
+
+
 class TuningJob(_common.BaseModel):
   """A tuning job."""
 
@@ -10268,6 +10424,9 @@ class TuningJob(_common.BaseModel):
       default=None,
       description="""Optional. The display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters.""",
   )
+  veo_tuning_spec: Optional[VeoTuningSpec] = Field(
+      default=None, description="""Tuning Spec for Veo Tuning."""
+  )
 
   @property
   def has_ended(self) -> bool:
@@ -10355,6 +10514,9 @@ class TuningJobDict(TypedDict, total=False):
   tuned_model_display_name: Optional[str]
   """Optional. The display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters."""
 
+  veo_tuning_spec: Optional[VeoTuningSpecDict]
+  """Tuning Spec for Veo Tuning."""
+
 
 TuningJobOrDict = Union[TuningJob, TuningJobDict]
 
@@ -12914,6 +13076,10 @@ class UpscaleImageConfig(_common.BaseModel):
       output image will have be more different from the input image, but
       with finer details and less noise.""",
   )
+  labels: Optional[dict[str, str]] = Field(
+      default=None,
+      description="""User specified labels to track billing usage.""",
+  )
 
 
 class UpscaleImageConfigDict(TypedDict, total=False):
@@ -12952,6 +13118,9 @@ class UpscaleImageConfigDict(TypedDict, total=False):
       output image will have be more different from the input image, but
       with finer details and less noise."""
 
+  labels: Optional[dict[str, str]]
+  """User specified labels to track billing usage."""
+
 
 UpscaleImageConfigOrDict = Union[UpscaleImageConfig, UpscaleImageConfigDict]
 
@@ -14633,6 +14802,13 @@ class LiveConnectConfig(_common.BaseModel):
       description="""The speech generation configuration.
       """,
   )
+  thinking_config: Optional[ThinkingConfig] = Field(
+      default=None,
+      description="""Config for thinking features.
+      An error will be returned if this field is set for models that don't
+      support thinking.
+      """,
+  )
   enable_affective_dialog: Optional[bool] = Field(
       default=None,
       description="""If enabled, the model will detect emotions and adapt its responses accordingly.""",
@@ -14738,6 +14914,12 @@ class LiveConnectConfigDict(TypedDict, total=False):
   """The speech generation configuration.
       """
 
+  thinking_config: Optional[ThinkingConfigDict]
+  """Config for thinking features.
+      An error will be returned if this field is set for models that don't
+      support thinking.
+      """
+
   enable_affective_dialog: Optional[bool]
   """If enabled, the model will detect emotions and adapt its responses accordingly."""
 

google/genai/version.py

@@ -13,4 +13,4 @@
 # limitations under the License.
 #
 
-__version__ = '1.40.0' # x-release-please-version
+__version__ = '1.42.0' # x-release-please-version

{google_genai-1.40.0.dist-info → google_genai-1.42.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-genai
-Version: 1.40.0
+Version: 1.42.0
 Summary: GenAI Python SDK
 Author-email: Google LLC <googleapis-packages@google.com>
 License: Apache-2.0
@@ -296,7 +296,7 @@ See the 'Create a client' section above to initialize a client.
 
 ```python
 response = client.models.generate_content(
-    model='gemini-2.0-flash-001', contents='Why is the sky blue?'
+    model='gemini-2.5-flash', contents='Why is the sky blue?'
 )
 print(response.text)
 ```
@@ -313,7 +313,7 @@ python code.
 ```python
 file = client.files.upload(file='a11.txt')
 response = client.models.generate_content(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents=['Could you summarize this file?', file]
 )
 print(response.text)
@@ -617,7 +617,7 @@ print(async_pager[0])
 from google.genai import types
 
 response = client.models.generate_content(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents='Say something bad.',
     config=types.GenerateContentConfig(
         safety_settings=[
@@ -651,7 +651,7 @@ def get_current_weather(location: str) -> str:
 
 
 response = client.models.generate_content(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents='What is the weather like in Boston?',
     config=types.GenerateContentConfig(tools=[get_current_weather]),
 )
@@ -667,7 +667,7 @@ as follows:
 from google.genai import types
 
 response = client.models.generate_content(
-  model='gemini-2.0-flash-001',
+  model='gemini-2.5-flash',
   contents='What is the weather like in Boston?',
   config=types.GenerateContentConfig(
     tools=[get_current_weather],
@@ -714,7 +714,7 @@ function = types.FunctionDeclaration(
 tool = types.Tool(function_declarations=[function])
 
 response = client.models.generate_content(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents='What is the weather like in Boston?',
     config=types.GenerateContentConfig(tools=[tool]),
 )
@@ -758,7 +758,7 @@ function_response_content = types.Content(
 )
 
 response = client.models.generate_content(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents=[
         user_prompt_content,
         function_call_content,
@@ -793,7 +793,7 @@ def get_current_weather(location: str) -> str:
     return "sunny"
 
 response = client.models.generate_content(
-    model="gemini-2.0-flash-001",
+    model="gemini-2.5-flash",
     contents="What is the weather like in Boston?",
     config=types.GenerateContentConfig(
         tools=[get_current_weather],
@@ -823,7 +823,7 @@ def get_current_weather(location: str) -> str:
     return "sunny"
 
 response = client.models.generate_content(
-    model="gemini-2.0-flash-001",
+    model="gemini-2.5-flash",
     contents="What is the weather like in Boston?",
     config=types.GenerateContentConfig(
         tools=[get_current_weather],
@@ -913,7 +913,7 @@ user_profile = {
 }
 
 response = client.models.generate_content(
-    model='gemini-2.0-flash',
+    model='gemini-2.5-flash',
     contents='Give me a random user profile.',
     config={
         'response_mime_type': 'application/json',
@@ -943,7 +943,7 @@ class CountryInfo(BaseModel):
 
 
 response = client.models.generate_content(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents='Give me information for the United States.',
     config=types.GenerateContentConfig(
         response_mime_type='application/json',
@@ -957,7 +957,7 @@ print(response.text)
 from google.genai import types
 
 response = client.models.generate_content(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents='Give me information for the United States.',
     config=types.GenerateContentConfig(
         response_mime_type='application/json',
@@ -995,6 +995,8 @@ You can set response_mime_type to 'text/x.enum' to return one of those enum
 values as the response.
 
 ```python
+from enum import Enum
+
 class InstrumentEnum(Enum):
   PERCUSSION = 'Percussion'
   STRING = 'String'
@@ -1003,7 +1005,7 @@ class InstrumentEnum(Enum):
   KEYBOARD = 'Keyboard'
 
 response = client.models.generate_content(
-      model='gemini-2.0-flash-001',
+      model='gemini-2.5-flash',
       contents='What instrument plays multiple notes at once?',
       config={
           'response_mime_type': 'text/x.enum',
@@ -1029,7 +1031,7 @@ class InstrumentEnum(Enum):
   KEYBOARD = 'Keyboard'
 
 response = client.models.generate_content(
-      model='gemini-2.0-flash-001',
+      model='gemini-2.5-flash',
       contents='What instrument plays multiple notes at once?',
       config={
           'response_mime_type': 'application/json',
@@ -1048,7 +1050,7 @@ to you, rather than being returned as one chunk.
 
 ```python
 for chunk in client.models.generate_content_stream(
-    model='gemini-2.0-flash-001', contents='Tell me a story in 300 words.'
+    model='gemini-2.5-flash', contents='Tell me a story in 300 words.'
 ):
     print(chunk.text, end='')
 ```
@@ -1062,7 +1064,7 @@ you can use the `from_uri` class method to create a `Part` object.
 from google.genai import types
 
 for chunk in client.models.generate_content_stream(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents=[
         'What is this image about?',
         types.Part.from_uri(
@@ -1086,7 +1088,7 @@ with open(YOUR_IMAGE_PATH, 'rb') as f:
     image_bytes = f.read()
 
 for chunk in client.models.generate_content_stream(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents=[
         'What is this image about?',
         types.Part.from_bytes(data=image_bytes, mime_type=YOUR_IMAGE_MIME_TYPE),
@@ -1105,7 +1107,7 @@ of `client.models.generate_content`
 
 ```python
 response = await client.aio.models.generate_content(
-    model='gemini-2.0-flash-001', contents='Tell me a story in 300 words.'
+    model='gemini-2.5-flash', contents='Tell me a story in 300 words.'
 )
 
 print(response.text)
@@ -1116,7 +1118,7 @@ print(response.text)
 
 ```python
 async for chunk in await client.aio.models.generate_content_stream(
-    model='gemini-2.0-flash-001', contents='Tell me a story in 300 words.'
+    model='gemini-2.5-flash', contents='Tell me a story in 300 words.'
 ):
     print(chunk.text, end='')
 ```
@@ -1125,7 +1127,7 @@ async for chunk in await client.aio.models.generate_content_stream(
 
 ```python
 response = client.models.count_tokens(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents='why is the sky blue?',
 )
 print(response)
@@ -1137,7 +1139,7 @@ Compute tokens is only supported in Vertex AI.
 
 ```python
 response = client.models.compute_tokens(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents='why is the sky blue?',
 )
 print(response)
@@ -1147,7 +1149,7 @@ print(response)
 
 ```python
 response = await client.aio.models.count_tokens(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents='why is the sky blue?',
 )
 print(response)
@@ -1156,14 +1158,14 @@ print(response)
 #### Local Count Tokens
 
 ```python
-tokenizer = genai.LocalTokenizer(model_name='gemini-2.0-flash-001')
+tokenizer = genai.LocalTokenizer(model_name='gemini-2.5-flash')
 result = tokenizer.count_tokens("What is your name?")
 ```
 
 #### Local Compute Tokens
 
 ```python
-tokenizer = genai.LocalTokenizer(model_name='gemini-2.0-flash-001')
+tokenizer = genai.LocalTokenizer(model_name='gemini-2.5-flash')
 result = tokenizer.compute_tokens("What is your name?")
 ```
 
@@ -1376,7 +1378,7 @@ that it can reflect on its previous responses (i.e., engage in an ongoing
 ### Send Message (Synchronous Non-Streaming)
 
 ```python
-chat = client.chats.create(model='gemini-2.0-flash-001')
+chat = client.chats.create(model='gemini-2.5-flash')
 response = chat.send_message('tell me a story')
 print(response.text)
 response = chat.send_message('summarize the story you told me in 1 sentence')
@@ -1386,7 +1388,7 @@ print(response.text)
 ### Send Message (Synchronous Streaming)
 
 ```python
-chat = client.chats.create(model='gemini-2.0-flash-001')
+chat = client.chats.create(model='gemini-2.5-flash')
 for chunk in chat.send_message_stream('tell me a story'):
     print(chunk.text)
 ```
@@ -1394,7 +1396,7 @@ for chunk in chat.send_message_stream('tell me a story'):
 ### Send Message (Asynchronous Non-Streaming)
 
 ```python
-chat = client.aio.chats.create(model='gemini-2.0-flash-001')
+chat = client.aio.chats.create(model='gemini-2.5-flash')
 response = await chat.send_message('tell me a story')
 print(response.text)
 ```
@@ -1402,7 +1404,7 @@ print(response.text)
 ### Send Message (Asynchronous Streaming)
 
 ```python
-chat = client.aio.chats.create(model='gemini-2.0-flash-001')
+chat = client.aio.chats.create(model='gemini-2.5-flash')
 async for chunk in await chat.send_message_stream('tell me a story'):
     print(chunk.text)
 ```
@@ -1461,7 +1463,7 @@ else:
     file_uris = [file1.uri, file2.uri]
 
 cached_content = client.caches.create(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     config=types.CreateCachedContentConfig(
         contents=[
             types.Content(
@@ -1496,7 +1498,7 @@ cached_content = client.caches.get(name=cached_content.name)
 from google.genai import types
 
 response = client.models.generate_content(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     contents='Summarize the pdfs',
     config=types.GenerateContentConfig(
         cached_content=cached_content.name,
@@ -1518,7 +1520,7 @@ section above to initialize a client.
 ```python
 from google.genai import types
 
-model = 'gemini-2.0-flash-001'
+model = 'gemini-2.5-flash'
 training_dataset = types.TuningDataset(
   # or gcs_uri=my_vertex_multimodal_dataset
     gcs_uri='gs://cloud-samples-data/ai-platform/generative_ai/gemini-1_5/text/sft_train_data.jsonl',
@@ -1672,7 +1674,7 @@ Vertex AI:
 ```python
 # Specify model and source file only, destination and job display name will be auto-populated
 job = client.batches.create(
-    model='gemini-2.0-flash-001',
+    model='gemini-2.5-flash',
     src='bq://my-project.my-dataset.my-table',  # or "gs://path/to/input/data"
 )
 
@@ -1684,7 +1686,7 @@ Gemini Developer API:
 ```python
 # Create a batch job with inlined requests
 batch_job = client.batches.create(
-    model="gemini-2.0-flash",
+    model="gemini-2.5-flash",
     src=[{
       "contents": [{
         "parts": [{
@@ -1699,7 +1701,7 @@ batch_job = client.batches.create(
 job
 ```
 
-In order to create a batch job with file name. Need to upload a jsonl file.
+In order to create a batch job with file name. Need to upload a json file.
 For example myrequests.json:
 
 ```
@@ -1712,14 +1714,14 @@ Then upload the file.
 ```python
 # Upload the file
 file = client.files.upload(
-    file='myrequest.json',
-    config=types.UploadFileConfig(display_name='test_json')
+    file='myrequests.json',
+    config=types.UploadFileConfig(display_name='test-json')
 )
 
 # Create a batch job with file name
 batch_job = client.batches.create(
     model="gemini-2.0-flash",
-    src="files/file_name",
+    src="files/test-json",
 )
 ```