google-genai 1.31.0__py3-none-any.whl → 1.33.0__py3-none-any.whl

google/genai/models.py

@@ -21,6 +21,7 @@ from typing import Any, AsyncIterator, Awaitable, Iterator, Optional, Union
 from urllib.parse import urlencode
 
 from . import _api_module
+from . import _base_transformers as base_t
 from . import _common
 from . import _extra_utils
 from . import _mcp_utils
@@ -1260,7 +1261,7 @@ def _Image_to_mldev(
     setv(
         to_object,
         ['bytesBase64Encoded'],
-        t.t_bytes(getv(from_object, ['image_bytes'])),
+        base_t.t_bytes(getv(from_object, ['image_bytes'])),
     )
 
   if getv(from_object, ['mime_type']) is not None:
@@ -1269,6 +1270,29 @@ def _Image_to_mldev(
   return to_object
 
 
+def _GenerateVideosSource_to_mldev(
+    from_object: Union[dict[str, Any], object],
+    parent_object: Optional[dict[str, Any]] = None,
+) -> dict[str, Any]:
+  to_object: dict[str, Any] = {}
+  if getv(from_object, ['prompt']) is not None:
+    setv(
+        parent_object, ['instances[0]', 'prompt'], getv(from_object, ['prompt'])
+    )
+
+  if getv(from_object, ['image']) is not None:
+    setv(
+        parent_object,
+        ['instances[0]', 'image'],
+        _Image_to_mldev(getv(from_object, ['image']), to_object),
+    )
+
+  if getv(from_object, ['video']) is not None:
+    raise ValueError('video parameter is not supported in Gemini API.')
+
+  return to_object
+
+
 def _GenerateVideosConfig_to_mldev(
     from_object: Union[dict[str, Any], object],
     parent_object: Optional[dict[str, Any]] = None,
@@ -1306,7 +1330,11 @@ def _GenerateVideosConfig_to_mldev(
     )
 
   if getv(from_object, ['resolution']) is not None:
-    raise ValueError('resolution parameter is not supported in Gemini API.')
+    setv(
+        parent_object,
+        ['parameters', 'resolution'],
+        getv(from_object, ['resolution']),
+    )
 
   if getv(from_object, ['person_generation']) is not None:
     setv(
@@ -1377,6 +1405,15 @@ def _GenerateVideosParameters_to_mldev(
   if getv(from_object, ['video']) is not None:
     raise ValueError('video parameter is not supported in Gemini API.')
 
+  if getv(from_object, ['source']) is not None:
+    setv(
+        to_object,
+        ['config'],
+        _GenerateVideosSource_to_mldev(
+            getv(from_object, ['source']), to_object
+        ),
+    )
+
   if getv(from_object, ['config']) is not None:
     setv(
         to_object,
@@ -2502,7 +2539,7 @@ def _Image_to_vertex(
     setv(
         to_object,
         ['bytesBase64Encoded'],
-        t.t_bytes(getv(from_object, ['image_bytes'])),
+        base_t.t_bytes(getv(from_object, ['image_bytes'])),
     )
 
   if getv(from_object, ['mime_type']) is not None:
@@ -2797,6 +2834,13 @@ def _UpscaleImageAPIConfig_to_vertex(
 ) -> dict[str, Any]:
   to_object: dict[str, Any] = {}
 
+  if getv(from_object, ['output_gcs_uri']) is not None:
+    setv(
+        parent_object,
+        ['parameters', 'storageUri'],
+        getv(from_object, ['output_gcs_uri']),
+    )
+
   if getv(from_object, ['include_rai_reason']) is not None:
     setv(
         parent_object,
@@ -2973,6 +3017,13 @@ def _RecontextImageConfig_to_vertex(
         getv(from_object, ['person_generation']),
     )
 
+  if getv(from_object, ['add_watermark']) is not None:
+    setv(
+        parent_object,
+        ['parameters', 'addWatermark'],
+        getv(from_object, ['add_watermark']),
+    )
+
   if getv(from_object, ['output_mime_type']) is not None:
     setv(
         parent_object,
@@ -3387,7 +3438,7 @@ def _Video_to_vertex(
     setv(
         to_object,
         ['bytesBase64Encoded'],
-        t.t_bytes(getv(from_object, ['video_bytes'])),
+        base_t.t_bytes(getv(from_object, ['video_bytes'])),
     )
 
   if getv(from_object, ['mime_type']) is not None:
@@ -3396,6 +3447,33 @@ def _Video_to_vertex(
   return to_object
 
 
+def _GenerateVideosSource_to_vertex(
+    from_object: Union[dict[str, Any], object],
+    parent_object: Optional[dict[str, Any]] = None,
+) -> dict[str, Any]:
+  to_object: dict[str, Any] = {}
+  if getv(from_object, ['prompt']) is not None:
+    setv(
+        parent_object, ['instances[0]', 'prompt'], getv(from_object, ['prompt'])
+    )
+
+  if getv(from_object, ['image']) is not None:
+    setv(
+        parent_object,
+        ['instances[0]', 'image'],
+        _Image_to_vertex(getv(from_object, ['image']), to_object),
+    )
+
+  if getv(from_object, ['video']) is not None:
+    setv(
+        parent_object,
+        ['instances[0]', 'video'],
+        _Video_to_vertex(getv(from_object, ['video']), to_object),
+    )
+
+  return to_object
+
+
 def _VideoGenerationReferenceImage_to_vertex(
     from_object: Union[dict[str, Any], object],
     parent_object: Optional[dict[str, Any]] = None,
@@ -3553,6 +3631,15 @@ def _GenerateVideosParameters_to_vertex(
         _Video_to_vertex(getv(from_object, ['video']), to_object),
     )
 
+  if getv(from_object, ['source']) is not None:
+    setv(
+        to_object,
+        ['config'],
+        _GenerateVideosSource_to_vertex(
+            getv(from_object, ['source']), to_object
+        ),
+    )
+
   if getv(from_object, ['config']) is not None:
     setv(
         to_object,
@@ -3914,7 +4001,7 @@ def _Image_from_mldev(
     setv(
         to_object,
         ['image_bytes'],
-        t.t_bytes(getv(from_object, ['bytesBase64Encoded'])),
+        base_t.t_bytes(getv(from_object, ['bytesBase64Encoded'])),
     )
 
   if getv(from_object, ['mimeType']) is not None:
@@ -4101,6 +4188,10 @@ def _DeleteModelResponse_from_mldev(
     parent_object: Optional[dict[str, Any]] = None,
 ) -> dict[str, Any]:
   to_object: dict[str, Any] = {}
+  if getv(from_object, ['sdkHttpResponse']) is not None:
+    setv(
+        to_object, ['sdk_http_response'], getv(from_object, ['sdkHttpResponse'])
+    )
 
   return to_object
 
@@ -4140,7 +4231,7 @@ def _Video_from_mldev(
     setv(
         to_object,
         ['video_bytes'],
-        t.t_bytes(getv(from_object, ['video', 'encodedVideo'])),
+        base_t.t_bytes(getv(from_object, ['video', 'encodedVideo'])),
     )
 
   if getv(from_object, ['encoding']) is not None:
@@ -4606,7 +4697,7 @@ def _Image_from_vertex(
     setv(
         to_object,
         ['image_bytes'],
-        t.t_bytes(getv(from_object, ['bytesBase64Encoded'])),
+        base_t.t_bytes(getv(from_object, ['bytesBase64Encoded'])),
     )
 
   if getv(from_object, ['mimeType']) is not None:
@@ -4968,6 +5059,10 @@ def _DeleteModelResponse_from_vertex(
     parent_object: Optional[dict[str, Any]] = None,
 ) -> dict[str, Any]:
   to_object: dict[str, Any] = {}
+  if getv(from_object, ['sdkHttpResponse']) is not None:
+    setv(
+        to_object, ['sdk_http_response'], getv(from_object, ['sdkHttpResponse'])
+    )
 
   return to_object
 
@@ -5016,7 +5111,7 @@ def _Video_from_vertex(
     setv(
         to_object,
         ['video_bytes'],
-        t.t_bytes(getv(from_object, ['bytesBase64Encoded'])),
+        base_t.t_bytes(getv(from_object, ['bytesBase64Encoded'])),
     )
 
   if getv(from_object, ['mimeType']) is not None:
@@ -5165,6 +5260,13 @@ class Models(_api_module.BaseModule):
         'post', path, request_dict, http_options
     )
 
+    if config is not None and getattr(
+        config, 'should_return_http_response', None
+    ):
+      return_value = types.GenerateContentResponse(sdk_http_response=response)
+      self._api_client._verify_response(return_value)
+      return return_value
+
     response_dict = '' if not response.body else json.loads(response.body)
 
     if self._api_client.vertexai:
@@ -5364,13 +5466,7 @@ class Models(_api_module.BaseModule):
       prompt: str,
       config: Optional[types.GenerateImagesConfigOrDict] = None,
   ) -> types.GenerateImagesResponse:
-    """Generates images based on a text description and configuration.
-
-    Args:
-      model (str): The model to use.
-      prompt (str): A text description of the images to generate.
-      config (GenerateImagesConfig): Configuration for generation.
-    """
+    """Private method for generating images."""
 
     parameter_model = types._GenerateImagesParameters(
         model=model,
@@ -5443,47 +5539,7 @@ class Models(_api_module.BaseModule):
       reference_images: list[types._ReferenceImageAPIOrDict],
       config: Optional[types.EditImageConfigOrDict] = None,
   ) -> types.EditImageResponse:
-    """Edits an image based on a text description and configuration.
-
-    Args:
-      model (str): The model to use.
-      prompt (str): A text description of the edit to apply to the image.
-        reference_images (list[Union[RawReferenceImage, MaskReferenceImage,
-        ControlReferenceImage, StyleReferenceImage, SubjectReferenceImage]): The
-        reference images for editing.
-      config (EditImageConfig): Configuration for editing.
-
-    Usage:
-
-    .. code-block:: python
-
-      from google.genai.types import RawReferenceImage, MaskReferenceImage
-
-      raw_ref_image = RawReferenceImage(
-        reference_id=1,
-        reference_image=types.Image.from_file(IMAGE_FILE_PATH),
-      )
-
-      mask_ref_image = MaskReferenceImage(
-        reference_id=2,
-        config=types.MaskReferenceConfig(
-            mask_mode='MASK_MODE_FOREGROUND',
-            mask_dilation=0.06,
-        ),
-      )
-      response = client.models.edit_image(
-        model='imagen-3.0-capability-001',
-        prompt='man with dog',
-        reference_images=[raw_ref_image, mask_ref_image],
-        config=types.EditImageConfig(
-            edit_mode= "EDIT_MODE_INPAINT_INSERTION",
-            number_of_images= 1,
-            include_rai_reason= True,
-        )
-      )
-      response.generated_images[0].image.show()
-      # Shows a man with a dog instead of a cat.
-    """
+    """Private method for editing an image."""
 
     parameter_model = types._EditImageParameters(
         model=model,
@@ -5547,14 +5603,7 @@ class Models(_api_module.BaseModule):
       upscale_factor: str,
       config: Optional[types._UpscaleImageAPIConfigOrDict] = None,
   ) -> types.UpscaleImageResponse:
-    """Upscales an image.
-
-    Args:
-      model (str): The model to use.
-      image (Image): The input image for upscaling.
-      upscale_factor (str): The factor to upscale the image (x2 or x4).
-      config (_UpscaleImageAPIConfig): Configuration for upscaling.
-    """
+    """Private method for upscaling an image."""
 
     parameter_model = types._UpscaleImageAPIParameters(
         model=model,
@@ -6050,7 +6099,9 @@ class Models(_api_module.BaseModule):
     return_value = types.DeleteModelResponse._from_response(
         response=response_dict, kwargs=parameter_model.model_dump()
     )
-
+    return_value.sdk_http_response = types.HttpResponse(
+        headers=response.headers
+    )
     self._api_client._verify_response(return_value)
     return return_value
 
@@ -6235,47 +6286,17 @@ class Models(_api_module.BaseModule):
       prompt: Optional[str] = None,
       image: Optional[types.ImageOrDict] = None,
       video: Optional[types.VideoOrDict] = None,
+      source: Optional[types.GenerateVideosSourceOrDict] = None,
       config: Optional[types.GenerateVideosConfigOrDict] = None,
   ) -> types.GenerateVideosOperation:
-    """Generates videos based on an input (text, image, or video) and configuration.
-
-    The following use cases are supported:
-    1. Text to video generation.
-    2a. Image to video generation (additional text prompt is optional).
-    2b. Image to video generation with frame interpolation (specify last_frame
-    in config).
-    3. Video extension (additional text prompt is optional)
-
-    Args:
-      model: The model to use.
-      prompt: The text prompt for generating the videos. Optional for image to
-        video and video extension use cases.
-      image: The input image for generating the videos. Optional if prompt is
-        provided.
-      video: The input video for video extension use cases. Optional if prompt
-        or image is provided.
-      config: Configuration for generation.
-
-    Usage:
-
-      ```
-      operation = client.models.generate_videos(
-          model="veo-2.0-generate-001",
-          prompt="A neon hologram of a cat driving at top speed",
-      )
-      while not operation.done:
-          time.sleep(10)
-          operation = client.operations.get(operation)
-
-      operation.result.generated_videos[0].video.uri
-      ```
-    """
+    """Private method for generating videos."""
 
     parameter_model = types._GenerateVideosParameters(
         model=model,
         prompt=prompt,
         image=image,
         video=video,
+        source=source,
         config=config,
     )
 
@@ -6794,6 +6815,7 @@ class Models(_api_module.BaseModule):
       config_dct = dict(config)
     api_config = types._UpscaleImageAPIConfigDict(
         http_options=config_dct.get('http_options', None),
+        output_gcs_uri=config_dct.get('output_gcs_uri', None),
         include_rai_reason=config_dct.get('include_rai_reason', None),
         output_mime_type=config_dct.get('output_mime_type', None),
         output_compression_quality=config_dct.get(
@@ -6823,6 +6845,7 @@ class Models(_api_module.BaseModule):
       prompt: Optional[str] = None,
       image: Optional[types.ImageOrDict] = None,
       video: Optional[types.VideoOrDict] = None,
+      source: Optional[types.GenerateVideosSourceOrDict] = None,
       config: Optional[types.GenerateVideosConfigOrDict] = None,
   ) -> types.GenerateVideosOperation:
     """Generates videos based on an input (text, image, or video) and configuration.
@@ -6837,11 +6860,15 @@ class Models(_api_module.BaseModule):
     Args:
       model: The model to use.
       prompt: The text prompt for generating the videos. Optional for image to
-        video and video extension use cases.
+        video and video extension use cases. This argument is deprecated, please
+        use source instead.
       image: The input image for generating the videos. Optional if prompt is
-        provided.
+        provided. This argument is deprecated, please use source instead.
       video: The input video for video extension use cases. Optional if prompt
-        or image is provided.
+        or image is provided. This argument is deprecated, please use source
+        instead.
+      source: The input source for generating the videos (prompt, image, and/or
+        video)
       config: Configuration for generation.
 
     Usage:
@@ -6849,7 +6876,9 @@ class Models(_api_module.BaseModule):
       ```
       operation = client.models.generate_videos(
           model="veo-2.0-generate-001",
-          prompt="A neon hologram of a cat driving at top speed",
+          source=types.GenerateVideosSource(
+              prompt="A neon hologram of a cat driving at top speed",
+          ),
       )
       while not operation.done:
           time.sleep(10)
@@ -6858,11 +6887,17 @@ class Models(_api_module.BaseModule):
       operation.result.generated_videos[0].video.uri
       ```
     """
+    if (prompt or image or video) and source:
+      raise ValueError(
+          'Source and prompt/image/video are mutually exclusive.'
+          + ' Please only use source.'
+      )
     return self._generate_videos(
         model=model,
         prompt=prompt,
         image=image,
         video=video,
+        source=source,
         config=config,
     )
 
@@ -6972,6 +7007,13 @@ class AsyncModels(_api_module.BaseModule):
         'post', path, request_dict, http_options
     )
 
+    if config is not None and getattr(
+        config, 'should_return_http_response', None
+    ):
+      return_value = types.GenerateContentResponse(sdk_http_response=response)
+      self._api_client._verify_response(return_value)
+      return return_value
+
     response_dict = '' if not response.body else json.loads(response.body)
 
     if self._api_client.vertexai:
@@ -7176,13 +7218,7 @@ class AsyncModels(_api_module.BaseModule):
       prompt: str,
       config: Optional[types.GenerateImagesConfigOrDict] = None,
   ) -> types.GenerateImagesResponse:
-    """Generates images based on a text description and configuration.
-
-    Args:
-      model (str): The model to use.
-      prompt (str): A text description of the images to generate.
-      config (GenerateImagesConfig): Configuration for generation.
-    """
+    """Private method for generating images asynchronously."""
 
     parameter_model = types._GenerateImagesParameters(
         model=model,
@@ -7255,47 +7291,7 @@ class AsyncModels(_api_module.BaseModule):
       reference_images: list[types._ReferenceImageAPIOrDict],
       config: Optional[types.EditImageConfigOrDict] = None,
   ) -> types.EditImageResponse:
-    """Edits an image based on a text description and configuration.
-
-    Args:
-      model (str): The model to use.
-      prompt (str): A text description of the edit to apply to the image.
-        reference_images (list[Union[RawReferenceImage, MaskReferenceImage,
-        ControlReferenceImage, StyleReferenceImage, SubjectReferenceImage]): The
-        reference images for editing.
-      config (EditImageConfig): Configuration for editing.
-
-    Usage:
-
-    .. code-block:: python
-
-      from google.genai.types import RawReferenceImage, MaskReferenceImage
-
-      raw_ref_image = RawReferenceImage(
-        reference_id=1,
-        reference_image=types.Image.from_file(IMAGE_FILE_PATH),
-      )
-
-      mask_ref_image = MaskReferenceImage(
-        reference_id=2,
-        config=types.MaskReferenceConfig(
-            mask_mode='MASK_MODE_FOREGROUND',
-            mask_dilation=0.06,
-        ),
-      )
-      response = await client.aio.models.edit_image(
-        model='imagen-3.0-capability-001',
-        prompt='man with dog',
-        reference_images=[raw_ref_image, mask_ref_image],
-        config=types.EditImageConfig(
-            edit_mode= "EDIT_MODE_INPAINT_INSERTION",
-            number_of_images= 1,
-            include_rai_reason= True,
-        )
-      )
-      response.generated_images[0].image.show()
-      # Shows a man with a dog instead of a cat.
-    """
+    """Private method for editing an image asynchronously."""
 
     parameter_model = types._EditImageParameters(
         model=model,
@@ -7359,14 +7355,7 @@ class AsyncModels(_api_module.BaseModule):
       upscale_factor: str,
       config: Optional[types._UpscaleImageAPIConfigOrDict] = None,
   ) -> types.UpscaleImageResponse:
-    """Upscales an image.
-
-    Args:
-      model (str): The model to use.
-      image (Image): The input image for upscaling.
-      upscale_factor (str): The factor to upscale the image (x2 or x4).
-      config (_UpscaleImageAPIConfig): Configuration for upscaling.
-    """
+    """Private method for upscaling an image asynchronously."""
 
     parameter_model = types._UpscaleImageAPIParameters(
         model=model,
@@ -7869,7 +7858,9 @@ class AsyncModels(_api_module.BaseModule):
     return_value = types.DeleteModelResponse._from_response(
         response=response_dict, kwargs=parameter_model.model_dump()
     )
-
+    return_value.sdk_http_response = types.HttpResponse(
+        headers=response.headers
+    )
     self._api_client._verify_response(return_value)
     return return_value
 
@@ -8053,47 +8044,17 @@ class AsyncModels(_api_module.BaseModule):
       prompt: Optional[str] = None,
       image: Optional[types.ImageOrDict] = None,
       video: Optional[types.VideoOrDict] = None,
+      source: Optional[types.GenerateVideosSourceOrDict] = None,
       config: Optional[types.GenerateVideosConfigOrDict] = None,
   ) -> types.GenerateVideosOperation:
-    """Generates videos based on an input (text, image, or video) and configuration.
-
-    The following use cases are supported:
-    1. Text to video generation.
-    2a. Image to video generation (additional text prompt is optional).
-    2b. Image to video generation with frame interpolation (specify last_frame
-    in config).
-    3. Video extension (additional text prompt is optional)
-
-    Args:
-      model: The model to use.
-      prompt: The text prompt for generating the videos. Optional for image to
-        video and video extension use cases.
-      image: The input image for generating the videos. Optional if prompt is
-        provided.
-      video: The input video for video extension use cases. Optional if prompt
-        or image is provided.
-      config: Configuration for generation.
-
-    Usage:
-
-      ```
-      operation = client.models.generate_videos(
-          model="veo-2.0-generate-001",
-          prompt="A neon hologram of a cat driving at top speed",
-      )
-      while not operation.done:
-          time.sleep(10)
-          operation = client.operations.get(operation)
-
-      operation.result.generated_videos[0].video.uri
-      ```
-    """
+    """Private method for generating videos asynchronously."""
 
     parameter_model = types._GenerateVideosParameters(
         model=model,
         prompt=prompt,
         image=image,
         video=video,
+        source=source,
         config=config,
     )
 
@@ -8645,6 +8606,7 @@ class AsyncModels(_api_module.BaseModule):
       config_dct = dict(config)
     api_config = types._UpscaleImageAPIConfigDict(
         http_options=config_dct.get('http_options', None),
+        output_gcs_uri=config_dct.get('output_gcs_uri', None),
         include_rai_reason=config_dct.get('include_rai_reason', None),
         output_mime_type=config_dct.get('output_mime_type', None),
         output_compression_quality=config_dct.get(
@@ -8674,6 +8636,7 @@ class AsyncModels(_api_module.BaseModule):
       prompt: Optional[str] = None,
       image: Optional[types.ImageOrDict] = None,
       video: Optional[types.VideoOrDict] = None,
+      source: Optional[types.GenerateVideosSourceOrDict] = None,
       config: Optional[types.GenerateVideosConfigOrDict] = None,
   ) -> types.GenerateVideosOperation:
     """Generates videos based on an input (text, image, or video) and configuration.
@@ -8688,11 +8651,15 @@ class AsyncModels(_api_module.BaseModule):
     Args:
       model: The model to use.
       prompt: The text prompt for generating the videos. Optional for image to
-        video and video extension use cases.
+        video and video extension use cases. This argument is deprecated, please
+        use source instead.
       image: The input image for generating the videos. Optional if prompt is
-        provided.
+        provided. This argument is deprecated, please use source instead.
       video: The input video for video extension use cases. Optional if prompt
-        or image is provided.
+        or image is provided. This argument is deprecated, please use source
+        instead.
+      source: The input source for generating the videos (prompt, image, and/or
+        video)
       config: Configuration for generation.
 
     Usage:
@@ -8700,7 +8667,9 @@ class AsyncModels(_api_module.BaseModule):
       ```
       operation = client.models.generate_videos(
           model="veo-2.0-generate-001",
-          prompt="A neon hologram of a cat driving at top speed",
+          source=types.GenerateVideosSource(
+              prompt="A neon hologram of a cat driving at top speed",
+          ),
       )
       while not operation.done:
           time.sleep(10)
@@ -8709,10 +8678,16 @@ class AsyncModels(_api_module.BaseModule):
       operation.result.generated_videos[0].video.uri
       ```
     """
+    if (prompt or image or video) and source:
+      raise ValueError(
+          'Source and prompt/image/video are mutually exclusive.'
+          + ' Please only use source.'
+      )
     return await self._generate_videos(
         model=model,
         prompt=prompt,
         image=image,
         video=video,
+        source=source,
         config=config,
     )