| | |
- google.genai._interactions.BaseTransport(builtins.object)
-
- AICoreDynamicTransport
- google.genai.client.Client(builtins.object)
-
- Client
- google.genai.models.Models(google.genai._api_module.BaseModule)
-
- Models
- httpx.AsyncBaseTransport(builtins.object)
-
- AsyncAICoreDynamicTransport
class AICoreDynamicTransport(google.genai._interactions.BaseTransport) |
| |
AICoreDynamicTransport(proxy_client: gen_ai_hub.proxy.core.base.BaseProxyClient, **deployment_selector_kwargs)
Synchronous transport that dynamically resolves deployment URLs per request.
|
| |
- Method resolution order:
- AICoreDynamicTransport
- google.genai._interactions.BaseTransport
- builtins.object
Methods defined here:
- __init__(self, proxy_client: gen_ai_hub.proxy.core.base.BaseProxyClient, **deployment_selector_kwargs)
- Transport constructor.
:param proxy_client: The proxy client used to select deployments.
:type proxy_client: BaseProxyClient
- close(self)
- Closes the inner transport.
- get_selector_kwargs(self)
- Get the deployment selector kwargs.
:return: The deployment selector kwargs.
:rtype: dict
- handle_request(self, request: httpx.Request) -> httpx.Response
- Handles the request by rewriting it to route through the appropriate AI Core deployment.
:param request: The original HTTPX request.
:type request: httpx.Request
:return: The HTTPX response from the AI Core deployment.
:rtype: httpx.Response
Methods inherited from google.genai._interactions.BaseTransport:
- __enter__(self: 'T') -> 'T'
- __exit__(self, exc_type: 'type[BaseException] | None' = None, exc_value: 'BaseException | None' = None, traceback: 'TracebackType | None' = None) -> 'None'
Data descriptors inherited from google.genai._interactions.BaseTransport:
- __dict__
- dictionary for instance variables (if defined)
- __weakref__
- list of weak references to the object (if defined)
|
class AsyncAICoreDynamicTransport(httpx.AsyncBaseTransport) |
| |
AsyncAICoreDynamicTransport(proxy_client: gen_ai_hub.proxy.core.base.BaseProxyClient, **deployment_selector_kwargs)
Asynchronous transport that dynamically resolves deployment URLs per request.
|
| |
- Method resolution order:
- AsyncAICoreDynamicTransport
- httpx.AsyncBaseTransport
- builtins.object
Methods defined here:
- __init__(self, proxy_client: gen_ai_hub.proxy.core.base.BaseProxyClient, **deployment_selector_kwargs)
- Transport constructor.
:param proxy_client: The proxy client used to select deployments.
:type proxy_client: BaseProxyClient
- async aclose(self)
- Closes the inner transport.
- get_selector_kwargs(self)
- get the deployment selector kwargs.
:return: The deployment selector kwargs.
:rtype: dict
- async handle_async_request(self, request: httpx.Request) -> httpx.Response
- Handles the request by rewriting it to route through the appropriate AI Core deployment.
:param request: The original HTTPX request.
:type request: httpx.Request
:return: The HTTPX response from the AI Core deployment.
:rtype: httpx.Response
Methods inherited from httpx.AsyncBaseTransport:
- async __aenter__(self: 'A') -> 'A'
- async __aexit__(self, exc_type: 'type[BaseException] | None' = None, exc_value: 'BaseException | None' = None, traceback: 'TracebackType | None' = None) -> 'None'
Data descriptors inherited from httpx.AsyncBaseTransport:
- __dict__
- dictionary for instance variables (if defined)
- __weakref__
- list of weak references to the object (if defined)
|
class Client(google.genai.client.Client) |
| |
Client(vertexai: bool = True, project: str = 'placeholder', location: str = 'placeholder', deployment_id: str = '', config_id: str = '', config_name: str = '', proxy_client: gen_ai_hub.proxy.core.base.BaseProxyClient = None, timeout: int = None, **kwargs)
Unified, native-feeling client that dynamically routes requests
through SAP AI Core deployments based on the requested identifiers e.g. model name.
|
| |
- Method resolution order:
- Client
- google.genai.client.Client
- builtins.object
Methods defined here:
- __init__(self, vertexai: bool = True, project: str = 'placeholder', location: str = 'placeholder', deployment_id: str = '', config_id: str = '', config_name: str = '', proxy_client: gen_ai_hub.proxy.core.base.BaseProxyClient = None, timeout: int = None, **kwargs)
- Initializes the Client.
:param vertexai: to indicate Vertex AI usage, defaults to True
:type vertexai: bool, optional
:param project: the GCP project, defaults to "placeholder"
:type project: str, optional
:param location: the GCP location, defaults to "placeholder"
:type location: str, optional
:param deployment_id: the deployment identifier, defaults to ""
:type deployment_id: str, optional
:param config_id: the configuration identifier, defaults to ""
:type config_id: str, optional
:param config_name: the configuration name, defaults to ""
:type config_name: str, optional
:param proxy_client: the proxy client to use, defaults to None
:type proxy_client: BaseProxyClient, optional
:param timeout: the request timeout, defaults to None
:type timeout: int, optional
Methods inherited from google.genai.client.Client:
- __del__(self) -> None
- __enter__(self) -> 'Client'
- __exit__(self, exc_type: Optional[Exception], exc_value: Optional[Exception], traceback: Optional[traceback]) -> None
- close(self) -> None
- Closes the synchronous client explicitly.
However, it doesn't close the async client, which can be closed using the
Client.aio.aclose() method or using the async context manager.
Usage:
.. code-block:: python
from google.genai import Client
client = Client(
vertexai=True, project='my-project-id', location='us-central1'
)
response_1 = client.models.generate_content(
model='gemini-2.0-flash',
contents='Hello World',
)
response_2 = client.models.generate_content(
model='gemini-2.0-flash',
contents='Hello World',
)
# Close the client to release resources.
client.close()
Readonly properties inherited from google.genai.client.Client:
- aio
- auth_tokens
- batches
- caches
- chats
- file_search_stores
- files
- interactions
- models
- operations
- tunings
- vertexai
- Returns whether the client is using the Vertex AI API.
- webhooks
Data descriptors inherited from google.genai.client.Client:
- __dict__
- dictionary for instance variables (if defined)
- __weakref__
- list of weak references to the object (if defined)
|
class Models(google.genai.models.Models) |
| |
Models(api_client_: google.genai._api_client.BaseApiClient)
Class that extends the original Google Models class for patch embed_content method.
|
| |
- Method resolution order:
- Models
- google.genai.models.Models
- google.genai._api_module.BaseModule
- builtins.object
Methods defined here:
- embed_content(self, *, model: str, contents: Union[google.genai.types.Content, str, google.genai.types.File, google.genai.types.Part, list[Union[str, google.genai.types.File, google.genai.types.Part]], list[Union[google.genai.types.Content, str, google.genai.types.File, google.genai.types.Part, list[Union[str, google.genai.types.File, google.genai.types.Part]]]], google.genai.types.ContentDict, google.genai.types.FileDict, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]], list[Union[google.genai.types.Content, google.genai.types.ContentDict, str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]]]]], config: Union[google.genai.types.EmbedContentConfig, google.genai.types.EmbedContentConfigDict, NoneType] = None) -> google.genai.types.EmbedContentResponse
- Need for add model version for "gemini-embedding" model.
Methods inherited from google.genai.models.Models:
- compute_tokens(self, *, model: str, contents: Union[google.genai.types.Content, str, google.genai.types.File, google.genai.types.Part, list[Union[str, google.genai.types.File, google.genai.types.Part]], list[Union[google.genai.types.Content, str, google.genai.types.File, google.genai.types.Part, list[Union[str, google.genai.types.File, google.genai.types.Part]]]], google.genai.types.ContentDict, google.genai.types.FileDict, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]], list[Union[google.genai.types.Content, google.genai.types.ContentDict, str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]]]]], config: Union[google.genai.types.ComputeTokensConfig, google.genai.types.ComputeTokensConfigDict, NoneType] = None) -> google.genai.types.ComputeTokensResponse
- Given a list of contents, returns a corresponding TokensInfo containing the
list of tokens and list of token ids.
This method is not supported by the Gemini Developer API.
Args:
model (str): The model to use.
contents (list[shared.Content]): The content to compute tokens for.
Usage:
.. code-block:: python
response = client.models.compute_tokens(
model='gemini-2.0-flash',
contents='What is your name?',
)
print(response)
# tokens_info=[TokensInfo(role='user', token_ids=['1841', ...],
# tokens=[b'What', b' is', b' your', b' name', b'?'])]
- count_tokens(self, *, model: str, contents: Union[google.genai.types.Content, str, google.genai.types.File, google.genai.types.Part, list[Union[str, google.genai.types.File, google.genai.types.Part]], list[Union[google.genai.types.Content, str, google.genai.types.File, google.genai.types.Part, list[Union[str, google.genai.types.File, google.genai.types.Part]]]], google.genai.types.ContentDict, google.genai.types.FileDict, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]], list[Union[google.genai.types.Content, google.genai.types.ContentDict, str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]]]]], config: Union[google.genai.types.CountTokensConfig, google.genai.types.CountTokensConfigDict, NoneType] = None) -> google.genai.types.CountTokensResponse
- Counts the number of tokens in the given content.
Multimodal input is supported for Gemini models.
Args:
model (str): The model to use for counting tokens.
contents (list[types.Content]): The content to count tokens for.
config (CountTokensConfig): The configuration for counting tokens.
Usage:
.. code-block:: python
response = client.models.count_tokens(
model='gemini-2.0-flash',
contents='What is your name?',
)
print(response)
# total_tokens=5 cached_content_token_count=None
- delete(self, *, model: str, config: Union[google.genai.types.DeleteModelConfig, google.genai.types.DeleteModelConfigDict, NoneType] = None) -> google.genai.types.DeleteModelResponse
- edit_image(self, *, model: str, prompt: str, reference_images: list[typing.Union[google.genai.types._ReferenceImageAPI, google.genai.types._ReferenceImageAPIDict]], config: Union[google.genai.types.EditImageConfig, google.genai.types.EditImageConfigDict, NoneType] = None) -> google.genai.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.
- generate_content(self, *, model: str, contents: Union[google.genai.types.Content, google.genai.types.ContentDict, str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]], list[Union[google.genai.types.Content, google.genai.types.ContentDict, str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]]]]], config: Union[google.genai.types.GenerateContentConfig, google.genai.types.GenerateContentConfigDict, NoneType] = None) -> google.genai.types.GenerateContentResponse
- Makes an API request to generate content using a model.
For the `model` parameter, supported formats for Vertex AI API include:
- The Gemini model ID, for example: 'gemini-2.0-flash'
- The full resource name starts with 'projects/', for example:
'projects/my-project-id/locations/us-central1/publishers/google/models/gemini-2.0-flash'
- The partial resource name with 'publishers/', for example:
'publishers/google/models/gemini-2.0-flash' or
- `/` separated publisher and model name, for example:
'google/gemini-2.0-flash'
For the `model` parameter, supported formats for Gemini API include:
- The Gemini model ID, for example: 'gemini-2.0-flash'
- The model name starts with 'models/', for example:
'models/gemini-2.0-flash'
- For tuned models, the model name starts with 'tunedModels/',
for example:
'tunedModels/1234567890123456789'
Some models support multimodal input and output.
Built-in MCP support is an experimental feature.
Usage:
.. code-block:: python
from google.genai import types
from google import genai
client = genai.Client(
vertexai=True, project='my-project-id', location='us-central1'
)
response = client.models.generate_content(
model='gemini-2.0-flash',
contents='''What is a good name for a flower shop that specializes in
selling bouquets of dried flowers?'''
)
print(response.text)
# **Elegant & Classic:**
# * The Dried Bloom
# * Everlasting Florals
# * Timeless Petals
response = client.models.generate_content(
model='gemini-2.0-flash',
contents=[
types.Part.from_text(text='What is shown in this image?'),
types.Part.from_uri(file_uri='gs://generativeai-downloads/images/scones.jpg',
mime_type='image/jpeg')
]
)
print(response.text)
# The image shows a flat lay arrangement of freshly baked blueberry
# scones.
- generate_content_stream(self, *, model: str, contents: Union[google.genai.types.Content, google.genai.types.ContentDict, str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]], list[Union[google.genai.types.Content, google.genai.types.ContentDict, str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict, list[Union[str, google.genai.types.File, google.genai.types.FileDict, google.genai.types.Part, google.genai.types.PartDict]]]]], config: Union[google.genai.types.GenerateContentConfig, google.genai.types.GenerateContentConfigDict, NoneType] = None) -> Iterator[google.genai.types.GenerateContentResponse]
- Makes an API request to generate content using a model and yields the model's response in chunks.
For the `model` parameter, supported formats for Vertex AI API include:
- The Gemini model ID, for example: 'gemini-2.0-flash'
- The full resource name starts with 'projects/', for example:
'projects/my-project-id/locations/us-central1/publishers/google/models/gemini-2.0-flash'
- The partial resource name with 'publishers/', for example:
'publishers/google/models/gemini-2.0-flash' or
- `/` separated publisher and model name, for example:
'google/gemini-2.0-flash'
For the `model` parameter, supported formats for Gemini API include:
- The Gemini model ID, for example: 'gemini-2.0-flash'
- The model name starts with 'models/', for example:
'models/gemini-2.0-flash'
- For tuned models, the model name starts with 'tunedModels/',
for example:
'tunedModels/1234567890123456789'
Some models support multimodal input and output.
Built-in MCP support is an experimental feature.
Usage:
.. code-block:: python
from google.genai import types
from google import genai
client = genai.Client(
vertexai=True, project='my-project-id', location='us-central1'
)
for chunk in client.models.generate_content_stream(
model='gemini-2.0-flash',
contents='''What is a good name for a flower shop that specializes in
selling bouquets of dried flowers?'''
):
print(chunk.text)
# **Elegant & Classic:**
# * The Dried Bloom
# * Everlasting Florals
# * Timeless Petals
for chunk in client.models.generate_content_stream(
model='gemini-2.0-flash',
contents=[
types.Part.from_text('What is shown in this image?'),
types.Part.from_uri('gs://generativeai-downloads/images/scones.jpg',
'image/jpeg')
]
):
print(chunk.text)
# The image shows a flat lay arrangement of freshly baked blueberry
# scones.
- generate_images(self, *, model: str, prompt: str, config: Union[google.genai.types.GenerateImagesConfig, google.genai.types.GenerateImagesConfigDict, NoneType] = None) -> google.genai.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.
Usage:
.. code-block:: python
response = client.models.generate_images(
model='imagen-3.0-generate-002',
prompt='Man with a dog',
config=types.GenerateImagesConfig(
number_of_images= 1,
include_rai_reason= True,
)
)
response.generated_images[0].image.show()
# Shows a man with a dog.
- generate_videos(self, *, model: str, prompt: Optional[str] = None, image: Union[google.genai.types.Image, google.genai.types.ImageDict, NoneType] = None, video: Union[google.genai.types.Video, google.genai.types.VideoDict, NoneType] = None, source: Union[google.genai.types.GenerateVideosSource, google.genai.types.GenerateVideosSourceDict, NoneType] = None, config: Union[google.genai.types.GenerateVideosConfig, google.genai.types.GenerateVideosConfigDict, NoneType] = None) -> google.genai.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. This argument is deprecated, please
use source instead.
image: The input image for generating the videos. Optional if prompt is
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. 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:
```
operation = client.models.generate_videos(
model="veo-2.0-generate-001",
source=types.GenerateVideosSource(
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
```
- get(self, *, model: str, config: Union[google.genai.types.GetModelConfig, google.genai.types.GetModelConfigDict, NoneType] = None) -> google.genai.types.Model
- list(self, *, config: Union[google.genai.types.ListModelsConfig, google.genai.types.ListModelsConfigDict, NoneType] = None) -> google.genai.pagers.Pager[google.genai.types.Model]
- Makes an API request to list the available models.
If `query_base` is set to True in the config or not set (default), the
API will return all available base models. If set to False, it will return
all tuned models.
Args:
config (ListModelsConfigOrDict): Configuration for retrieving models.
Usage:
.. code-block:: python
response=client.models.list(config={'page_size': 5})
print(response.page)
# [Model(name='projects/./locations/./models/123', display_name='my_model'
response=client.models.list(config={'page_size': 5, 'query_base': True})
print(response.page)
# [Model(name='publishers/google/models/gemini-2.0-flash-exp' ...
- recontext_image(self, *, model: str, source: Union[google.genai.types.RecontextImageSource, google.genai.types.RecontextImageSourceDict], config: Union[google.genai.types.RecontextImageConfig, google.genai.types.RecontextImageConfigDict, NoneType] = None) -> google.genai.types.RecontextImageResponse
- Recontextualizes an image.
There is one type of recontextualization currently supported:
1) Virtual Try-On: Generate images of persons modeling fashion products.
Args:
model (str): The model to use.
source (RecontextImageSource): An object containing the source inputs
(prompt, person_image, product_images) for image recontext. prompt is
behind an allowlist. person_image is required. product_images is
required. Only one product image is supported currently.
config (RecontextImageConfig): Configuration for recontextualization.
Usage:
```
virtual_try_on_response = client.models.recontext_image(
model="virtual-try-on-001",
source=types.RecontextImageSource(
person_image=types.Image.from_file(IMAGE1_FILE_PATH),
product_images=[types.ProductImage.from_file(IMAGE2_FILE_PATH)],
),
config=types.RecontextImageConfig(
number_of_images=1,
),
)
image = virtual_try_on_response.generated_images[0].image
```
- segment_image(self, *, model: str, source: Union[google.genai.types.SegmentImageSource, google.genai.types.SegmentImageSourceDict], config: Union[google.genai.types.SegmentImageConfig, google.genai.types.SegmentImageConfigDict, NoneType] = None) -> google.genai.types.SegmentImageResponse
- Segments an image, creating a mask of a specified area.
Args:
model (str): The model to use.
source (SegmentImageSource): An object containing the source inputs
(prompt, image, scribble_image) for image segmentation. The prompt is
required for prompt mode and semantic mode, disallowed for other modes.
scribble_image is required for the interactive mode, disallowed for
other modes.
config (SegmentImageConfig): Configuration for segmentation.
Usage:
```
response = client.models.segment_image(
model="image-segmentation-001",
source=types.SegmentImageSource(
image=types.Image.from_file(IMAGE_FILE_PATH),
),
)
mask_image = response.generated_masks[0].mask
```
- update(self, *, model: str, config: Union[google.genai.types.UpdateModelConfig, google.genai.types.UpdateModelConfigDict, NoneType] = None) -> google.genai.types.Model
- upscale_image(self, *, model: str, image: Union[google.genai.types.Image, google.genai.types.ImageDict], upscale_factor: str, config: Union[google.genai.types.UpscaleImageConfig, google.genai.types.UpscaleImageConfigDict, NoneType] = None) -> google.genai.types.UpscaleImageResponse
- Makes an API request to upscale a provided 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 (UpscaleImageConfig): Configuration for upscaling.
Usage:
.. code-block:: python
from google.genai.types import Image
IMAGE_FILE_PATH="my-image.png"
response=client.models.upscale_image(
model='imagen-3.0-generate-001',
image=types.Image.from_file(IMAGE_FILE_PATH),
upscale_factor='x2',
)
response.generated_images[0].image.show()
# Opens my-image.png which is upscaled by a factor of 2.
Methods inherited from google.genai._api_module.BaseModule:
- __init__(self, api_client_: google.genai._api_client.BaseApiClient)
- Initialize self. See help(type(self)) for accurate signature.
Readonly properties inherited from google.genai._api_module.BaseModule:
- vertexai
Data descriptors inherited from google.genai._api_module.BaseModule:
- __dict__
- dictionary for instance variables (if defined)
- __weakref__
- list of weak references to the object (if defined)
| |