As of January 1, 2020 this library no longer supports Python 2 on the latest released version.
Library versions released prior to that date will continue to be available. For more information please
visit Python 2 support on Google Cloud.
Source code for google.ai.generativelanguage_v1.services.generative_service.async_client
# -*- coding: utf-8 -*-
# Copyright 2025 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from collections import OrderedDict
import logging as std_logging
import re
from typing import (
AsyncIterable,
Awaitable,
Callable,
Dict,
Mapping,
MutableMapping,
MutableSequence,
Optional,
Sequence,
Tuple,
Type,
Union,
)
from google.api_core import exceptions as core_exceptions
from google.api_core import gapic_v1
from google.api_core import retry_async as retries
from google.api_core.client_options import ClientOptions
from google.auth import credentials as ga_credentials # type: ignore
from google.oauth2 import service_account # type: ignore
import google.protobuf
from google.ai.generativelanguage_v1 import gapic_version as package_version
try:
OptionalRetry = Union[retries.AsyncRetry, gapic_v1.method._MethodDefault, None]
except AttributeError: # pragma: NO COVER
OptionalRetry = Union[retries.AsyncRetry, object, None] # type: ignore
from google.longrunning import operations_pb2 # type: ignore
from google.ai.generativelanguage_v1.types import content
from google.ai.generativelanguage_v1.types import content as gag_content
from google.ai.generativelanguage_v1.types import generative_service
from .client import GenerativeServiceClient
from .transports.base import DEFAULT_CLIENT_INFO, GenerativeServiceTransport
from .transports.grpc_asyncio import GenerativeServiceGrpcAsyncIOTransport
try:
from google.api_core import client_logging # type: ignore
CLIENT_LOGGING_SUPPORTED = True # pragma: NO COVER
except ImportError: # pragma: NO COVER
CLIENT_LOGGING_SUPPORTED = False
_LOGGER = std_logging.getLogger(__name__)
[docs]class GenerativeServiceAsyncClient:
"""API for using Large Models that generate multimodal content
and have additional capabilities beyond text generation.
"""
_client: GenerativeServiceClient
# Copy defaults from the synchronous client for use here.
# Note: DEFAULT_ENDPOINT is deprecated. Use _DEFAULT_ENDPOINT_TEMPLATE instead.
DEFAULT_ENDPOINT = GenerativeServiceClient.DEFAULT_ENDPOINT
DEFAULT_MTLS_ENDPOINT = GenerativeServiceClient.DEFAULT_MTLS_ENDPOINT
_DEFAULT_ENDPOINT_TEMPLATE = GenerativeServiceClient._DEFAULT_ENDPOINT_TEMPLATE
_DEFAULT_UNIVERSE = GenerativeServiceClient._DEFAULT_UNIVERSE
model_path = staticmethod(GenerativeServiceClient.model_path)
parse_model_path = staticmethod(GenerativeServiceClient.parse_model_path)
common_billing_account_path = staticmethod(
GenerativeServiceClient.common_billing_account_path
)
parse_common_billing_account_path = staticmethod(
GenerativeServiceClient.parse_common_billing_account_path
)
common_folder_path = staticmethod(GenerativeServiceClient.common_folder_path)
parse_common_folder_path = staticmethod(
GenerativeServiceClient.parse_common_folder_path
)
common_organization_path = staticmethod(
GenerativeServiceClient.common_organization_path
)
parse_common_organization_path = staticmethod(
GenerativeServiceClient.parse_common_organization_path
)
common_project_path = staticmethod(GenerativeServiceClient.common_project_path)
parse_common_project_path = staticmethod(
GenerativeServiceClient.parse_common_project_path
)
common_location_path = staticmethod(GenerativeServiceClient.common_location_path)
parse_common_location_path = staticmethod(
GenerativeServiceClient.parse_common_location_path
)
[docs] @classmethod
def from_service_account_info(cls, info: dict, *args, **kwargs):
"""Creates an instance of this client using the provided credentials
info.
Args:
info (dict): The service account private key info.
args: Additional arguments to pass to the constructor.
kwargs: Additional arguments to pass to the constructor.
Returns:
GenerativeServiceAsyncClient: The constructed client.
"""
return GenerativeServiceClient.from_service_account_info.__func__(GenerativeServiceAsyncClient, info, *args, **kwargs) # type: ignore
[docs] @classmethod
def from_service_account_file(cls, filename: str, *args, **kwargs):
"""Creates an instance of this client using the provided credentials
file.
Args:
filename (str): The path to the service account private key json
file.
args: Additional arguments to pass to the constructor.
kwargs: Additional arguments to pass to the constructor.
Returns:
GenerativeServiceAsyncClient: The constructed client.
"""
return GenerativeServiceClient.from_service_account_file.__func__(GenerativeServiceAsyncClient, filename, *args, **kwargs) # type: ignore
from_service_account_json = from_service_account_file
[docs] @classmethod
def get_mtls_endpoint_and_cert_source(
cls, client_options: Optional[ClientOptions] = None
):
"""Return the API endpoint and client cert source for mutual TLS.
The client cert source is determined in the following order:
(1) if `GOOGLE_API_USE_CLIENT_CERTIFICATE` environment variable is not "true", the
client cert source is None.
(2) if `client_options.client_cert_source` is provided, use the provided one; if the
default client cert source exists, use the default one; otherwise the client cert
source is None.
The API endpoint is determined in the following order:
(1) if `client_options.api_endpoint` if provided, use the provided one.
(2) if `GOOGLE_API_USE_CLIENT_CERTIFICATE` environment variable is "always", use the
default mTLS endpoint; if the environment variable is "never", use the default API
endpoint; otherwise if client cert source exists, use the default mTLS endpoint, otherwise
use the default API endpoint.
More details can be found at https://google.aip.dev/auth/4114.
Args:
client_options (google.api_core.client_options.ClientOptions): Custom options for the
client. Only the `api_endpoint` and `client_cert_source` properties may be used
in this method.
Returns:
Tuple[str, Callable[[], Tuple[bytes, bytes]]]: returns the API endpoint and the
client cert source to use.
Raises:
google.auth.exceptions.MutualTLSChannelError: If any errors happen.
"""
return GenerativeServiceClient.get_mtls_endpoint_and_cert_source(client_options) # type: ignore
@property
def transport(self) -> GenerativeServiceTransport:
"""Returns the transport used by the client instance.
Returns:
GenerativeServiceTransport: The transport used by the client instance.
"""
return self._client.transport
@property
def api_endpoint(self):
"""Return the API endpoint used by the client instance.
Returns:
str: The API endpoint used by the client instance.
"""
return self._client._api_endpoint
@property
def universe_domain(self) -> str:
"""Return the universe domain used by the client instance.
Returns:
str: The universe domain used
by the client instance.
"""
return self._client._universe_domain
get_transport_class = GenerativeServiceClient.get_transport_class
def __init__(
self,
*,
credentials: Optional[ga_credentials.Credentials] = None,
transport: Optional[
Union[
str,
GenerativeServiceTransport,
Callable[..., GenerativeServiceTransport],
]
] = "grpc_asyncio",
client_options: Optional[ClientOptions] = None,
client_info: gapic_v1.client_info.ClientInfo = DEFAULT_CLIENT_INFO,
) -> None:
"""Instantiates the generative service async client.
Args:
credentials (Optional[google.auth.credentials.Credentials]): The
authorization credentials to attach to requests. These
credentials identify the application to the service; if none
are specified, the client will attempt to ascertain the
credentials from the environment.
transport (Optional[Union[str,GenerativeServiceTransport,Callable[..., GenerativeServiceTransport]]]):
The transport to use, or a Callable that constructs and returns a new transport to use.
If a Callable is given, it will be called with the same set of initialization
arguments as used in the GenerativeServiceTransport constructor.
If set to None, a transport is chosen automatically.
client_options (Optional[Union[google.api_core.client_options.ClientOptions, dict]]):
Custom options for the client.
1. The ``api_endpoint`` property can be used to override the
default endpoint provided by the client when ``transport`` is
not explicitly provided. Only if this property is not set and
``transport`` was not explicitly provided, the endpoint is
determined by the GOOGLE_API_USE_MTLS_ENDPOINT environment
variable, which have one of the following values:
"always" (always use the default mTLS endpoint), "never" (always
use the default regular endpoint) and "auto" (auto-switch to the
default mTLS endpoint if client certificate is present; this is
the default value).
2. If the GOOGLE_API_USE_CLIENT_CERTIFICATE environment variable
is "true", then the ``client_cert_source`` property can be used
to provide a client certificate for mTLS transport. If
not provided, the default SSL client certificate will be used if
present. If GOOGLE_API_USE_CLIENT_CERTIFICATE is "false" or not
set, no client certificate will be used.
3. The ``universe_domain`` property can be used to override the
default "googleapis.com" universe. Note that ``api_endpoint``
property still takes precedence; and ``universe_domain`` is
currently not supported for mTLS.
client_info (google.api_core.gapic_v1.client_info.ClientInfo):
The client info used to send a user-agent string along with
API requests. If ``None``, then default info will be used.
Generally, you only need to set this if you're developing
your own client library.
Raises:
google.auth.exceptions.MutualTlsChannelError: If mutual TLS transport
creation failed for any reason.
"""
self._client = GenerativeServiceClient(
credentials=credentials,
transport=transport,
client_options=client_options,
client_info=client_info,
)
if CLIENT_LOGGING_SUPPORTED and _LOGGER.isEnabledFor(
std_logging.DEBUG
): # pragma: NO COVER
_LOGGER.debug(
"Created client `google.ai.generativelanguage_v1.GenerativeServiceAsyncClient`.",
extra={
"serviceName": "google.ai.generativelanguage.v1.GenerativeService",
"universeDomain": getattr(
self._client._transport._credentials, "universe_domain", ""
),
"credentialsType": f"{type(self._client._transport._credentials).__module__}.{type(self._client._transport._credentials).__qualname__}",
"credentialsInfo": getattr(
self.transport._credentials, "get_cred_info", lambda: None
)(),
}
if hasattr(self._client._transport, "_credentials")
else {
"serviceName": "google.ai.generativelanguage.v1.GenerativeService",
"credentialsType": None,
},
)
[docs] async def generate_content(
self,
request: Optional[
Union[generative_service.GenerateContentRequest, dict]
] = None,
*,
model: Optional[str] = None,
contents: Optional[MutableSequence[content.Content]] = None,
retry: OptionalRetry = gapic_v1.method.DEFAULT,
timeout: Union[float, object] = gapic_v1.method.DEFAULT,
metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
) -> generative_service.GenerateContentResponse:
r"""Generates a model response given an input
``GenerateContentRequest``. Refer to the `text generation
guide <https://ai.google.dev/gemini-api/docs/text-generation>`__
for detailed usage information. Input capabilities differ
between models, including tuned models. Refer to the `model
guide <https://ai.google.dev/gemini-api/docs/models/gemini>`__
and `tuning
guide <https://ai.google.dev/gemini-api/docs/model-tuning>`__
for details.
.. code-block:: python
# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
# client as shown in:
# https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1
async def sample_generate_content():
# Create a client
client = generativelanguage_v1.GenerativeServiceAsyncClient()
# Initialize request argument(s)
request = generativelanguage_v1.GenerateContentRequest(
model="model_value",
)
# Make the request
response = await client.generate_content(request=request)
# Handle the response
print(response)
Args:
request (Optional[Union[google.ai.generativelanguage_v1.types.GenerateContentRequest, dict]]):
The request object. Request to generate a completion from
the model.
model (:class:`str`):
Required. The name of the ``Model`` to use for
generating the completion.
Format: ``models/{model}``.
This corresponds to the ``model`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
contents (:class:`MutableSequence[google.ai.generativelanguage_v1.types.Content]`):
Required. The content of the current conversation with
the model.
For single-turn queries, this is a single instance. For
multi-turn queries like
`chat <https://ai.google.dev/gemini-api/docs/text-generation#chat>`__,
this is a repeated field that contains the conversation
history and the latest request.
This corresponds to the ``contents`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
retry (google.api_core.retry_async.AsyncRetry): Designation of what errors, if any,
should be retried.
timeout (float): The timeout for this request.
metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
sent along with the request as metadata. Normally, each value must be of type `str`,
but for metadata keys ending with the suffix `-bin`, the corresponding values must
be of type `bytes`.
Returns:
google.ai.generativelanguage_v1.types.GenerateContentResponse:
Response from the model supporting multiple candidate
responses.
Safety ratings and content filtering are reported for
both prompt in
GenerateContentResponse.prompt_feedback and for each
candidate in finish_reason and in safety_ratings. The
API: - Returns either all requested candidates or
none of them - Returns no candidates at all only if
there was something wrong with the prompt (check
prompt_feedback) - Reports feedback on each candidate
in finish_reason and safety_ratings.
"""
# Create or coerce a protobuf request object.
# - Quick check: If we got a request object, we should *not* have
# gotten any keyword arguments that map to the request.
flattened_params = [model, contents]
has_flattened_params = (
len([param for param in flattened_params if param is not None]) > 0
)
if request is not None and has_flattened_params:
raise ValueError(
"If the `request` argument is set, then none of "
"the individual field arguments should be set."
)
# - Use the request object if provided (there's no risk of modifying the input as
# there are no flattened fields), or create one.
if not isinstance(request, generative_service.GenerateContentRequest):
request = generative_service.GenerateContentRequest(request)
# If we have keyword arguments corresponding to fields on the
# request, apply these.
if model is not None:
request.model = model
if contents:
request.contents.extend(contents)
# Wrap the RPC method; this adds retry and timeout information,
# and friendly error handling.
rpc = self._client._transport._wrapped_methods[
self._client._transport.generate_content
]
# Certain fields should be provided within the metadata header;
# add these here.
metadata = tuple(metadata) + (
gapic_v1.routing_header.to_grpc_metadata((("model", request.model),)),
)
# Validate the universe domain.
self._client._validate_universe_domain()
# Send the request.
response = await rpc(
request,
retry=retry,
timeout=timeout,
metadata=metadata,
)
# Done; return the response.
return response
[docs] def stream_generate_content(
self,
request: Optional[
Union[generative_service.GenerateContentRequest, dict]
] = None,
*,
model: Optional[str] = None,
contents: Optional[MutableSequence[content.Content]] = None,
retry: OptionalRetry = gapic_v1.method.DEFAULT,
timeout: Union[float, object] = gapic_v1.method.DEFAULT,
metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
) -> Awaitable[AsyncIterable[generative_service.GenerateContentResponse]]:
r"""Generates a `streamed
response <https://ai.google.dev/gemini-api/docs/text-generation?lang=python#generate-a-text-stream>`__
from the model given an input ``GenerateContentRequest``.
.. code-block:: python
# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
# client as shown in:
# https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1
async def sample_stream_generate_content():
# Create a client
client = generativelanguage_v1.GenerativeServiceAsyncClient()
# Initialize request argument(s)
request = generativelanguage_v1.GenerateContentRequest(
model="model_value",
)
# Make the request
stream = await client.stream_generate_content(request=request)
# Handle the response
async for response in stream:
print(response)
Args:
request (Optional[Union[google.ai.generativelanguage_v1.types.GenerateContentRequest, dict]]):
The request object. Request to generate a completion from
the model.
model (:class:`str`):
Required. The name of the ``Model`` to use for
generating the completion.
Format: ``models/{model}``.
This corresponds to the ``model`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
contents (:class:`MutableSequence[google.ai.generativelanguage_v1.types.Content]`):
Required. The content of the current conversation with
the model.
For single-turn queries, this is a single instance. For
multi-turn queries like
`chat <https://ai.google.dev/gemini-api/docs/text-generation#chat>`__,
this is a repeated field that contains the conversation
history and the latest request.
This corresponds to the ``contents`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
retry (google.api_core.retry_async.AsyncRetry): Designation of what errors, if any,
should be retried.
timeout (float): The timeout for this request.
metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
sent along with the request as metadata. Normally, each value must be of type `str`,
but for metadata keys ending with the suffix `-bin`, the corresponding values must
be of type `bytes`.
Returns:
AsyncIterable[google.ai.generativelanguage_v1.types.GenerateContentResponse]:
Response from the model supporting multiple candidate
responses.
Safety ratings and content filtering are reported for
both prompt in
GenerateContentResponse.prompt_feedback and for each
candidate in finish_reason and in safety_ratings. The
API: - Returns either all requested candidates or
none of them - Returns no candidates at all only if
there was something wrong with the prompt (check
prompt_feedback) - Reports feedback on each candidate
in finish_reason and safety_ratings.
"""
# Create or coerce a protobuf request object.
# - Quick check: If we got a request object, we should *not* have
# gotten any keyword arguments that map to the request.
flattened_params = [model, contents]
has_flattened_params = (
len([param for param in flattened_params if param is not None]) > 0
)
if request is not None and has_flattened_params:
raise ValueError(
"If the `request` argument is set, then none of "
"the individual field arguments should be set."
)
# - Use the request object if provided (there's no risk of modifying the input as
# there are no flattened fields), or create one.
if not isinstance(request, generative_service.GenerateContentRequest):
request = generative_service.GenerateContentRequest(request)
# If we have keyword arguments corresponding to fields on the
# request, apply these.
if model is not None:
request.model = model
if contents:
request.contents.extend(contents)
# Wrap the RPC method; this adds retry and timeout information,
# and friendly error handling.
rpc = self._client._transport._wrapped_methods[
self._client._transport.stream_generate_content
]
# Certain fields should be provided within the metadata header;
# add these here.
metadata = tuple(metadata) + (
gapic_v1.routing_header.to_grpc_metadata((("model", request.model),)),
)
# Validate the universe domain.
self._client._validate_universe_domain()
# Send the request.
response = rpc(
request,
retry=retry,
timeout=timeout,
metadata=metadata,
)
# Done; return the response.
return response
[docs] async def embed_content(
self,
request: Optional[Union[generative_service.EmbedContentRequest, dict]] = None,
*,
model: Optional[str] = None,
content: Optional[gag_content.Content] = None,
retry: OptionalRetry = gapic_v1.method.DEFAULT,
timeout: Union[float, object] = gapic_v1.method.DEFAULT,
metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
) -> generative_service.EmbedContentResponse:
r"""Generates a text embedding vector from the input ``Content``
using the specified `Gemini Embedding
model <https://ai.google.dev/gemini-api/docs/models/gemini#text-embedding>`__.
.. code-block:: python
# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
# client as shown in:
# https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1
async def sample_embed_content():
# Create a client
client = generativelanguage_v1.GenerativeServiceAsyncClient()
# Initialize request argument(s)
request = generativelanguage_v1.EmbedContentRequest(
model="model_value",
)
# Make the request
response = await client.embed_content(request=request)
# Handle the response
print(response)
Args:
request (Optional[Union[google.ai.generativelanguage_v1.types.EmbedContentRequest, dict]]):
The request object. Request containing the ``Content`` for the model to
embed.
model (:class:`str`):
Required. The model's resource name. This serves as an
ID for the Model to use.
This name should match a model name returned by the
``ListModels`` method.
Format: ``models/{model}``
This corresponds to the ``model`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
content (:class:`google.ai.generativelanguage_v1.types.Content`):
Required. The content to embed. Only the ``parts.text``
fields will be counted.
This corresponds to the ``content`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
retry (google.api_core.retry_async.AsyncRetry): Designation of what errors, if any,
should be retried.
timeout (float): The timeout for this request.
metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
sent along with the request as metadata. Normally, each value must be of type `str`,
but for metadata keys ending with the suffix `-bin`, the corresponding values must
be of type `bytes`.
Returns:
google.ai.generativelanguage_v1.types.EmbedContentResponse:
The response to an EmbedContentRequest.
"""
# Create or coerce a protobuf request object.
# - Quick check: If we got a request object, we should *not* have
# gotten any keyword arguments that map to the request.
flattened_params = [model, content]
has_flattened_params = (
len([param for param in flattened_params if param is not None]) > 0
)
if request is not None and has_flattened_params:
raise ValueError(
"If the `request` argument is set, then none of "
"the individual field arguments should be set."
)
# - Use the request object if provided (there's no risk of modifying the input as
# there are no flattened fields), or create one.
if not isinstance(request, generative_service.EmbedContentRequest):
request = generative_service.EmbedContentRequest(request)
# If we have keyword arguments corresponding to fields on the
# request, apply these.
if model is not None:
request.model = model
if content is not None:
request.content = content
# Wrap the RPC method; this adds retry and timeout information,
# and friendly error handling.
rpc = self._client._transport._wrapped_methods[
self._client._transport.embed_content
]
# Certain fields should be provided within the metadata header;
# add these here.
metadata = tuple(metadata) + (
gapic_v1.routing_header.to_grpc_metadata((("model", request.model),)),
)
# Validate the universe domain.
self._client._validate_universe_domain()
# Send the request.
response = await rpc(
request,
retry=retry,
timeout=timeout,
metadata=metadata,
)
# Done; return the response.
return response
[docs] async def batch_embed_contents(
self,
request: Optional[
Union[generative_service.BatchEmbedContentsRequest, dict]
] = None,
*,
model: Optional[str] = None,
requests: Optional[
MutableSequence[generative_service.EmbedContentRequest]
] = None,
retry: OptionalRetry = gapic_v1.method.DEFAULT,
timeout: Union[float, object] = gapic_v1.method.DEFAULT,
metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
) -> generative_service.BatchEmbedContentsResponse:
r"""Generates multiple embedding vectors from the input ``Content``
which consists of a batch of strings represented as
``EmbedContentRequest`` objects.
.. code-block:: python
# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
# client as shown in:
# https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1
async def sample_batch_embed_contents():
# Create a client
client = generativelanguage_v1.GenerativeServiceAsyncClient()
# Initialize request argument(s)
requests = generativelanguage_v1.EmbedContentRequest()
requests.model = "model_value"
request = generativelanguage_v1.BatchEmbedContentsRequest(
model="model_value",
requests=requests,
)
# Make the request
response = await client.batch_embed_contents(request=request)
# Handle the response
print(response)
Args:
request (Optional[Union[google.ai.generativelanguage_v1.types.BatchEmbedContentsRequest, dict]]):
The request object. Batch request to get embeddings from
the model for a list of prompts.
model (:class:`str`):
Required. The model's resource name. This serves as an
ID for the Model to use.
This name should match a model name returned by the
``ListModels`` method.
Format: ``models/{model}``
This corresponds to the ``model`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
requests (:class:`MutableSequence[google.ai.generativelanguage_v1.types.EmbedContentRequest]`):
Required. Embed requests for the batch. The model in
each of these requests must match the model specified
``BatchEmbedContentsRequest.model``.
This corresponds to the ``requests`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
retry (google.api_core.retry_async.AsyncRetry): Designation of what errors, if any,
should be retried.
timeout (float): The timeout for this request.
metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
sent along with the request as metadata. Normally, each value must be of type `str`,
but for metadata keys ending with the suffix `-bin`, the corresponding values must
be of type `bytes`.
Returns:
google.ai.generativelanguage_v1.types.BatchEmbedContentsResponse:
The response to a BatchEmbedContentsRequest.
"""
# Create or coerce a protobuf request object.
# - Quick check: If we got a request object, we should *not* have
# gotten any keyword arguments that map to the request.
flattened_params = [model, requests]
has_flattened_params = (
len([param for param in flattened_params if param is not None]) > 0
)
if request is not None and has_flattened_params:
raise ValueError(
"If the `request` argument is set, then none of "
"the individual field arguments should be set."
)
# - Use the request object if provided (there's no risk of modifying the input as
# there are no flattened fields), or create one.
if not isinstance(request, generative_service.BatchEmbedContentsRequest):
request = generative_service.BatchEmbedContentsRequest(request)
# If we have keyword arguments corresponding to fields on the
# request, apply these.
if model is not None:
request.model = model
if requests:
request.requests.extend(requests)
# Wrap the RPC method; this adds retry and timeout information,
# and friendly error handling.
rpc = self._client._transport._wrapped_methods[
self._client._transport.batch_embed_contents
]
# Certain fields should be provided within the metadata header;
# add these here.
metadata = tuple(metadata) + (
gapic_v1.routing_header.to_grpc_metadata((("model", request.model),)),
)
# Validate the universe domain.
self._client._validate_universe_domain()
# Send the request.
response = await rpc(
request,
retry=retry,
timeout=timeout,
metadata=metadata,
)
# Done; return the response.
return response
[docs] async def count_tokens(
self,
request: Optional[Union[generative_service.CountTokensRequest, dict]] = None,
*,
model: Optional[str] = None,
contents: Optional[MutableSequence[content.Content]] = None,
retry: OptionalRetry = gapic_v1.method.DEFAULT,
timeout: Union[float, object] = gapic_v1.method.DEFAULT,
metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
) -> generative_service.CountTokensResponse:
r"""Runs a model's tokenizer on input ``Content`` and returns the
token count. Refer to the `tokens
guide <https://ai.google.dev/gemini-api/docs/tokens>`__ to learn
more about tokens.
.. code-block:: python
# This snippet has been automatically generated and should be regarded as a
# code template only.
# It will require modifications to work:
# - It may require correct/in-range values for request initialization.
# - It may require specifying regional endpoints when creating the service
# client as shown in:
# https://googleapis.dev/python/google-api-core/latest/client_options.html
from google.ai import generativelanguage_v1
async def sample_count_tokens():
# Create a client
client = generativelanguage_v1.GenerativeServiceAsyncClient()
# Initialize request argument(s)
request = generativelanguage_v1.CountTokensRequest(
model="model_value",
)
# Make the request
response = await client.count_tokens(request=request)
# Handle the response
print(response)
Args:
request (Optional[Union[google.ai.generativelanguage_v1.types.CountTokensRequest, dict]]):
The request object. Counts the number of tokens in the ``prompt`` sent to a
model.
Models may tokenize text differently, so each model may
return a different ``token_count``.
model (:class:`str`):
Required. The model's resource name. This serves as an
ID for the Model to use.
This name should match a model name returned by the
``ListModels`` method.
Format: ``models/{model}``
This corresponds to the ``model`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
contents (:class:`MutableSequence[google.ai.generativelanguage_v1.types.Content]`):
Optional. The input given to the model as a prompt. This
field is ignored when ``generate_content_request`` is
set.
This corresponds to the ``contents`` field
on the ``request`` instance; if ``request`` is provided, this
should not be set.
retry (google.api_core.retry_async.AsyncRetry): Designation of what errors, if any,
should be retried.
timeout (float): The timeout for this request.
metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
sent along with the request as metadata. Normally, each value must be of type `str`,
but for metadata keys ending with the suffix `-bin`, the corresponding values must
be of type `bytes`.
Returns:
google.ai.generativelanguage_v1.types.CountTokensResponse:
A response from CountTokens.
It returns the model's token_count for the prompt.
"""
# Create or coerce a protobuf request object.
# - Quick check: If we got a request object, we should *not* have
# gotten any keyword arguments that map to the request.
flattened_params = [model, contents]
has_flattened_params = (
len([param for param in flattened_params if param is not None]) > 0
)
if request is not None and has_flattened_params:
raise ValueError(
"If the `request` argument is set, then none of "
"the individual field arguments should be set."
)
# - Use the request object if provided (there's no risk of modifying the input as
# there are no flattened fields), or create one.
if not isinstance(request, generative_service.CountTokensRequest):
request = generative_service.CountTokensRequest(request)
# If we have keyword arguments corresponding to fields on the
# request, apply these.
if model is not None:
request.model = model
if contents:
request.contents.extend(contents)
# Wrap the RPC method; this adds retry and timeout information,
# and friendly error handling.
rpc = self._client._transport._wrapped_methods[
self._client._transport.count_tokens
]
# Certain fields should be provided within the metadata header;
# add these here.
metadata = tuple(metadata) + (
gapic_v1.routing_header.to_grpc_metadata((("model", request.model),)),
)
# Validate the universe domain.
self._client._validate_universe_domain()
# Send the request.
response = await rpc(
request,
retry=retry,
timeout=timeout,
metadata=metadata,
)
# Done; return the response.
return response
[docs] async def list_operations(
self,
request: Optional[operations_pb2.ListOperationsRequest] = None,
*,
retry: OptionalRetry = gapic_v1.method.DEFAULT,
timeout: Union[float, object] = gapic_v1.method.DEFAULT,
metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
) -> operations_pb2.ListOperationsResponse:
r"""Lists operations that match the specified filter in the request.
Args:
request (:class:`~.operations_pb2.ListOperationsRequest`):
The request object. Request message for
`ListOperations` method.
retry (google.api_core.retry_async.AsyncRetry): Designation of what errors,
if any, should be retried.
timeout (float): The timeout for this request.
metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
sent along with the request as metadata. Normally, each value must be of type `str`,
but for metadata keys ending with the suffix `-bin`, the corresponding values must
be of type `bytes`.
Returns:
~.operations_pb2.ListOperationsResponse:
Response message for ``ListOperations`` method.
"""
# Create or coerce a protobuf request object.
# The request isn't a proto-plus wrapped type,
# so it must be constructed via keyword expansion.
if isinstance(request, dict):
request = operations_pb2.ListOperationsRequest(**request)
# Wrap the RPC method; this adds retry and timeout information,
# and friendly error handling.
rpc = self.transport._wrapped_methods[self._client._transport.list_operations]
# Certain fields should be provided within the metadata header;
# add these here.
metadata = tuple(metadata) + (
gapic_v1.routing_header.to_grpc_metadata((("name", request.name),)),
)
# Validate the universe domain.
self._client._validate_universe_domain()
# Send the request.
response = await rpc(
request,
retry=retry,
timeout=timeout,
metadata=metadata,
)
# Done; return the response.
return response
[docs] async def get_operation(
self,
request: Optional[operations_pb2.GetOperationRequest] = None,
*,
retry: OptionalRetry = gapic_v1.method.DEFAULT,
timeout: Union[float, object] = gapic_v1.method.DEFAULT,
metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
) -> operations_pb2.Operation:
r"""Gets the latest state of a long-running operation.
Args:
request (:class:`~.operations_pb2.GetOperationRequest`):
The request object. Request message for
`GetOperation` method.
retry (google.api_core.retry_async.AsyncRetry): Designation of what errors,
if any, should be retried.
timeout (float): The timeout for this request.
metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
sent along with the request as metadata. Normally, each value must be of type `str`,
but for metadata keys ending with the suffix `-bin`, the corresponding values must
be of type `bytes`.
Returns:
~.operations_pb2.Operation:
An ``Operation`` object.
"""
# Create or coerce a protobuf request object.
# The request isn't a proto-plus wrapped type,
# so it must be constructed via keyword expansion.
if isinstance(request, dict):
request = operations_pb2.GetOperationRequest(**request)
# Wrap the RPC method; this adds retry and timeout information,
# and friendly error handling.
rpc = self.transport._wrapped_methods[self._client._transport.get_operation]
# Certain fields should be provided within the metadata header;
# add these here.
metadata = tuple(metadata) + (
gapic_v1.routing_header.to_grpc_metadata((("name", request.name),)),
)
# Validate the universe domain.
self._client._validate_universe_domain()
# Send the request.
response = await rpc(
request,
retry=retry,
timeout=timeout,
metadata=metadata,
)
# Done; return the response.
return response
[docs] async def delete_operation(
self,
request: Optional[operations_pb2.DeleteOperationRequest] = None,
*,
retry: OptionalRetry = gapic_v1.method.DEFAULT,
timeout: Union[float, object] = gapic_v1.method.DEFAULT,
metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
) -> None:
r"""Deletes a long-running operation.
This method indicates that the client is no longer interested
in the operation result. It does not cancel the operation.
If the server doesn't support this method, it returns
`google.rpc.Code.UNIMPLEMENTED`.
Args:
request (:class:`~.operations_pb2.DeleteOperationRequest`):
The request object. Request message for
`DeleteOperation` method.
retry (google.api_core.retry_async.AsyncRetry): Designation of what errors,
if any, should be retried.
timeout (float): The timeout for this request.
metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
sent along with the request as metadata. Normally, each value must be of type `str`,
but for metadata keys ending with the suffix `-bin`, the corresponding values must
be of type `bytes`.
Returns:
None
"""
# Create or coerce a protobuf request object.
# The request isn't a proto-plus wrapped type,
# so it must be constructed via keyword expansion.
if isinstance(request, dict):
request = operations_pb2.DeleteOperationRequest(**request)
# Wrap the RPC method; this adds retry and timeout information,
# and friendly error handling.
rpc = self.transport._wrapped_methods[self._client._transport.delete_operation]
# Certain fields should be provided within the metadata header;
# add these here.
metadata = tuple(metadata) + (
gapic_v1.routing_header.to_grpc_metadata((("name", request.name),)),
)
# Validate the universe domain.
self._client._validate_universe_domain()
# Send the request.
await rpc(
request,
retry=retry,
timeout=timeout,
metadata=metadata,
)
[docs] async def cancel_operation(
self,
request: Optional[operations_pb2.CancelOperationRequest] = None,
*,
retry: OptionalRetry = gapic_v1.method.DEFAULT,
timeout: Union[float, object] = gapic_v1.method.DEFAULT,
metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
) -> None:
r"""Starts asynchronous cancellation on a long-running operation.
The server makes a best effort to cancel the operation, but success
is not guaranteed. If the server doesn't support this method, it returns
`google.rpc.Code.UNIMPLEMENTED`.
Args:
request (:class:`~.operations_pb2.CancelOperationRequest`):
The request object. Request message for
`CancelOperation` method.
retry (google.api_core.retry_async.AsyncRetry): Designation of what errors,
if any, should be retried.
timeout (float): The timeout for this request.
metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
sent along with the request as metadata. Normally, each value must be of type `str`,
but for metadata keys ending with the suffix `-bin`, the corresponding values must
be of type `bytes`.
Returns:
None
"""
# Create or coerce a protobuf request object.
# The request isn't a proto-plus wrapped type,
# so it must be constructed via keyword expansion.
if isinstance(request, dict):
request = operations_pb2.CancelOperationRequest(**request)
# Wrap the RPC method; this adds retry and timeout information,
# and friendly error handling.
rpc = self.transport._wrapped_methods[self._client._transport.cancel_operation]
# Certain fields should be provided within the metadata header;
# add these here.
metadata = tuple(metadata) + (
gapic_v1.routing_header.to_grpc_metadata((("name", request.name),)),
)
# Validate the universe domain.
self._client._validate_universe_domain()
# Send the request.
await rpc(
request,
retry=retry,
timeout=timeout,
metadata=metadata,
)
async def __aenter__(self) -> "GenerativeServiceAsyncClient":
return self
async def __aexit__(self, exc_type, exc, tb):
await self.transport.close()
DEFAULT_CLIENT_INFO = gapic_v1.client_info.ClientInfo(
gapic_version=package_version.__version__
)
if hasattr(DEFAULT_CLIENT_INFO, "protobuf_runtime_version"): # pragma: NO COVER
DEFAULT_CLIENT_INFO.protobuf_runtime_version = google.protobuf.__version__
__all__ = ("GenerativeServiceAsyncClient",)
