Class GenerativeServiceClient (2.30.0-rc)

API for using Large Models that generate multimodal content and have additional capabilities beyond text generation.

Equality

Instances of this class created via copy-construction or copy-assignment always compare equal. Instances created with equal std::shared_ptr<*Connection> objects compare equal. Objects that compare equal share the same underlying resources.

Performance

Creating a new instance of this class is a relatively expensive operation, new objects establish new connections to the service. In contrast, copy-construction, move-construction, and the corresponding assignment operations are relatively efficient as the copies share all underlying resources.

Thread Safety

Concurrent access to different instances of this class, even if they compare equal, is guaranteed to work. Two or more threads operating on the same instance of this class is not guaranteed to work. Since copy-construction and move-construction is a relatively efficient operation, consider using such a copy when using this class from multiple threads.

Constructors

GenerativeServiceClient(GenerativeServiceClient const &)

Copy and move support

Parameter
Name	Description
	`GenerativeServiceClient const &`

GenerativeServiceClient(GenerativeServiceClient &&)

Copy and move support

Parameter
Name	Description
	`GenerativeServiceClient &&`

GenerativeServiceClient(std::shared_ptr< GenerativeServiceConnection >, Options)

Parameters
Name	Description
`connection`	`std::shared_ptr< GenerativeServiceConnection >`
`opts`	`Options`

Operators

operator=(GenerativeServiceClient const &)

Copy and move support

Parameter
Name	Description
	`GenerativeServiceClient const &`

Returns
Type	Description
`GenerativeServiceClient &`

operator=(GenerativeServiceClient &&)

Copy and move support

Parameter
Name	Description
	`GenerativeServiceClient &&`

Returns
Type	Description
`GenerativeServiceClient &`

Functions

GenerateContent(std::string const &, std::vector< google::ai::generativelanguage::v1::Content > const &, Options)

Generates a model response given an input GenerateContentRequest.

Refer to the text generation guide for detailed usage information. Input capabilities differ between models, including tuned models. Refer to the model guide and tuning guide for details.

Parameters
Name	Description
`model`	`std::string const &` Required. The name of the `Model` to use for generating the completion. Format: `name=models/{model}`.
`contents`	`std::vector< google::ai::generativelanguage::v1::Content > const &` 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, this is a repeated field that contains the conversation history and the latest request.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StatusOr< google::ai::generativelanguage::v1::GenerateContentResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.GenerateContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.

GenerateContent(google::ai::generativelanguage::v1::GenerateContentRequest const &, Options)

Generates a model response given an input GenerateContentRequest.

Refer to the text generation guide for detailed usage information. Input capabilities differ between models, including tuned models. Refer to the model guide and tuning guide for details.

Parameters
Name	Description
`request`	`google::ai::generativelanguage::v1::GenerateContentRequest const &` Unary RPCs, such as the one wrapped by this function, receive a single `request` proto message which includes all the inputs for the RPC. In this case, the proto message is a google.ai.generativelanguage.v1.GenerateContentRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StatusOr< google::ai::generativelanguage::v1::GenerateContentResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.GenerateContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.

StreamGenerateContent(std::string const &, std::vector< google::ai::generativelanguage::v1::Content > const &, Options)

Generates a streamed response from the model given an input GenerateContentRequest.

Parameters
Name	Description
`model`	`std::string const &` Required. The name of the `Model` to use for generating the completion. Format: `name=models/{model}`.
`contents`	`std::vector< google::ai::generativelanguage::v1::Content > const &` 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, this is a repeated field that contains the conversation history and the latest request.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StreamRange< google::ai::generativelanguage::v1::GenerateContentResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.GenerateContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.

StreamGenerateContent(google::ai::generativelanguage::v1::GenerateContentRequest const &, Options)

Generates a streamed response from the model given an input GenerateContentRequest.

Parameters
Name	Description
`request`	`google::ai::generativelanguage::v1::GenerateContentRequest const &` Unary RPCs, such as the one wrapped by this function, receive a single `request` proto message which includes all the inputs for the RPC. In this case, the proto message is a google.ai.generativelanguage.v1.GenerateContentRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StreamRange< google::ai::generativelanguage::v1::GenerateContentResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.GenerateContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.

EmbedContent(std::string const &, google::ai::generativelanguage::v1::Content const &, Options)

Generates a text embedding vector from the input Content using the specified Gemini Embedding model.

Parameters
Name	Description
`model`	`std::string const &` 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}`
`content`	`google::ai::generativelanguage::v1::Content const &` Required. The content to embed. Only the `parts.text` fields will be counted.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StatusOr< google::ai::generativelanguage::v1::EmbedContentResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.EmbedContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.

EmbedContent(google::ai::generativelanguage::v1::EmbedContentRequest const &, Options)

Generates a text embedding vector from the input Content using the specified Gemini Embedding model.

Parameters
Name	Description
`request`	`google::ai::generativelanguage::v1::EmbedContentRequest const &` Unary RPCs, such as the one wrapped by this function, receive a single `request` proto message which includes all the inputs for the RPC. In this case, the proto message is a google.ai.generativelanguage.v1.EmbedContentRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StatusOr< google::ai::generativelanguage::v1::EmbedContentResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.EmbedContentResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.

BatchEmbedContents(std::string const &, std::vector< google::ai::generativelanguage::v1::EmbedContentRequest > const &, Options)

Generates multiple embedding vectors from the input Content which consists of a batch of strings represented as EmbedContentRequest objects.

Parameters
Name	Description
`model`	`std::string const &` 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}`
`requests`	`std::vector< google::ai::generativelanguage::v1::EmbedContentRequest > const &` Required. Embed requests for the batch. The model in each of these requests must match the model specified `BatchEmbedContentsRequest.model`.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StatusOr< google::ai::generativelanguage::v1::BatchEmbedContentsResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.BatchEmbedContentsResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.

BatchEmbedContents(google::ai::generativelanguage::v1::BatchEmbedContentsRequest const &, Options)

Generates multiple embedding vectors from the input Content which consists of a batch of strings represented as EmbedContentRequest objects.

Parameters
Name	Description
`request`	`google::ai::generativelanguage::v1::BatchEmbedContentsRequest const &` Unary RPCs, such as the one wrapped by this function, receive a single `request` proto message which includes all the inputs for the RPC. In this case, the proto message is a google.ai.generativelanguage.v1.BatchEmbedContentsRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StatusOr< google::ai::generativelanguage::v1::BatchEmbedContentsResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.BatchEmbedContentsResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.

CountTokens(std::string const &, std::vector< google::ai::generativelanguage::v1::Content > const &, Options)

Runs a model's tokenizer on input Content and returns the token count.

Refer to the tokens guide to learn more about tokens.

Parameters
Name	Description
`model`	`std::string const &` 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}`
`contents`	`std::vector< google::ai::generativelanguage::v1::Content > const &` Optional. The input given to the model as a prompt. This field is ignored when `generate_content_request` is set.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StatusOr< google::ai::generativelanguage::v1::CountTokensResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.CountTokensResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.

CountTokens(google::ai::generativelanguage::v1::CountTokensRequest const &, Options)

Runs a model's tokenizer on input Content and returns the token count.

Refer to the tokens guide to learn more about tokens.

Parameters
Name	Description
`request`	`google::ai::generativelanguage::v1::CountTokensRequest const &` Unary RPCs, such as the one wrapped by this function, receive a single `request` proto message which includes all the inputs for the RPC. In this case, the proto message is a google.ai.generativelanguage.v1.CountTokensRequest. Proto messages are converted to C++ classes by Protobuf, using the Protobuf mapping rules.
`opts`	`Options` Optional. Override the class-level options, such as retry and backoff policies.

Returns
Type	Description
`StatusOr< google::ai::generativelanguage::v1::CountTokensResponse >`	the result of the RPC. The response message type (google.ai.generativelanguage.v1.CountTokensResponse) is mapped to a C++ class using the Protobuf mapping rules. If the request fails, the `StatusOr` contains the error details.