genai.text.tokenization.tokenization_service module

pydantic model genai.text.tokenization.tokenization_service.BaseConfig[source]

Bases: BaseServiceConfig

Config:

  • extra: str = forbid

  • validate_assignment: bool = True

  • validate_default: bool = True

field create_execution_options: CreateExecutionOptions = CreateExecutionOptions(throw_on_error=True, ordered=True, concurrency_limit=None, batch_size=None, rate_limit_options=None, callback=None)
pydantic model genai.text.tokenization.tokenization_service.CreateExecutionOptions[source]

Bases: BaseServiceConfig

Execution options for tokenization process.

Config:

  • extra: str = forbid

  • validate_assignment: bool = True

  • validate_default: bool = True

field batch_size: Annotated[int | None, FieldInfo(annotation=NoneType, required=True, description='Upper limit for size of single batch of prompts (the size can be actually lower in case the payload is large enough).')] = None

Upper limit for size of single batch of prompts (the size can be actually lower in case the payload is large enough).

field callback: Annotated[Callable[[TextTokenizationCreateResponse], None] | None, FieldInfo(annotation=NoneType, required=True, description='Callback which is called everytime the response comes.')] = None

Callback which is called everytime the response comes.

field concurrency_limit: Annotated[int | None, FieldInfo(annotation=NoneType, required=True, description="Upper bound for concurrent executions (in case the passed value is higher than the API allows, the API's limit will be used).", metadata=[Ge(ge=1)])] = None

Upper bound for concurrent executions (in case the passed value is higher than the API allows, the API’s limit will be used).

Constraints:

  • ge = 1

field ordered: Annotated[bool, FieldInfo(annotation=NoneType, required=True, description='Items will be yielded in the order they were passed in, although they may be processed on the server in different order.')] = True

Items will be yielded in the order they were passed in, although they may be processed on the server in different order.

field rate_limit_options: Annotated[dict | None, FieldInfo(annotation=NoneType, required=True, description='HTTPX Transport Options to limit number of requests per second.')] = None

HTTPX Transport Options to limit number of requests per second.

field throw_on_error: Annotated[bool, FieldInfo(annotation=NoneType, required=True, description="Flag indicating whether to throw an error if any error occurs during execution (if disabled, 'None' may be returned in case of error).")] = True

Flag indicating whether to throw an error if any error occurs during execution (if disabled, ‘None’ may be returned in case of error).

class genai.text.tokenization.tokenization_service.TokenizationService[source]

Bases: BaseService[BaseConfig, BaseServiceServices]

Config

alias of BaseConfig

create(*, input, model_id=None, prompt_id=None, parameters=None, execution_options=None)[source]
Parameters:

  • input (str | list[str]) – The input data for tokenization. It can be a single string or a list of strings.

  • model_id (str | None) – The ID of the model to use for tokenization. Eiter ‘model_id’ or ‘prompt_id’ must be provided.

  • prompt_id (str | None) – The ID of the prompt to use for tokenization. Eiter ‘model_id’ or ‘prompt_id’ must be provided.

  • parameters (dict | TextTokenizationParameters | None) – The parameters for tokenization, like return options.

  • execution_options (dict | CreateExecutionOptions | None) – The execution options for tokenization like batch size, callbacks and cetra.

Raises:
Return type:

Generator[TextTokenizationCreateResponse, None, None]