genai.extensions.localserver.schema module#

pydantic model genai.extensions.localserver.schema.TextGenerationCreateRequest[source]#

Bases: _TextGenerationCreateRequest

Following properties are required for local server

Config:

  • extra: str = allow

  • use_enum_values: bool = True

  • protected_namespaces: tuple = ()

  • validate_assignment: bool = True

  • allow_inf_nan: bool = False

  • validate_default: bool = True

field data: PromptTemplateData | None = None#
field input: str | None = None#

The input is the prompt to generate completions, passed as a string. Note: The method tokenizes the input internally. It is recommended not to leave any trailing spaces.

field model_id: str [Required]#

The ID of the model or tune to be used for this request.

field moderations: ModerationParameters | None = None#
field parameters: TextGenerationParameters [Optional]#
pydantic model genai.extensions.localserver.schema.TextTokenizationCreateRequest[source]#

Bases: _TextTokenizationCreateRequest

Following properties are required for local server

Config:

  • extra: str = allow

  • use_enum_values: bool = True

  • protected_namespaces: tuple = ()

  • validate_assignment: bool = True

  • allow_inf_nan: bool = False

  • validate_default: bool = True

field input: str | list[str] | None = None#
field model_id: str [Required]#
field parameters: TextTokenizationParameters [Optional]#
field prompt_id: str | None = None#