通过

OnnxGenAIChatCompletion Class

OnnxGenAI text completion service.

Note: This class is marked as 'experimental' and may change in the future.

Initializes a new instance of the OnnxGenAITextCompletion class.

Constructor

OnnxGenAIChatCompletion(template: ONNXTemplate, ai_model_path: str | None = None, ai_model_id: str | None = None, env_file_path: str | None = None, env_file_encoding: str | None = None, *, model: Any, tokenizer: Any, tokenizer_stream: Any, enable_multi_modality: bool = False, service_id: str = '', instruction_role: str = None)

Parameters

Name Description
template
Required

The chat template configuration.
ai_model_path

Local path to the ONNX model Folder.

Default value: None
ai_model_id

The ID of the AI model. Defaults to None.

Default value: None
env_file_path

Use the environment settings file as a fallback to environment variables.

Default value: None
env_file_encoding

The encoding of the environment settings file.

Default value: None
kwargs
Required

Additional arguments.

Keyword-Only Parameters

Name Description
model
Required
tokenizer
Required
tokenizer_stream
Required
enable_multi_modality
Required
service_id
Required
instruction_role
Required

Methods

get_prompt_execution_settings_class

Create a request settings object.

get_prompt_execution_settings_class

Create a request settings object.

get_prompt_execution_settings_class() -> type[PromptExecutionSettings]

Attributes

SUPPORTS_FUNCTION_CALLING 

SUPPORTS_FUNCTION_CALLING: ClassVar[bool] = False

is_experimental 

is_experimental = True

stage_status 

stage_status = 'experimental'

template 

template: ONNXTemplate