Contact UsGet started
© 2025 Direct Cursus Technology L.L.C.

Domain

Written by
Updated at November 7, 2025

class yandex_cloud_ml_sdk._chat.completions.function.AsyncChatCompletions

A class for working with chat completions models.

This class provides the core functionality for creating chat model instances and managing completions. It handles model URI construction and provides methods for listing available models.

async list(*, timeout=60)

Returns all available models in selected subdomain (completions, embeddings, etc)

Parameters

timeout (float) – The timeout, or the maximum time to wait for the request to complete in seconds.

Return type

tuple[AsyncChatModel, …]

__call__(model_name, *, model_version='latest')

Create a model instance in selected chat subdomain (completions, embeddings, etc)

Constructs the model URI based on the provided name and version. If the name contains ‘://’, it is treated as a full URI. Otherwise constructs a URI in the form ‘gpt://<folder_id>//’.

Parameters

  • model_name (str) – The name or URI of the model.
  • model_version (str) – The version of the model to use. Defaults to ‘latest’.

Return type

ModelTypeT

Model

class yandex_cloud_ml_sdk._chat.completions.model.AsyncChatModel

A class for working with chat models providing inference functionality.

This class provides the foundation for chat model implementations, handling configuration, request building, and response processing.

async run(messages, *, timeout=180)

Executes the model with the provided messages.

Parameters

Return type

ChatModelResult[AsyncToolCall]

async run_stream(messages, *, timeout=180)

Executes the model with the provided messages and yields partial results as they become available.

Parameters

Return type

AsyncIterator[ChatModelResult[AsyncToolCall]]

property config: ConfigTypeT

configure(*, temperature=Undefined, max_tokens=Undefined, reasoning_mode=Undefined, response_format=Undefined, tools=Undefined, parallel_tool_calls=Undefined, tool_choice=Undefined, extra_query=Undefined)

Configure the model with specified parameters.

Parameters

  • temperature (UndefinedOr[float] | None) – Sampling temperature (0-1). Higher values produce more random results.
  • max_tokens (UndefinedOr[int] | None) – Maximum number of tokens to generate in the response.
  • reasoning_mode (UndefinedOr[ChatReasoningModeType] | None) – Reasoning mode for internal processing before responding.
  • response_format (UndefinedOr[ResponseType] | None) – Format of the response (JsonSchema, JSON string, or pydantic model). See structured output documentation_BaseChatModel_URL.
  • tools (UndefinedOr[Sequence[CompletionTool] | CompletionTool]) – Tools available for completion. Can be a sequence or single tool.
  • parallel_tool_calls (UndefinedOr[bool]) – Whether to allow parallel tool calls. Defaults to ‘true’.
  • tool_choice (UndefinedOr[ToolChoiceType]) – Strategy for tool selection. There are several ways to configure tool_choice for query processing: - no tools to call (tool_choice='none'); - required to call any tool (tool_choice='required'); - call a specific tool (tool_choice={'type': 'function', 'function': {'name': 'another_calculator'}} or directly passing a tool object).
  • extra_query (UndefinedOr[QueryType]) – Additional experimental model parameters.

Return type

Self

property uri: str