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

Assistants domain

Written by
Updated at September 25, 2025

class yandex_cloud_ml_sdk._assistants.domain.Assistants

Base class for assistants management.

Provides common functionality for creating, getting and listing assistants.

create(model, *, temperature=Undefined, max_tokens=Undefined, instruction=Undefined, max_prompt_tokens=Undefined, prompt_truncation_strategy=Undefined, name=Undefined, description=Undefined, labels=Undefined, ttl_days=Undefined, tools=Undefined, expiration_policy=Undefined, response_format=Undefined, timeout=60)

Create a new assistant instance.

Parameters

Return type

Assistant

get(assistant_id, *, timeout=60)

Get an existing assistant by ID.

Parameters

  • assistant_id (str) – ID of the assistant to retrieve
  • timeout (float) – The timeout, or the maximum time to wait for the request to complete in seconds. Defaults to 60 seconds.

Return type

Assistant

list(*, page_size=Undefined, timeout=60)

List all assistants.

Parameters

  • page_size (int | Undefined) – Number of assistants per page
  • timeout (float) – The timeout, or the maximum time to wait for the request to complete in seconds. Defaults to 60 seconds.

Return type

Iterator[Assistant]

class yandex_cloud_ml_sdk._assistants.assistant.Assistant

Base class providing read-only access to Yandex Cloud ML Assistant configuration and metadata.

This class implements the core interface for interacting with Yandex Cloud ML Assistant API in a read-only manner. It serves as the parent class for both synchronous (Assistant) and asynchronous (AsyncAssistant) implementations.

update(*, model=Undefined, temperature=Undefined, max_tokens=Undefined, instruction=Undefined, max_prompt_tokens=Undefined, prompt_truncation_strategy=Undefined, name=Undefined, description=Undefined, labels=Undefined, ttl_days=Undefined, tools=Undefined, expiration_policy=Undefined, response_format=Undefined, timeout=60)

Update the assistant’s configuration with new parameters.

This method sends an update request to Yandex Cloud ML API to modify the assistant’s configuration. Only specified parameters will be updated, others remain unchanged.

Parameters

Return type

Self

delete(*, timeout=60)

Delete the assistant from Yandex Cloud ML.

Sends a delete request to the Yandex Cloud ML API to remove the assistant. After successful deletion, marks the assistant as deleted internally.

Parameters

timeout (float) – The timeout, or the maximum time to wait for the request to complete in seconds. Defaults to 60 seconds.

Return type

None

list_versions(page_size=Undefined, page_token=Undefined, timeout=60)

List all versions of the assistant.

This method retrieves historical versions of the assistant in a paginated manner.

Parameters

  • page_size (int | Undefined) – Maximum number of versions to return per page
  • page_token (str | Undefined) – Token for pagination
  • timeout (float) – The timeout, or the maximum time to wait for the request to complete in seconds. Defaults to 60 seconds.

Return type

Iterator[AssistantVersion]

run(thread, *, custom_temperature=Undefined, custom_max_tokens=Undefined, custom_max_prompt_tokens=Undefined, custom_prompt_truncation_strategy=Undefined, custom_response_format=Undefined, timeout=60)

Execute a non-streaming run with the assistant on the given thread.

Parameters

  • thread (str | Thread) – Thread ID or Thread object to run on
  • custom_temperature (UndefinedOr[float]) – Override for model temperature
  • custom_max_tokens (UndefinedOr[int]) – Override for max tokens to generate
  • custom_max_prompt_tokens (UndefinedOr[int]) – Override for max prompt tokens
  • custom_prompt_truncation_strategy (UndefinedOr[PromptTruncationStrategyType]) – Override for prompt truncation strategy
  • custom_response_format (UndefinedOr[ResponseType]) – Override for response format
  • timeout (float) – The timeout, or the maximum time to wait for the request to complete in seconds. Defaults to 60 seconds.

Return type

Run

run_stream(thread, *, custom_temperature=Undefined, custom_max_tokens=Undefined, custom_max_prompt_tokens=Undefined, custom_prompt_truncation_strategy=Undefined, custom_response_format=Undefined, timeout=60)

Execute a streaming run with the assistant on the given thread.

Parameters

  • thread (str | Thread) – Thread ID or Thread object to run on
  • custom_temperature (UndefinedOr[float]) – Override for model temperature
  • custom_max_tokens (UndefinedOr[int]) – Override for max tokens to generate
  • custom_max_prompt_tokens (UndefinedOr[int]) – Override for max prompt tokens
  • custom_prompt_truncation_strategy (UndefinedOr[PromptTruncationStrategyType]) – Override for prompt truncation strategy
  • custom_response_format (UndefinedOr[ResponseType]) – Override for response format
  • timeout (float) – The timeout, or the maximum time to wait for the request to complete in seconds. Defaults to 60 seconds.

Return type

Run

property max_prompt_tokens: int | None

Returns the maximum number of prompt tokens allowed for the assistant.

name: str | None

The name of the assistant.

description: str | None

The description of the assistant.

created_by: str

The identifier of the user who created the assistant.

created_at: datetime

The timestamp when the assistant was created.

updated_by: str

The identifier of the user who last updated the assistant.

updated_at: datetime

The timestamp when the assistant was last updated.

expires_at: datetime

The timestamp when the assistant will expire.

labels: dict[str, str] | None

Additional labels associated with the assistant.

expiration_config: ExpirationConfig

Expiration configuration for the assistant.

model: BaseGPTModel

The GPT model used by the assistant.

instruction: str | None

Instructions or guidelines that the assistant should follow. These instructions guide the assistant’s behavior and responses.

prompt_truncation_options: PromptTruncationOptions

Options for truncating thread messages. Controls how messages are truncated when forming the prompt.

tools: tuple[BaseTool]... ,

Tools available to the assistant. Can be a sequence or a single tool. Tools must implement BaseTool interface.

response_format: ResponseType | None

A format of the response returned by the model. Could be a JsonSchema, a JSON string, or a pydantic model

id: str

Previous
Models domain
Next
Tools domain