Yandex Cloud
Поиск
Связаться с намиПодключиться
  • Истории успеха
  • Документация
  • Блог
  • Все сервисы
  • Статус работы сервисов
    • Доступны в регионе
    • Инфраструктура и сеть
    • Платформа данных
    • Контейнеры
    • Инструменты разработчика
    • Бессерверные вычисления
    • Безопасность
    • Мониторинг и управление ресурсами
    • ИИ для бизнеса
    • Бизнес-инструменты
  • Все решения
    • По отраслям
    • По типу задач
    • Экономика платформы
    • Безопасность
    • Техническая поддержка
    • Каталог партнёров
    • Обучение и сертификация
    • Облако для стартапов
    • Облако для крупного бизнеса
    • Центр технологий для общества
    • Партнёрская программа
    • Поддержка IT-бизнеса
    • Облако для фрилансеров
    • Обучение и сертификация
    • Блог
    • Документация
    • Мероприятия и вебинары
    • Контакты, чаты и сообщества
    • Идеи
    • Тарифы Yandex Cloud
    • Промоакции и free tier
    • Правила тарификации
  • Истории успеха
  • Документация
  • Блог
Проект Яндекса
© 2025 ТОО «Облачные Сервисы Казахстан»
Yandex AI Studio
  • Начало работы с Model Gallery
    • О сервисе Yandex AI Studio
    • Yandex Workflows
    • Квоты и лимиты
    • Термины и определения
  • Переход с AI Assistant API на Responses API
  • Совместимость с OpenAI
    • Обзор
    • Аутентификация в API
        • Overview
          • Overview
          • Create
          • Get
          • Update
          • Delete
          • List
          • ListVersions
  • Управление доступом
  • Правила тарификации
  • Аудитные логи Audit Trails
  • Публичные материалы
  • История изменений

В этой статье:

  • gRPC request
  • ListAssistantsRequest
  • ListAssistantsResponse
  • Assistant
  • ExpirationConfig
  • PromptTruncationOptions
  • AutoStrategy
  • LastMessagesStrategy
  • CompletionOptions
  • Tool
  • SearchIndexTool
  • RephraserOptions
  • CallStrategy
  • AlwaysCall
  • AutoCall
  • FunctionTool
  • GenSearchTool
  • GenSearchOptions
  • SiteOption
  • HostOption
  • UrlOption
  • SearchFilter
  • ResponseFormat
  • JsonSchema
  1. Справочники API
  2. AI Assistant API (англ.)
  3. gRPC
  4. Assistant
  5. List

AI Assistants API, gRPC: AssistantService.List

Статья создана
Yandex Cloud
Обновлена 8 августа 2025 г.
  • gRPC request
  • ListAssistantsRequest
  • ListAssistantsResponse
  • Assistant
  • ExpirationConfig
  • PromptTruncationOptions
  • AutoStrategy
  • LastMessagesStrategy
  • CompletionOptions
  • Tool
  • SearchIndexTool
  • RephraserOptions
  • CallStrategy
  • AlwaysCall
  • AutoCall
  • FunctionTool
  • GenSearchTool
  • GenSearchOptions
  • SiteOption
  • HostOption
  • UrlOption
  • SearchFilter
  • ResponseFormat
  • JsonSchema

List assistants in a specific folder.

gRPC requestgRPC request

rpc List (ListAssistantsRequest) returns (ListAssistantsResponse)

ListAssistantsRequestListAssistantsRequest

{
  "folder_id": "string",
  "page_size": "int64",
  "page_token": "string"
}

Request message for listing assistants in a specific folder.

Field

Description

folder_id

string

Required field. Folder ID from which to list assistants.

page_size

int64

Maximum number of assistants to return per page.

page_token

string

Token to retrieve the next page of results.

ListAssistantsResponseListAssistantsResponse

{
  "assistants": [
    {
      "id": "string",
      "folder_id": "string",
      "name": "string",
      "description": "string",
      "created_by": "string",
      "created_at": "google.protobuf.Timestamp",
      "updated_by": "string",
      "updated_at": "google.protobuf.Timestamp",
      "expiration_config": {
        "expiration_policy": "ExpirationPolicy",
        "ttl_days": "int64"
      },
      "expires_at": "google.protobuf.Timestamp",
      "labels": "map<string, string>",
      "model_uri": "string",
      "instruction": "string",
      "prompt_truncation_options": {
        "max_prompt_tokens": "google.protobuf.Int64Value",
        // Includes only one of the fields `auto_strategy`, `last_messages_strategy`
        "auto_strategy": "AutoStrategy",
        "last_messages_strategy": {
          "num_messages": "int64"
        }
        // end of the list of possible fields
      },
      "completion_options": {
        "max_tokens": "google.protobuf.Int64Value",
        "temperature": "google.protobuf.DoubleValue"
      },
      "tools": [
        {
          // Includes only one of the fields `search_index`, `function`, `gen_search`
          "search_index": {
            "search_index_ids": [
              "string"
            ],
            "max_num_results": "google.protobuf.Int64Value",
            "rephraser_options": {
              "rephraser_uri": "string"
            },
            "call_strategy": {
              // Includes only one of the fields `always_call`, `auto_call`
              "always_call": "AlwaysCall",
              "auto_call": {
                "name": "string",
                "instruction": "string"
              }
              // end of the list of possible fields
            }
          },
          "function": {
            "name": "string",
            "description": "string",
            "parameters": "google.protobuf.Struct"
          },
          "gen_search": {
            "options": {
              // Includes only one of the fields `site`, `host`, `url`
              "site": {
                "site": [
                  "string"
                ]
              },
              "host": {
                "host": [
                  "string"
                ]
              },
              "url": {
                "url": [
                  "string"
                ]
              },
              // end of the list of possible fields
              "enable_nrfm_docs": "bool",
              "search_filters": [
                {
                  // Includes only one of the fields `date`, `lang`, `format`
                  "date": "string",
                  "lang": "string",
                  "format": "DocFormat"
                  // end of the list of possible fields
                }
              ]
            },
            "description": "string"
          }
          // end of the list of possible fields
        }
      ],
      "response_format": {
        // Includes only one of the fields `json_object`, `json_schema`
        "json_object": "bool",
        "json_schema": {
          "schema": "google.protobuf.Struct"
        }
        // end of the list of possible fields
      }
    }
  ],
  "next_page_token": "string"
}

Response message for the list operation.

Field

Description

assistants[]

Assistant

List of assistants in the specified folder.

next_page_token

string

Token to retrieve the next page of results.

AssistantAssistant

Assistant represents an AI assistant configuration with various settings and metadata.

Field

Description

id

string

Unique identifier of the assistant.

folder_id

string

ID of the folder that the assistant belongs to.

name

string

Name of the assistant.

description

string

Description of the assistant.

created_by

string

Identifier of the subject who created this assistant.

created_at

google.protobuf.Timestamp

Timestamp representing when the assistant was created.

updated_by

string

Identifier of the subject who last updated this assistant.

updated_at

google.protobuf.Timestamp

Timestamp representing the last time this assistant was updated.

expiration_config

ExpirationConfig

Configuration for the expiration of the assistant, defining when and how the assistant will expire.

expires_at

google.protobuf.Timestamp

Timestamp representing when the assistant will expire.

labels

object (map<string, string>)

Set of key-value pairs that can be used to organize and categorize the assistant.

model_uri

string

The ID of the model to be used for completion generation.

instruction

string

Instructions or guidelines that the assistant should follow when generating responses or performing tasks.
These instructions can help guide the assistant's behavior and responses.

prompt_truncation_options

PromptTruncationOptions

Configuration options for truncating the prompt when the token count exceeds a specified limit.

completion_options

CompletionOptions

Configuration options for completion generation.

tools[]

Tool

List of tools that the assistant can use to perform additional tasks.
One example is the SearchIndexTool, which is used for Retrieval-Augmented Generation (RAG).

response_format

ResponseFormat

Specifies the format of the model's response.

ExpirationConfigExpirationConfig

Field

Description

expiration_policy

enum ExpirationPolicy

  • EXPIRATION_POLICY_UNSPECIFIED
  • STATIC
  • SINCE_LAST_ACTIVE

ttl_days

int64

PromptTruncationOptionsPromptTruncationOptions

Defines the options for truncating thread messages within a prompt.

Field

Description

max_prompt_tokens

google.protobuf.Int64Value

The maximum number of tokens allowed in the prompt.
If the prompt exceeds this limit, the thread messages will be truncated.
Default max_prompt_tokens: 7000

auto_strategy

AutoStrategy

Includes only one of the fields auto_strategy, last_messages_strategy.

Specifies the truncation strategy to use when the prompt exceeds the token limit.

last_messages_strategy

LastMessagesStrategy

Retains only the last num_messages messages in the thread.
If these messages exceed max_prompt_tokens, older messages will be further truncated to fit the limit.

Includes only one of the fields auto_strategy, last_messages_strategy.

Specifies the truncation strategy to use when the prompt exceeds the token limit.

AutoStrategyAutoStrategy

Auto truncation strategy.

Field

Description

Empty

LastMessagesStrategyLastMessagesStrategy

Truncates the prompt by retaining only the last num_messages messages in the thread.

Field

Description

num_messages

int64

The number of most recent messages to retain in the prompt.
If these messages exceed max_prompt_tokens, older messages will be further truncated to fit the limit.

CompletionOptionsCompletionOptions

Defines the options for completion generation.

Field

Description

max_tokens

google.protobuf.Int64Value

The limit on the number of tokens used for single completion generation.
Must be greater than zero. This maximum allowed parameter value may depend on the model being used.

temperature

google.protobuf.DoubleValue

Affects creativity and randomness of responses. Should be a double number between 0 (inclusive) and 1 (inclusive).
Lower values produce more straightforward responses while higher values lead to increased creativity and randomness.
Default temperature: 0.3

ToolTool

Represents a general tool that can be one of several types.

Field

Description

search_index

SearchIndexTool

SearchIndexTool tool that performs search across specified indexes.

Includes only one of the fields search_index, function, gen_search.

function

FunctionTool

Function tool that can be invoked by the assistant.

Includes only one of the fields search_index, function, gen_search.

gen_search

GenSearchTool

Performs web retrieval and generative synthesis.

Includes only one of the fields search_index, function, gen_search.

SearchIndexToolSearchIndexTool

Configures a tool that enables Retrieval-Augmented Generation (RAG) by allowing the assistant to search across a specified search index.

Field

Description

search_index_ids[]

string

A list of search index IDs that this tool will query. Currently, only a single index ID is supported.

max_num_results

google.protobuf.Int64Value

The maximum number of results to return from the search.
Fewer results may be returned if necessary to fit within the prompt's token limit.
This ensures that the combined prompt and search results do not exceed the token constraints.

rephraser_options

RephraserOptions

Options for rephrasing user queries.
Used to rewrite the last user message for search,
incorporating context from the previous conversation.

call_strategy

CallStrategy

Defines the strategy for triggering search.
Controls whether search results are always included or returned only when
the model explicitly calls the tool.

RephraserOptionsRephraserOptions

Options for configuring the rephrasing the last user message for search using context from previous conversation.

Field

Description

rephraser_uri

string

Required field. The ID of the model used to rephrase the last user message for search.

CallStrategyCallStrategy

Defines when the assistant uses the search tool.

Field

Description

always_call

AlwaysCall

Includes only one of the fields always_call, auto_call.

One of always_call or auto_call.
always_call is used if no strategy is explicitly set

auto_call

AutoCall

Includes only one of the fields always_call, auto_call.

One of always_call or auto_call.
always_call is used if no strategy is explicitly set

AlwaysCallAlwaysCall

Always includes retrieved search results in the prompt.

Field

Description

Empty

AutoCallAutoCall

Exposes the tool as a callable function.
The model decides when to trigger search based on the instruction.

Field

Description

name

string

The name of the tool as exposed to the model.

instruction

string

Required field. Required instruction that helps the model decide when to call the tool.

FunctionToolFunctionTool

Represents a function tool that can be invoked by the assistant.

Field

Description

name

string

The name of the function.

description

string

A description of the function's purpose or behavior.

parameters

google.protobuf.Struct

A JSON Schema that defines the expected parameters for the function.
The schema should describe the required fields, their types, and any constraints or default values.

GenSearchToolGenSearchTool

Field

Description

options

GenSearchOptions

Scoping and filtering rules for the search query

description

string

Required field. description of the purpose

GenSearchOptionsGenSearchOptions

Field

Description

site

SiteOption

Includes only one of the fields site, host, url.

Restricts the search to the specific websites, hosts or pages.
Includes only one of the fields site, host, url.

host

HostOption

Includes only one of the fields site, host, url.

Restricts the search to the specific websites, hosts or pages.
Includes only one of the fields site, host, url.

url

UrlOption

Includes only one of the fields site, host, url.

Restricts the search to the specific websites, hosts or pages.
Includes only one of the fields site, host, url.

enable_nrfm_docs

bool

Use the documents inaccessible from the front page.

search_filters[]

SearchFilter

Restricts the search by date, document formats or language.

SiteOptionSiteOption

Restricts the search to the specific websites.

Field

Description

site[]

string

HostOptionHostOption

Restricts the search to the specific hosts.

Field

Description

host[]

string

UrlOptionUrlOption

Restricts the search to the specific pages.

Field

Description

url[]

string

SearchFilterSearchFilter

Field

Description

date

string

Restrict by document date

Includes only one of the fields date, lang, format.

Includes only one of the fields date, lang, format.

lang

string

Restrict by document language. Use ISO 639-1 language codes.

Includes only one of the fields date, lang, format.

Includes only one of the fields date, lang, format.

format

enum DocFormat

Restrict by document format.

Includes only one of the fields date, lang, format.

Includes only one of the fields date, lang, format.

  • DOC_FORMAT_UNSPECIFIED
  • DOC_FORMAT_PDF
  • DOC_FORMAT_XLS
  • DOC_FORMAT_ODS
  • DOC_FORMAT_RTF
  • DOC_FORMAT_PPT
  • DOC_FORMAT_ODP
  • DOC_FORMAT_SWF
  • DOC_FORMAT_ODT
  • DOC_FORMAT_ODG
  • DOC_FORMAT_DOC

ResponseFormatResponseFormat

Specifies the format of the model's response.

Field

Description

json_object

bool

When set to true, the model will respond with a valid JSON object.
Be sure to explicitly ask the model for JSON.
Otherwise, it may generate excessive whitespace and run indefinitely until it reaches the token limit.

Includes only one of the fields json_object, json_schema.

json_schema

JsonSchema

Enforces a specific JSON structure for the model's response based on a provided schema.

Includes only one of the fields json_object, json_schema.

JsonSchemaJsonSchema

Represents the expected structure of the model's response using a JSON Schema.

Field

Description

schema

google.protobuf.Struct

The JSON Schema that the model's output must conform to.

Была ли статья полезна?

Предыдущая
Delete
Следующая
ListVersions
Проект Яндекса
© 2025 ТОО «Облачные Сервисы Казахстан»