complete
Generates text using YandexGPT by sending a dialogue history and receiving a synchronous response. Supports model selection, token limits, and temperature control.
Instructions
Генерация текста через YandexGPT. Синхронный запрос с ожиданием ответа.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"messages": "<messages>"
},
"name": "complete"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Модель (yandexgpt-lite, yandexgpt, yandexgpt-32k) | yandexgpt-lite |
| messages | Yes | Массив сообщений диалога | |
| maxTokens | No | Максимальное количество токенов | |
| temperature | No | Температура генерации (0–1) |