AI_TRANSLATE

更新时间:
复制 MD 格式

AI_TRANSLATE is a MaxCompute AI function that calls a model to translate input text into a specified language.

Syntax

STRING AI_TRANSLATE(
  STRING <model_name>,
  STRING <version_name>,
  STRING <input>,
  STRING <target_language>
  [, STRING <model_parameters>]
);

Parameters

  • model_name: Required. STRING. The name of the model to use. For more information, see SQL AI functions.

  • version_name: Required. STRING. The version of the model to use. To call the default version, enter DEFAULT_VERSION.

  • input: Required. STRING. The text to translate.

  • target_language: Required. STRING. The target language for the translation, specified as an ISO-639 language code. The following language codes are supported:

    Language code

    Language

    zh

    Chinese

    en

    English

    es

    Spanish

    fr

    French

    de

    German

    ja

    Japanese

    ko

    Korean

    ru

    Russian

    ar

    Arabic

    pt

    Portuguese

  • model_parameters: Optional. STRING. Specifies model parameters such as max_tokens, temperature, and top_p. The format is a JSON string:

    '{"max_tokens": 500, "temperature": 0.6, "top_p": 0.95}'.

    • max_tokens: The maximum number of tokens to generate in a single model call. For MaxCompute public models, the default value is 4,096.

    • temperature: A value between 0 and 1 that controls the randomness of the output. A higher value results in more creative and diverse output, while a lower value produces more deterministic and conservative output.

    • top_p: A value between 0 and 1 that limits the range of candidate labels the model can choose from. A higher value allows for a broader range and more diversity, while a lower value narrows the range and produces more focused results.

Return value

Returns the translated text as a STRING value.

  • If the input or target_language parameter is not a STRING, an error is returned.

Examples

Example 1: Translate text into a specified language

Calls the qwen3.7-max public model provided by MaxCompute to translate an English sentence into Chinese.

SET odps.namespace.schema=true;

SELECT AI_TRANSLATE(
    bigdata_public_modelset.default.`qwen3.7-max`,
    DEFAULT_VERSION,
    'MaxCompute is a fast and fully managed computing platform for large-scale data warehousing.',
    'zh'
) AS translated_text;

-- Result
+-------------------------------------------------------------------------------------------+
| translated_text                                                                           |
+-------------------------------------------------------------------------------------------+
| MaxCompute is a fast and fully managed computing platform for large-scale data warehousing. |
+-------------------------------------------------------------------------------------------+

Example 2: Translate table data into multiple languages

Calls the deepseek-v4-pro public model provided by MaxCompute to translate the same English text into Chinese, Japanese, French, and Spanish in a single query.

-- Sample data
CREATE TABLE translation_tasks (
    source_text STRING,
    lang STRING
);

INSERT INTO translation_tasks VALUES
    ('Welcome to Alibaba Cloud.', 'zh'),
    ('Welcome to Alibaba Cloud.', 'ja'),
    ('Welcome to Alibaba Cloud.', 'fr'),
    ('Welcome to Alibaba Cloud.', 'es');

-- Translate the same text into multiple target languages
SET odps.namespace.schema=true;

SELECT
    source_text,
    lang,
    AI_TRANSLATE(
        bigdata_public_modelset.default.`deepseek-v4-pro`,
        DEFAULT_VERSION,
        source_text,
        lang
    ) AS translated_text
FROM translation_tasks;

-- Results
+-----------------------------+------+-------------------------------+
| source_text                 | lang | translated_text               |
+-----------------------------+------+-------------------------------+
| Welcome to Alibaba Cloud.   | zh   | Welcome to Alibaba Cloud.     |
| Welcome to Alibaba Cloud.   | ja   | アリババクラウドへようこそ。       |
| Welcome to Alibaba Cloud.   | fr   | Bienvenue sur Alibaba Cloud.  |
| Welcome to Alibaba Cloud.   | es   | Bienvenido a Alibaba Cloud.   |
+-----------------------------+------+-------------------------------+

FAQ

Troubleshoot common issues with public models

Symptom: When you call a public model that is supported by the model computing service, the following error message is returned.

FAILED: ODPS-0130071:[1,8] Semantic analysis exception - inference quota status check failed, error message: region cn-shanghai not found in inference quota

Cause: The model computing service is not enabled for the region, such as China (Shanghai), where your current project is located. As a result, AI inference resources cannot be called.

Solution: Go to the Alibaba Cloud Management Console to enable the model computing service for the region where your project is located. For more information, see Purchase and use the MaxCompute model computing service.