Vertex AI Translation is one of the three Vertex AI pre-trained APIs on Google Distributed Cloud (GDC) air-gapped. With the Vertex AI Translation service, you can translate text written in more than twenty languages into English.
Vertex AI Translation offers the following methods available in Distributed Cloud:
| Method | Description |
|---|---|
batchTranslateDocument |
Translate a large volume of document in asynchronous batch mode. |
detectLanguage |
Get the name of the language you are translating. |
getOperation |
Get the status of Vertex AI Translation operations. |
getSupportedLanguages |
Return a list of languages supported by the Vertex AI Translation API. For the complete list of the supported languages, see Supported languages for Vertex AI Translation. |
listOperations |
Obtain a list of operations that match a filter. |
translateDocument |
Translate documents in synchronous mode. |
translateText |
Translate input text from one language to another. |
To optionally define terms to translate, see Create and use a glossary.
Before making translation requests, set up a translation project. You can test the Vertex AI Translation API on Distributed Cloud by translating text from one language to another.
Considerations
When using the Vertex AI Translation API, particularly the translateText
method, consider the following aspects:
- The maximum input length of contents for translation is 1024 characters.
- The
translateTextmethod doesn't support batching. Types of characters and large portions of text affect translation quality. Therefore, if you experience translation issues, follow these steps:
- Remove all special and escape characters that might affect the processing of the request.
- Reduce the input size by splitting the contents into smaller sentences.
- Translate each of the smaller sentences again by sending them in separate requests to the endpoint.
For more information, see translateText.