Vertex AI Translation은 Google Distributed Cloud (GDC) 에어갭 어플라이언스에 있는 3개의 Vertex AI 사전 학습된 API 중 하나입니다. Vertex AI Translation 서비스를 사용하면 10개 이상의 언어로 작성된 텍스트를 영어로 번역할 수 있습니다.
Vertex AI Translation은 GDC 에어갭 어플라이언스에서 사용할 수 있는 다음 방법을 제공합니다.
[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["이해하기 어려움","hardToUnderstand","thumb-down"],["잘못된 정보 또는 샘플 코드","incorrectInformationOrSampleCode","thumb-down"],["필요한 정보/샘플이 없음","missingTheInformationSamplesINeed","thumb-down"],["번역 문제","translationIssue","thumb-down"],["기타","otherDown","thumb-down"]],["최종 업데이트: 2025-09-04(UTC)"],[],[],null,["# Learn about translation features\n\nVertex AI Translation is one of the three Vertex AI\npre-trained APIs on Google Distributed Cloud (GDC) air-gapped appliance. With the\nVertex AI Translation service, you can translate text written in more than\nten languages into English.\n\nVertex AI Translation offers the following methods available in\nGDC air-gapped appliance:\n\nBefore making translation requests, [set up a translation project](/distributed-cloud/hosted/docs/latest/appliance/application/ao-user/vai-set-up-translation).\nYou can test the Vertex AI Translation API on GDC air-gapped appliance by\n[translating text](/distributed-cloud/hosted/docs/latest/appliance/application/ao-user/quickstart-translation)\nfrom one language to another.\n\nConsiderations\n--------------\n\nWhen using the Vertex AI Translation API, particularly the `translateText`\nmethod, consider the following aspects:\n\n- The maximum input length of contents for translation is 1024 characters.\n- You can translate up to 61,000 characters per minute, equivalent to 1,024 characters per second.\n- The `translateText` method doesn't support batching.\n- Types of characters and large portions of text affect translation quality.\n Therefore, if you experience translation issues, follow these steps:\n\n 1. Remove all special and escape characters that might affect the processing of the request.\n 2. Reduce the input size by splitting the contents into smaller sentences.\n 3. Translate each of the smaller sentences again by sending them in separate requests to the endpoint.\n\nFailure to follow these limiting considerations might result in errors."]]
