Azure AI Translation Document Py

pip install azure-ai-translation-document

AZURE_DOCUMENT_TRANSLATION_ENDPOINT=https://<resource>.cognitiveservices.azure.com  # Required for all auth methods
# Storage for source and target documents
AZURE_SOURCE_CONTAINER_URL=https://<storage>.blob.core.windows.net/<container>?<sas>  # Required for all auth methods
AZURE_TARGET_CONTAINER_URL=https://<storage>.blob.core.windows.net/<container>?<sas>  # Required for all auth methods
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production
AZURE_DOCUMENT_TRANSLATION_KEY=<your-api-key>  # Only required for the legacy API-key auth path below

import os
from azure.identity import DefaultAzureCredential, ManagedIdentityCredential
from azure.ai.translation.document import DocumentTranslationClient

# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
credential = DefaultAzureCredential()
# Or use a specific credential directly in production:
# See https://learn.microsoft.com/python/api/overview/azure/identity-readme?view=azure-python#credential-classes
# credential = ManagedIdentityCredential()

with DocumentTranslationClient(
    endpoint=os.environ["AZURE_DOCUMENT_TRANSLATION_ENDPOINT"],
    credential=credential,
) as client:
    statuses = list(client.list_translation_statuses())

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document import DocumentTranslationClient, SingleDocumentTranslationClient

with DocumentTranslationClient(
    endpoint=os.environ["AZURE_DOCUMENT_TRANSLATION_ENDPOINT"],
    credential=AzureKeyCredential(os.environ["AZURE_DOCUMENT_TRANSLATION_KEY"]),
) as client:
    statuses = list(client.list_translation_statuses())

# SingleDocumentTranslationClient accepts the same key-based credential.

import os
from azure.ai.translation.document import DocumentTranslationClient, DocumentTranslationInput, TranslationTarget
from azure.core.exceptions import HttpResponseError
from azure.identity import DefaultAzureCredential

credential = DefaultAzureCredential()

with DocumentTranslationClient(
    endpoint=os.environ["AZURE_DOCUMENT_TRANSLATION_ENDPOINT"],
    credential=credential,
) as client:
    source_url = os.environ["AZURE_SOURCE_CONTAINER_URL"]
    target_url = os.environ["AZURE_TARGET_CONTAINER_URL"]

    try:
        # Start translation job
        poller = client.begin_translation(
            inputs=[
                DocumentTranslationInput(
                    source_url=source_url,
                    targets=[
                        TranslationTarget(
                            target_url=target_url,
                            language="es"  # Translate to Spanish
                        )
                    ]
                )
            ]
        )

        # Wait for completion
        result = poller.result()

        print(f"Status: {poller.status()}")
        print(f"Documents translated: {poller.details.documents_succeeded_count}")
        print(f"Documents failed: {poller.details.documents_failed_count}")
    except HttpResponseError as e:
        print(f"Translation failed: {e.message}")
        raise

poller = client.begin_translation(
    inputs=[
        DocumentTranslationInput(
            source_url=source_url,
            targets=[
                TranslationTarget(target_url=target_url_es, language="es"),
                TranslationTarget(target_url=target_url_fr, language="fr"),
                TranslationTarget(target_url=target_url_de, language="de")
            ]
        )
    ]
)

from azure.ai.translation.document import SingleDocumentTranslationClient
from azure.identity import DefaultAzureCredential

with open("document.docx", "rb") as f:
    document_content = f.read()

with SingleDocumentTranslationClient(endpoint, DefaultAzureCredential()) as single_client:
    result = single_client.translate(
        body=document_content,
        target_language="es",
        content_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
    )

# Save translated document
with open("document_es.docx", "wb") as f:
    f.write(result)

# Get all translation operations
operations = client.list_translation_statuses()

for op in operations:
    print(f"Operation ID: {op.id}")
    print(f"Status: {op.status}")
    print(f"Created: {op.created_on}")
    print(f"Total documents: {op.documents_total_count}")
    print(f"Succeeded: {op.documents_succeeded_count}")
    print(f"Failed: {op.documents_failed_count}")

# Get status of individual documents in a job
operation_id = poller.id
document_statuses = client.list_document_statuses(operation_id)

for doc in document_statuses:
    print(f"Document: {doc.source_document_url}")
    print(f"  Status: {doc.status}")
    print(f"  Translated to: {doc.translated_to}")
    if doc.error:
        print(f"  Error: {doc.error.message}")

# Cancel a running translation
client.cancel_translation(operation_id)

from azure.ai.translation.document import TranslationGlossary

poller = client.begin_translation(
    inputs=[
        DocumentTranslationInput(
            source_url=source_url,
            targets=[
                TranslationTarget(
                    target_url=target_url,
                    language="es",
                    glossaries=[
                        TranslationGlossary(
                            glossary_url="https://<storage>.blob.core.windows.net/glossary/terms.csv?<sas>",
                            file_format="csv"
                        )
                    ]
                )
            ]
        )
    ]
)

# Get supported formats
formats = client.get_supported_document_formats()

for fmt in formats:
    print(f"Format: {fmt.format}")
    print(f"  Extensions: {fmt.file_extensions}")
    print(f"  Content types: {fmt.content_types}")

# Get supported languages
languages = client.get_supported_languages()

for lang in languages:
    print(f"Language: {lang.name} ({lang.code})")

from azure.ai.translation.document.aio import DocumentTranslationClient
from azure.identity.aio import DefaultAzureCredential

async def translate_documents():
    async with DefaultAzureCredential() as credential:
        async with DocumentTranslationClient(
            endpoint=endpoint,
            credential=credential,
        ) as client:
            poller = await client.begin_translation(inputs=[...])
            result = await poller.result()