Azure Document Translation client library for Python

Azure Cognitive Services Document Translation is a cloud service that translates documents to and from 90 languages and dialects while preserving document structure and data format. Use the client library for Document Translation to:

  • Translate numerous, large files from an Azure Blob Storage container to a target container in your language of choice.

  • Check the translation status and progress of each document in the translation operation.

  • Apply a custom translation model or glossaries to tailor translation to your specific case.

Source code | Package (PyPI) | API reference documentation | Product documentation | Samples

Getting started

Prerequisites

Install the package

Install the Azure Document Translation client library for Python with pip:

pip install azure-ai-translation-document --pre

Note: This version of the client library defaults to the v1.0 version of the service

Create a Document Translation resource

Document Translation supports single-service access only. To access the service, create a Translator resource.

You can create the resource using

Option 1: Azure Portal

Option 2: Azure CLI. Below is an example of how you can create a Document Translation resource using the CLI:

# Create a new resource group to hold the document translation resource -
# if using an existing resource group, skip this step
az group create --name my-resource-group --location westus2

# Create document translation
az cognitiveservices account create \
    --name document-translation-resource \
    --custom-domain document-translation-resource \
    --resource-group my-resource-group \
    --kind TextTranslation \
    --sku S1 \
    --location westus2 \
    --yes

Authenticate the client

In order to interact with the Document Translation service, you will need to create an instance of a client. An endpoint and credential are necessary to instantiate the client object.

Looking up the endpoint

You can find the endpoint for your Document Translation resource using the Azure Portal.

Note that the service requires a custom domain endpoint. Follow the instructions in the above link to format your endpoint: https://{NAME-OF-YOUR-RESOURCE}.cognitiveservices.azure.com/

Get the API key

The API key can be found in the Azure Portal or by running the following Azure CLI command:

az cognitiveservices account keys list --name "resource-name" --resource-group "resource-group-name"

Create the client with AzureKeyCredential

To use an API key as the credential parameter, pass the key as a string into an instance of AzureKeyCredential.

from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document import DocumentTranslationClient

endpoint = "https://<resource-name>.cognitiveservices.azure.com/"
credential = AzureKeyCredential("<api_key>")
document_translation_client = DocumentTranslationClient(endpoint, credential)

Create the client with an Azure Active Directory credential

AzureKeyCredential authentication is used in the examples in this getting started guide, but you can also authenticate with Azure Active Directory using the azure-identity library.

To use the DefaultAzureCredential type shown below, or other credential types provided with the Azure SDK, please install the azure-identity package:

pip install azure-identity

You will also need to register a new AAD application and grant access to your Translator resource by assigning the "Cognitive Services User" role to your service principal.

Once completed, set the values of the client ID, tenant ID, and client secret of the AAD application as environment variables: AZURE_CLIENT_ID, AZURE_TENANT_ID, AZURE_CLIENT_SECRET.

from azure.identity import DefaultAzureCredential
from azure.ai.translation.document import DocumentTranslationClient
credential = DefaultAzureCredential()

document_translation_client = DocumentTranslationClient(
    endpoint="https://<resource-name>.cognitiveservices.azure.com/",
    credential=credential
)

Key concepts

The Document Translation service requires that you upload your files to an Azure Blob Storage source container and provide a target container where the translated documents can be written. SAS tokens to the containers (or files) are used to access the documents and create the translated documents in the target container. Additional information about setting this up can be found in the service documentation:

DocumentTranslationClient

Interaction with the Document Translation client library begins with an instance of the DocumentTranslationClient. The client provides operations for:

  • Creating a translation operation to translate documents in your source container(s) and write results to you target container(s).

  • Checking the status of individual documents in the translation operation and monitoring each document’s progress.

  • Enumerating all past and current translations operations.

  • Identifying supported glossary and document formats.

Translation Input

Input to the begin_translation client method can be provided in two different ways:

  1. A single source container with documents can be translated to a different language:

from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document import DocumentTranslationClient

document_translation_client = DocumentTranslationClient("<endpoint>", AzureKeyCredential("<api_key>"))
poller = document_translation_client.begin_translation("<sas_url_to_source>", "<sas_url_to_target>", "<target_language_code>")

  1. Or multiple different sources can be provided each with their own targets.

from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document import DocumentTranslationClient, DocumentTranslationInput, TranslationTarget

my_input = [
    DocumentTranslationInput(
        source_url="<sas_url_to_source_A>",
        targets=[
            TranslationTarget(target_url="<sas_url_to_target_fr>", language_code="fr"),
            TranslationTarget(target_url="<sas_url_to_target_de>", language_code="de")
        ]
    ),
    DocumentTranslationInput(
        source_url="<sas_url_to_source_B>",
        targets=[
            TranslationTarget(target_url="<sas_url_to_target_fr>", language_code="fr"),
            TranslationTarget(target_url="<sas_url_to_target_de>", language_code="de")
        ]
    ),
    DocumentTranslationInput(
        source_url="<sas_url_to_source_C>",
        targets=[
            TranslationTarget(target_url="<sas_url_to_target_fr>", language_code="fr"),
            TranslationTarget(target_url="<sas_url_to_target_de>", language_code="de")
        ]
    )
]

document_translation_client = DocumentTranslationClient("<endpoint>", AzureKeyCredential("<api_key>"))
poller = document_translation_client.begin_translation(my_input)

Note: the target_url for each target language must be unique.

See the service documentation for all supported languages.

Long-Running Operations

Long-running operations are operations which consist of an initial request sent to the service to start an operation, followed by polling the service at intervals to determine whether the operation has completed or failed, and if it has succeeded, to get the result.

Methods that translate documents are modeled as long-running operations. The client exposes a begin_<method-name> method that returns a DocumentTranslationLROPoller or AsyncDocumentTranslationLROPoller. Callers should wait for the operation to complete by calling result() on the poller object returned from the begin_<method-name> method. Sample code snippets are provided to illustrate using long-running operations below.

Examples

The following section provides several code snippets covering some of the most common Document Translation tasks, including:

Translate your documents

Translate the documents in your source container to the target container.

from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document import DocumentTranslationClient

endpoint = "https://<resource-name>.cognitiveservices.azure.com/"
credential = AzureKeyCredential("<api_key>")
source_container_sas_url_en = "<sas-url-en>"
target_container_sas_url_es = "<sas-url-es>"

document_translation_client = DocumentTranslationClient(endpoint, credential)

poller = document_translation_client.begin_translation(source_container_sas_url_en, target_container_sas_url_es, "es")

result = poller.result()

print("Status: {}".format(poller.status()))
print("Created on: {}".format(poller.details.created_on))
print("Last updated on: {}".format(poller.details.last_updated_on))
print("Total number of translations on documents: {}".format(poller.details.documents_total_count))

print("\nOf total documents...")
print("{} failed".format(poller.details.documents_failed_count))
print("{} succeeded".format(poller.details.documents_succeeded_count))

for document in result:
    print("Document ID: {}".format(document.id))
    print("Document status: {}".format(document.status))
    if document.status == "Succeeded":
        print("Source document location: {}".format(document.source_document_url))
        print("Translated document location: {}".format(document.translated_document_url))
        print("Translated to language: {}\n".format(document.translated_to))
    else:
        print("Error Code: {}, Message: {}\n".format(document.error.code, document.error.message))

Translate multiple inputs

Begin translating with documents in multiple source containers to multiple target containers in different languages.

from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document import DocumentTranslationClient, DocumentTranslationInput, TranslationTarget

endpoint = "https://<resource-name>.cognitiveservices.azure.com/"
credential = AzureKeyCredential("<api_key>")
source_container_sas_url_de = "<sas-url-de>"
source_container_sas_url_en = "<sas-url-en>"
target_container_sas_url_es = "<sas-url-es>"
target_container_sas_url_fr = "<sas-url-fr>"
target_container_sas_url_ar = "<sas-url-ar>"

document_translation_client = DocumentTranslationClient(endpoint, credential)

poller = document_translation_client.begin_translation(
    [
        DocumentTranslationInput(
            source_url=source_container_sas_url_en,
            targets=[
                TranslationTarget(target_url=target_container_sas_url_es, language_code="es"),
                TranslationTarget(target_url=target_container_sas_url_fr, language_code="fr"),
            ],
        ),
        DocumentTranslationInput(
            source_url=source_container_sas_url_de,
            targets=[
                TranslationTarget(target_url=target_container_sas_url_ar, language_code="ar"),
            ],
        )
    ]
)

result = poller.result()

for document in result:
    print("Document ID: {}".format(document.id))
    print("Document status: {}".format(document.status))
    if document.status == "Succeeded":
        print("Source document location: {}".format(document.source_document_url))
        print("Translated document location: {}".format(document.translated_document_url))
        print("Translated to language: {}\n".format(document.translated_to))
    else:
        print("Error Code: {}, Message: {}\n".format(document.error.code, document.error.message))

List translation operations

Enumerate over the translation operations submitted for the resource.

from azure.core.credentials import AzureKeyCredential
from azure.ai.translation.document import DocumentTranslationClient

endpoint = "https://<resource-name>.cognitiveservices.azure.com/"
credential = AzureKeyCredential("<api_key>")

document_translation_client = DocumentTranslationClient(endpoint, credential)

operations = document_translation_client.list_all_translation_statuses()  # type: ItemPaged[TranslationStatusResult]

for operation in operations:
    print("\nID: {}".format(operation.id))
    print("Status: {}".format(operation.status))
    print("Created on: {}".format(operation.created_on))
    print("Last updated on: {}".format(operation.last_updated_on))
    print("Total number of translations on documents: {}".format(operation.documents_total_count))
    print("Total number of characters charged: {}".format(operation.total_characters_charged))

    print("Of total documents...")
    print("{} failed".format(operation.documents_failed_count))
    print("{} succeeded".format(operation.documents_succeeded_count))
    print("{} cancelled".format(operation.documents_cancelled_count))

To see how to use the Document Translation client library with Azure Storage Blob to upload documents, create SAS tokens for your containers, and download the finished translated documents, see this sample. Note that you will need to install the azure-storage-blob library to run this sample.

Troubleshooting

General

Document Translation client library will raise exceptions defined in Azure Core.

Logging

This library uses the standard logging library for logging.

Basic information about HTTP sessions (URLs, headers, etc.) is logged at INFO level.

Detailed DEBUG level logging, including request/response bodies and unredacted headers, can be enabled on the client or per-operation with the logging_enable keyword argument.

See full SDK logging documentation with examples here.

Optional Configuration

Optional keyword arguments can be passed in at the client and per-operation level. The azure-core reference documentation describes available configurations for retries, logging, transport protocols, and more.

Next steps

The following section provides several code snippets illustrating common patterns used in the Document Translation Python client library.

More sample code

These code samples show common scenario operations with the Azure Document Translation client library.

Async samples

This library also includes a complete async API supported on Python 3.6+. To use it, you must first install an async transport, such as aiohttp. Async clients are found under the azure.ai.translation.document.aio namespace.

Additional documentation

For more extensive documentation on Azure Cognitive Services Document Translation, see the Document Translation documentation on docs.microsoft.com.

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit cla.microsoft.com.

When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Indices and tables

Developer Documentation