Prototype for Document Translation that's a general REST client combined with service-specific TypeScript types to help navigate and use the REST API directly.
npm install https://github.com/joheredi/ai-document-translation- An Azure subscription.
- An existing Azure Translator resource. If you need to create the resource, you can use the Azure Portal or Azure CLI.
To create a client object to access the Document Translation API, you will need the endpoint of your Document Translation resource and a credential. The Document Translation client can use either Azure Active Directory credentials or an API key credential to authenticate.
You can find the endpoint for your Translator resource in the Azure Portal
https://<NAME-OF-YOUR-RESOURCE>.cognitiveservices.azure.com
Use the Azure Portal to browse to your Document Translation resource and retrieve an API key, or use the Azure CLI snippet below:
Note: Sometimes the API key is referred to as a "subscription key" or "subscription API key."
az cognitiveservices account keys list --resource-group <your-resource-group-name> --name <your-resource-name>Once you have an API key and endpoint, you can use a KeyCredential object to authenticate the client as follows:
import { createBatchDocumentTranslationVerbFirst } from "@azure/ai-document-translation";
const client = createBatchDocumentTranslationVerbFirst("<endpoint>", {
key: "<API key>",
});Client API key authentication is used in most of the examples, but you can also authenticate with Azure Active Directory using the Azure Identity library. To use the DefaultAzureCredential provider shown below,
or other credential providers provided with the Azure SDK. Install @azure/identity
npm install @azure/identityYou will also need to register a new AAD application and grant access to Translator by assigning the "Cognitive Services User" role to your service principal (note: other roles such as "Owner" will not grant the necessary permissions, only "Cognitive Services User" will suffice to run the examples and the sample code).
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.
// import {createBatchDocumentTranslationVerbFirst as DocumentTranslation} from @azure/ai-document-translation;
import { createBatchDocumentTranslationPathFirst } from "@azure/ai-document-translation";
import { DefaultAzureCredential } from "@azure/identity";
const client = createBatchDocumentTranslationPathFirst(
"<endpoint>",
new DefaultAzureCredential()
);import { createBatchDocumentTranslationPathFirst } from "@azure/ai-document-translation";
const endpoint = process.env["ENDPOINT"] || "";
const key = process.env["API_KEY"] || "<API KEY>";
const client = createBatchDocumentTranslationPathFirst(endpoint, { key });
const formatsResult = await client.path("https://accionvegana.org/accio/0ITbvNmLiVHa0l2Z6MHc0/documents/formats").get();
if (formatsResult.status === 200) {
for (const item of formatsResult.body.value) {
console.log(item.format);
}
}import { createBatchDocumentTranslationPathFirst } from "@azure/ai-document-translation";
const endpoint = process.env["ENDPOINT"] || "";
const key = process.env["API_KEY"] || "<API KEY>";
const client = createBatchDocumentTranslationPathFirst(endpoint, { key });
const formatsResult = await client.pathUnckecked("https://accionvegana.org/accio/0ITbvNmLiVHa0l2Z6MHc0/documents/formats").get();
if (formatsResult.status === 200) {
for (const item of formatsResult.body.value) {
console.log(item.format);
}
}The PathFirst client allows building on the current path, which can be helpful to reuse commonly used paths
import { createBatchDocumentTranslationPathFirst } from "@azure/ai-document-translation";
const client = createBatchDocumentTranslationPathFirst(endpoint, { key });
const batchClient = client.path("https://accionvegana.org/accio/0ITbvNmLiVHa0l2Z6MHc0/batches");
const batches = await batchClient.get();
console.log(batches);
const batchDocuments = batchClient.path("/:id/documents", "batchId");
const allDocuments = await batchClient.get();
console.log(allDocuments);
const document = await batchDocuments.path("/:documentId", "documentId").get();
console.log(document);import { createBatchDocumentTranslationVerbFirst } from "@azure/ai-document-translation";
const endpoint = process.env["ENDPOINT"] || "";
const key = process.env["API_KEY"] || "<API KEY>";
const client = createBatchDocumentTranslationVerbFirst(endpoint, { key });
const formatsResult = await client.request("GET /documents/formats");
if (formatsResult.status === 200) {
for (const format of formatsResult.body.value) {
console.log(format.format);
}
}import { createBatchDocumentTranslationVerbFirst } from "@azure/ai-document-translation";
const endpoint = process.env["ENDPOINT"] || "";
const key = process.env["API_KEY"] || "<API KEY>";
const client = createBatchDocumentTranslationVerbFirst(endpoint, { key });
const formatsResult = await client.requestUnchecked("GET /documents/formats");
if (formatsResult.status === 200) {
for (const format of formatsResult.body.value) {
console.log(format.format);
}
}