Skip to content

how-to-use-text-translator.md

Latest commit

 

History

History
244 lines (176 loc) · 6.74 KB

how-to-use-text-translator.md

File metadata and controls

244 lines (176 loc) · 6.74 KB
title Use Azure Translator in Foundry Tools with REST API
description How to use prebuilt Azure AI translator in Fabric with REST API
ms.author lagayhar
ms.reviewer ruxu
ms.topic how-to
ms.date 02/28/2026
ms.update-cycle 180-days
ms.search.form
ms.collection ce-skilling-ai-copilot

Use prebuilt Azure Translator in Foundry Tools in Fabric with REST API and SynapseML (preview)

[!INCLUDE feature-preview]

Azure Translator in Foundry Tools is a Microsoft Foundry tool that enables you to perform language translation and other language-related operations.

This sample shows how to use the prebuilt Azure AI translator in Fabric with RESTful APIs to:

  • Translate text
  • Transliterate text
  • Get supported languages

Prerequisites

[!INCLUDE prerequisites]

  • Create a new notebook.
  • Attach your notebook to a lakehouse. On the left side of your notebook, select Add to add an existing lakehouse or create a new one.

Note

This article uses Microsoft Fabric's built-in prebuilt Foundry Tools, which handle authentication automatically. You don't need to obtain a separate Foundry Tools key - the authentication is managed through your Fabric workspace. For more information, see Prebuilt AI models in Fabric (preview).

The code samples in this article use libraries that are preinstalled in Microsoft Fabric notebooks:

  • SynapseML: Preinstalled in Fabric notebooks for machine learning capabilities
    • synapse.ml.core - Core SynapseML functionality
    • synapse.ml.fabric.service_discovery - Fabric service discovery utilities
    • synapse.ml.fabric.token_utils - Authentication token utilities
    • synapse.ml.services - Foundry Tools integration (includes Translate, Transliterate classes)
  • PySpark: Available by default in Fabric Spark compute
    • pyspark.sql.functions - DataFrame transformation functions (col, flatten)
  • Standard Python libraries: Built into Python runtime
    • json - JSON parsing and formatting
    • requests - HTTP client for REST API calls

Rest API

# Get workload endpoints and access token

from synapse.ml.fabric.service_discovery import get_fabric_env_config
from synapse.ml.fabric.token_utils import TokenUtils
import json
import requests


fabric_env_config = get_fabric_env_config().fabric_env_config
auth_header = TokenUtils().get_openai_auth_header()

# Make a RESTful request to Foundry tool
prebuilt_AI_base_host = fabric_env_config.ml_workload_endpoint + "cognitive/texttranslation/"
print("Workload endpoint for Foundry tool: \n" + prebuilt_AI_base_host)

service_url = prebuilt_AI_base_host + "language/:analyze-text?api-version=2022-05-01"
print("Service URL: \n" + service_url)

auth_headers = {
    "Authorization" : auth_header
}

def print_response(response):
    print(f"HTTP {response.status_code}")
    if response.status_code == 200:
        try:
            result = response.json()
            print(json.dumps(result, indent=2, ensure_ascii=False))
        except:
            print(f"parse error {response.content}")
    else:
        print(f"error message: {response.content}")

SynapseML

import synapse.ml.core
from synapse.ml.services import *
from pyspark.sql.functions import col, flatten

Text Translation

Rest API

Text translation is the core operation of the Translator service.

service_url = prebuilt_AI_base_host + "translate?api-version=3.0&to=fr"
post_body = [{'Text':'Hello, friend.'}]

response = requests.post(service_url, json=post_body, headers=auth_headers)

# Output all information of the request process
print_response(response)

Output

    HTTP 200
    [
      {
        "detectedLanguage": {
          "language": "en",
          "score": 1.0
        },
        "translations": [
          {
            "text": "Bonjour cher ami.",
            "to": "fr"
          }
        ]
      }
    ]

SynapseML

Text translation is the core operation of the Translator service.

df = spark.createDataFrame([
  (["Hello, what is your name?", "Bye"],)
], ["text",])

translate = (Translate()
    .setTextCol("text")
    .setToLanguage(["zh-Hans", "fr"])
    .setOutputCol("translation")
    .setConcurrency(5))

result = translate.transform(df)\
        .withColumn("translation", flatten(col("translation.translations")))\
        .withColumn("translation", col("translation.text"))

display(result.select("text", "translation"))

Text Transliteration

Rest API

Transliteration converts a word or phrase from the script (alphabet) of one language to another, based on phonetic similarity.

service_url = prebuilt_AI_base_host + "transliterate?api-version=3.0&language=ja&fromScript=Jpan&toScript=Latn"
post_body = [
    {"Text":"こんにちは"},
    {"Text":"さようなら"}
]

response = requests.post(service_url, json=post_body, headers=auth_headers)

# Output all information of the request process
print_response(response)

Output

    HTTP 200
    [
      {
        "text": "Kon'nichiwa​",
        "script": "Latn"
      },
      {
        "text": "sayonara",
        "script": "Latn"
      }
    ]

SynapseML

Transliteration converts a word or phrase from the script (alphabet) of one language to another, based on phonetic similarity.

transliterateDf =  spark.createDataFrame([
  (["こんにちは", "さようなら"],)
], ["text",])

transliterate = (Transliterate()
    .setLanguage("ja")
    .setFromScript("Jpan")
    .setToScript("Latn")
    .setTextCol("text")
    .setOutputCol("result"))

result = transliterate.transform(transliterateDf)\
        .withColumn("script", col("result.script"))

display(result.select("text", "script"))

Supported Languages Retrieval

Rest API

Returns a list of languages that Translator operations support.

service_url = prebuilt_AI_base_host + "languages?api-version=3.0"

response = requests.get(service_url, headers=auth_headers)

# Output all information of the request process
print_response(response)

SynapseML

No steps for SynapseML in this section.

Related content