translate.md

title	Use ai.translate with PySpark
description	Learn how to use the ai.translate function to translate input text into a new language of your choice with PySpark.
ms.reviewer	vimeland
ms.topic	how-to
ms.date	11/13/2025
ms.search.form	AI functions

Use ai.translate with PySpark

The ai.translate function uses generative AI to translate input text into a new language (of your choice), with a single line of code.

Note

• This article covers using ai.translate with PySpark. To use ai.translate with pandas, see this article.
• See other AI functions in this overview article.
• Learn how to customize the configuration of AI functions.

Overview

The ai.translate function is available for Spark DataFrames. You must specify an existing input column name as a parameter, along with a target language.

The function returns a new DataFrame with translations for each input text row, stored in an output column.

Syntax

df.ai.translate(to_lang="spanish", input_col="text", output_col="translations")

Parameters

Name	Description
to_lang Required	A string that represents the target language for text translations.
input_col Required	A string that contains the name of an existing column with input text values to translate.
output_col Optional	A string that contains the name of a new column that stores translations for each input text row. If you don't set this parameter, a default name generates for the output column.
error_col Optional	A string that contains the name of a new column that stores any OpenAI errors that result from processing each input text row. If you don't set this parameter, a default name generates for the error column. If an input row has no errors, the value in this column is null.

Returns

The function returns a Spark DataFrame that includes a new column that contains translations for the text in the input column row. If the input text is null, the result is null.

Example

# This code uses AI. Always review output for mistakes.

df = spark.createDataFrame([
        ("Hello! How are you doing today?",),
        ("Tell me what you'd like to know, and I'll do my best to help.",),
        ("The only thing we have to fear is fear itself.",),
    ], ["text"])

translations = df.ai.translate(to_lang="spanish", input_col="text", output_col="translations")
display(translations)

This example code cell provides the following output:

:::image type="content" source="../../media/ai-functions/translate-example-output.png" alt-text="Screenshot of a data frame with columns 'text' and 'translations'. The 'translations' column contains the text translated to Spanish." lightbox="../../media/ai-functions/translate-example-output.png":::

Multimodal input

The ai.translate function supports file-based multimodal input. You can translate the content of images, PDFs, and text files by setting input_col_type="path". For more information about supported file types and setup, see Use multimodal input with AI functions.

# This code uses AI. Always review output for mistakes.

results = custom_df.ai.translate(
    to_lang="Chinese",
    input_col="file_path",
    input_col_type="path",
    output_col="chinese_version",
)
display(results)

Related content

• Use ai.translate with pandas.

• Detect sentiment with ai.analyze_sentiment.

• Categorize text with ai.classify.

• Generate vector embeddings with ai.embed.

• Extract entities with ai_extract.

• Fix grammar with ai.fix_grammar.

• Answer custom user prompts with ai.generate_response.

• Calculate similarity with ai.similarity.

• Summarize text with ai.summarize.

• Learn more about the full set of AI functions.

• Use multimodal input with AI functions.

• Customize the configuration of AI functions.

• Did we miss a feature you need? Suggest it on the Fabric Ideas forum.