Skip to main content
Production use of this feature is available for specific editions only. Contact our sales team for more information.
The AI Fix Grammar transformation component uses the Databricks ai_fix_grammar() function to invoke generative AI to correct grammatical errors found in text in your input table. This function uses a Databricks chat model serving endpoint made available by Databricks Foundation Model APIs. The input to this component is a column of data in string format. The component can operate on multiple columns from the source table, as specified in the Columns property. The output is a string with corrected grammar, with one output column created per input column.
Make sure you have read and understand the Requirements set out by Databricks before using this component.

​
Use case

This component is especially helpful for cleaning up messy or user-entered text data before using it for analytics, Natural Language Processing (NLP), or reporting. Some typical use cases include:
  • Standardizing customer feedback or reviews.
  • Improving readability of CRM or sales notes.
  • Preparing text for sentiment analysis.

​
Properties

​
string
required
A human-readable name for the component.
​
object selector
required
Select the columns to check for grammatical errors. A new column with corrections is created for each input column.
​
boolean
required
  • Yes: Includes both your input columns with grammatical errors and the new columns with corrections. This will also include those input columns not selected in Columns.
  • No: Only includes the new correction columns.