Use Databricks Assistant
Preview
This feature is currently in Public Preview. Usage of the feature during the preview is free. Final pricing will be established and communicated prior to general availability (GA).
Databricks Assistant is a context-aware AI assistant that is available in Databricks notebooks, SQL editor, and file editor. Databricks Assistant lets you query data using a conversational interface, making you more productive inside Databricks. You can describe your task in English and let the assistant generate Python code or SQL queries, explain complex code, and automatically fix errors. The assistant uses Unity Catalog metadata to understand your tables, columns, descriptions, and popular data assets across your company to provide personalized responses.
Databricks Assistant can perform the following tasks:
Generate code.
Debug code, including identifying and suggesting fixes for errors.
Transform and optimize code.
Explain code.
Help you find relevant information in the Databricks documentation.
Databricks Assistant is enabled by default. An admin can disable or enable Databricks Assistant for all workspaces in an account. If an admin has permitted workspace setting overrides, workspace admins can enable or disable Databricks Assistant for specific workspaces. For more details, see Enable or disable Databricks Assistant.
Enablement of the Databricks Assistant for your account is captured as an account event in your audit logs, see Account-level account events.
Additional information
The following articles contain additional information about using Databricks Assistant:
How to use Databricks Assistant
Databricks Assistant is available in notebooks, SQL editor, file editor, and dashboards. This document focuses on notebooks. Usage in the other products is similar. For information about using Databricks Assistant to create visualizations for dashboards, see Create visualizations with Databricks Assistant.
In a notebook, Databricks Assistant is available in the Assistant pane or inline in a code cell.
Use Databricks Assistant in a notebook cell
To use Databricks Assistant directly in a code cell, press Cmd + i
on MacOS or Ctrl + i
on Windows. A text box appears within the cell. You can type a question or comment in English and then press Enter (not Shift+Enter, as you would to run a cell) to have the assistant generate a response.
You can also type /
to display a list of common commands, such as /explain
to explain the code in a cell, /fix
to propose a fix if the code has an error, and /doc
to suggest documentation comments for your code.
When you use /fix
or /doc
, the assistant displays proposed changes in a diff window. Select Accept to accept the proposed changes or Reject to keep the original code. If you accept the proposed code, the code does not automatically run. You can review the code before running it. If the generated code is not what you wanted, try again by adding more details or information to your comment. See Tips for using Databricks Assistant.
For code autocomplete, performance may be better using the Assistant pane than in a notebook cell.
To exit the Assistant in a notebook cell, click in the upper-right corner of the cell. The Assistant closes automatically if you Accept or Reject the code it generated.
Use the Assistant pane
To open the Assistant pane, click in the left sidebar.
Type questions in the text box at the bottom of the Assistant pane and press Enter or click at the right of the text box. The Assistant displays its answer. The following screenshot shows actions you can take after the Assistant has generated code in the Assistant pane.
You can run the same query again to generate another answer. To do so, hover your cursor over the answer and click .
To close the pane, click the icon again or click in the upper-right corner of the cell. You can expand the pane to full width by clicking ; click to return the pane to default width.
The Assistant pane keeps track of your conversations even if you close the pane or notebook. To clear previous conversations, click at the upper-right of the Assistant pane.
AI-based autocomplete
Preview
This feature is in Public Preview.
AI-based autocomplete provides inline code suggestions as you type in Databricks notebooks, the SQL editor, and the file editor. Inline code suggestions are available for Python and SQL.
Enable and disable inline code suggestions
The feature must be enabled for each user as follows:
Click Settings.
Under Experimental features, toggle Databricks Assistant Autocomplete.
Note
To disable this feature for your workspace, contact Databricks.
Inline code suggestions are not available in AWS GovCloud regions or workspaces with FedRAMP compliance.
Debug code
To use Databricks Assistant to fix code, ask a question in the Assistant pane or click the Diagnose Error button that appears in the cell results when an error occurs. The tabs below show examples for Python and SQL code.
Explain code
Databricks Assistant can provide detailed explanations of code snippets. In the prompt you provide, you can include terms like “be concise” or “explain code line-by-line” to request the level of detail for the explanation it provides. You can also ask Databricks Assistant to add comments to code.
Find relevant information in the Databricks documentation
Databricks Assistant can help answer questions based on Databricks documentation directly from the notebook editor.
Tips for using Databricks Assistant
This section includes some general tips and best practices when using Databricks Assistant.
Databricks Assistant uses context to provide better answers
Databricks Assistant has accesss to table and column schema and metadata. This allows you to use natural language and generate more accurate queries. For example, if a table has a column State, you can ask Databricks Assistant to generate a list of users who live in Michigan.
Databricks Assistant uses the following context:
Code or queries in the current notebook cell or Databricks SQL editor tab.
Table and Column names and descriptions.
Previous prompt questions.
Favorite and active tables.
For the diagnose error feature, the stack trace from the error output.
When selecting columns from a DataFrame, you can get more accurate results by providing a starting query. For example, provide a statement like SELECT * FROM <table_name>
. This allows Databricks Assistant to get the column names and not have to guess.
Because Databricks Assistant uses your conversation history to provide better and more accurate answers, you can ask Databricks Assistant to alter the output of a previous response without having to rewrite the entire prompt. You can use the Assistant’s chat history to iteratively clean, explore, filter, and slice DataFrames in the Assistant pane.
Be specific
The structure and detail that Databricks Assistant provides varies from time to time, even for the same prompt. Try to provide the assistant as much guidance as you can to help it return the information you want in the desired format, level of detail, and so on. For example:
“Explain this code in a couple sentences” or “Explain this code line-by-line”.
“Create a visualization using MatPlotLib” or “Create a visualization using Seaborn”.
Give examples of row-level data values
Because Databricks Assistant does not use row-level data, you might need to provide more detail to prompts to get the most accurate answer. Use table or column comments in Catalog Explorer to add a line of sample data. For example, suppose your height column is in the format feet
-inches
. To help the assistant interpret the data, add a comment such as “The height column is in string format and is separated by a hyphen. Example: ‘6-2’.” For information about table and column comments, see Document data in Catalog Explorer using markdown comments.
You might also need to provide details if column data type conversions are needed to perform an operation. For example: “convert this code from pandas to PySpark, including the code needed to convert the pandas DataFrame to a PySpark DataFrame and changing the data type of column churn from boolean to integer”.
Use Shift+Enter to add a new line in the chat text box
You can use Shift+Enter to add a new line in the Assistant chat text box. This makes it easy to format and organize your messages to Databricks Assistant.
Edit and run code in Databricks Assistant chat pane
You can run code in the Assistant pane to validate it or use it as a scratchpad. To run code, click in the upper-left corner of the code box in the Assistant pane. The tabs below show examples for Python and SQL code.
When you run code in the Assistant pane, output is displayed and the variables become usable in the notebook.
You can also edit the code that Databricks Assistant generates directly in the Assistant chat box before moving the code to the notebook.