Introducing Databricks Assistant Autocomplete

We are excited to introduce Databricks Assistant Autocomplete now in Public Preview. This feature brings the AI-powered assistant to you in real-time, providing personalized code suggestions as you type. Directly integrated into the notebook and SQL editor, Assistant Autocomplete suggestions blend seamlessly into your development flow and allow you to stay focused in the editor. 

Boost Productivity with AI-generated Code Suggestions

Databricks Assistant Autocomplete automatically provides fast code suggestions as you type in SQL and Python. AI code completion uses context from current code cells, Unity Catalog metadata, DataFrame data, and more to generate highly relevant suggestions as you type.

SQL

Python

Getting the most out of Databricks Assistant Autocomplete 

Databricks Assistant Autocomplete is a powerful tool, but can be enhanced by providing extra context. In order to get the most relevant and useful suggestions you’ll need to think about how to convey your intent properly. You can accomplish this through some of the following best practices:

• Provide comments for your functions and code
• Use clear and meaningful names for functions and variables
• Follow consistent and standard code style conventions

Databricks Assistant Autocomplete Example Use Cases 

Refactor existing functions 

Databricks Assistant autocomplete takes context from the nearby code to make refactoring and adding to functions easier than ever.

Generate tests and sample data 

Create sample data and generate tests without leaving your active code cell.

Improve clarity and documentation of existing code 

Automatically finish comments and summarize functions based on naming conventions and context.

Built with the Databricks Data Intelligence Platform

The model powering Assistant Autocomplete was tuned and developed on Databricks with Mosaic AI. By leveraging Mosaic AI Training and Managed MLflow, we customized a model to achieve both speed and accuracy, specifically optimized for data science workloads. 

Low latency is crucial for AI code completion as it directly impacts the user experience. Assistant Autocomplete utilizes Databricks Model Serving to serve the model close to users, ensuring a responsive and reliable experience.

Assistant Autocomplete prioritizes data protection

All AI-assistive features adhere strictly to our AI Assistance Trust and Safety guidelines. Specifically, your data is never blended across customers and is never used to train models. For more detailed information, see DatabricksIQ Trust and Safety.

Getting Started with Databricks Assistant Autocomplete

Databricks Assistant Autocomplete is available in the product today. Enable the feature on a per-user basis in developer settings as follows: 

1. Navigate to Settings.
2. Under Developer -> Experimental features, toggle Databricks Assistant Autocomplete.
3. As you type, suggestions automatically appear. Press Tab to accept a suggestion. To manually trigger a suggestion, press Option + Shift + Space (on macOS) or Control + Shift + Space (on Windows).

For more information on getting started, check out the documentation page. Learn other ways to use the Databricks Assistant to increase your developer productivity by checking out our blog on Tips and Tricks on using the Databricks Assistant, or learn about other Assistant features through our launch blog.