Databricks Previews Toolkit for Internal Data, AI App Creation
October 10, 2024
Databricks Apps is a new platform designed to make building internal data and AI applications something that can be done in a few clicks. Available now in public preview on AWS and Azure, the template-based system lets users weave data and frameworks of choice into full-featured apps that can run in the Databricks environment. The company says the system can code and deploy a secure data app with AI integration in five minutes. “Ideal use cases include data visualization, AI applications, self-service analytics and data quality monitoring,” according to the San Francisco-based company.
“With this offering, all a user has to do is select a Python framework from a set of options (Streamlit/Dash/Gradio/Flask), a template of the type of app they want to develop (chatbot or data visualization app) and configure a few basic settings, including those for mapping resources (like data warehouses or LLMs) and defining permissions,” writes VentureBeat.
Deployment is simple, with automatic provisioning of serverless compute, and a company blog post stresses compliance and security through built-in governance via the Unity Catalog and user authentication with OIDC/OAuth 2.0 and SSO.
The Databricks Apps debut “comes at a time when enterprises, despite being bullish on the potential of data-driven applications, continue to struggle with the operational hassle of the entire development cycle, right from provisioning the right infrastructure to ensuring security and access control of the developed app,” VentureBeat reports.
Databricks Apps takes a lot of the heavy-lifting — like mastering container hosting and managing infrastructure — making development and access for in-house applications more accessible for non-technical users.
Using easier to maintain code libraries instead of the complex SQL framework typically used for data queries “opens up new possibilities for making complex data insights accessible to a wider audience within organizations,” Databricks explains. “For instance, a marketing team can leverage Databricks Apps to create customized dashboards that visualize campaign performance metrics,” allowing team members to easily interpret and act on the data.
Databricks has long provided customers the ability to build custom dashboards. And it “already provides Mosaic AI, an environment that enables customers to integrate systems such as large language models with their enterprise’s proprietary data,” writes TechTarget, noting that what was missing “were the capabilities to develop the interactive applications such as generative AI chatbots that are powered by the combination of AI systems mixed with proprietary data.”
No Comments Yet
You can be the first to comment!
Leave a comment
You must be logged in to post a comment.