Optimizing Databricks LLM Pipelines with DSPy
If you’ve been following the world of industry-grade LLM technology for the last year, you’ve likely observed a plethora of frameworks and tools...
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...
How a Leading Venture Capital Firm is Building GenAI with Databricks
Successfully building GenAI applications means going beyond just leveraging the latest cutting-edge models. It requires the development of compound AI systems that integrate...
Research Survey: Productivity benefits from Databricks Assistant
In the fast-paced landscape of data science and engineering, integrating Artificial Intelligence (AI) has become integral for enhancing productivity. We’ve seen many tools...
Building DBRX-class Custom LLMs with Mosaic AI Training
We recently introduced DBRX : an open, state-of-the-art, general-purpose LLM. DBRX was trained, fine-tuned, and evaluated using Mosaic AI Training, scaling training to...
Improving Text2SQL Performance with Ease on Databricks
How we reached 79.9% on the Spider dev dataset with Llama3 8B through savvy prompting and fine-tuning on Databricks.
Accelerate GenAI App Development with New Updates to Databricks Model Serving
Last year, we launched foundation model support in Databricks Model Serving to enable enterprises to build secure and custom GenAI apps on a...
Calibrating the Mosaic Evaluation Gauntlet
A good benchmark is one that clearly shows which models are better and which are worse. The Databricks Mosaic Research team is dedicated...
Accurate, Safe and Governed: How to Move GenAI from POC to Production
When it comes to enterprise adoption of generative AI, most organizations are in transition. While 88% of customers we've talked to say they...
How AI in Business is Revolutionized by Data Intelligence
AI is everywhere; on our cell phones, on our computers, and frequently in the headlines. But behind all the headlines, the use of...