Generating Coding Tests for LLMs: A Focus on Spark SQL
Introduction Applying Large Language Models (LLMs) for code generation is becoming increasingly prevalent, as it helps you code faster and smarter. A primary...
Page 1
Enhancing LLM-as-a-Judge with Grading Notes
Evaluating long-form LLM outputs quickly and accurately is critical for rapid AI development. As a result, many developers wish to deploy LLM-as-judge methods...
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.
How we improved DatabricksIQ LLM quality for AI-generated table comments
We recently made significant improvements to the underlying algorithms supporting AI-generated comments in Unity Catalog and we’re excited to share our results. Through...
Adding Intelligence to Databricks Search
We are thrilled to announce major improvements to the search capabilities in your Databricks workspace. These enhancements build on DatabricksIQ, the Data Intelligence...