Articles by Alkis Polyzotis

Page 1

Databricks announces significant improvements to the built-in LLM judges in Agent Evaluation

September 5, 2024 by Max Marion, Arnav Singhvi, Samraj Moorjani, Avesh Singh, Michael Carbin and Alkis Polyzotis in Generative AI

An improved answer-correctness judge in Agent Evaluation Agent Evaluation enables Databricks customers to define, measure, and understand how to improve the quality of...

Announcing Mosaic AI Agent Framework and Agent Evaluation

July 2, 2024 by Eric Peter, Akhil Gupta, Mani Parkhe, Alkis Polyzotis, Chenen Liang, Maheswaran Venkatachalam, Michael Carbin and Niall Turbitt in Generative AI

Databricks announced the public preview of Mosaic AI Agent Framework and Agent Evaluation alongside our Generative AI Cookbook at the Data + AI...

Lakehouse Monitoring: A Unified Solution for Quality of Data and AI

December 12, 2023 by Jacqueline Li, Alkis Polyzotis and Kasey Uhlenhuth in Platform Blog

Introduction Databricks Lakehouse Monitoring allows you to monitor all your data pipelines – from data to features to ML models – without additional...

Announcing MLflow 2.8 LLM-as-a-judge metrics and Best Practices for LLM Evaluation of RAG Applications, Part 2

October 31, 2023 by Quinn Leng, Kasey Uhlenhuth, Alkis Polyzotis, Abe Omorogbe and Sunish Sheth in Engineering Blog

Today we're excited to announce MLflow 2.8 supports our LLM-as-a-judge metrics which can help save time and costs while providing an approximation of...

Announcing Inference Tables: Simplified Monitoring and Diagnostics for AI models

October 5, 2023 by Ahmed Bilal, Steven Chen, Kasey Uhlenhuth, Joshua Hartman, Alkis Polyzotis and Viswesh Periyasamy in Platform Blog

Have you ever deployed an AI model, only to discover it's delivering unexpected results in a real-world setting? Monitoring models is as crucial...

Best Practices for LLM Evaluation of RAG Applications

September 12, 2023 by Quinn Leng, Kasey Uhlenhuth and Alkis Polyzotis in Machine Learning

Chatbots are the most widely adopted use case for leveraging the powerful chat and reasoning capabilities of large language models (LLM). The retrieval...