The Mosaic AI Agent Framework and the Mosaic AI Tools Catalog are two services being launched by Databricks to help developers build their own retrieval augmented generation (RAG)-based applications. The company is also launching the Mosaic AI Agent Evaluation, an AI-assisted evaluation tool that combines LLM-based judges to test AI performance in production. Other new tools include the Mosaic AI Model Training service, which allows users to fine-tune models with their organization’s private data, and the Mosaic AI Gateway, a unified interface to query, manage, and deploy any open source or proprietary model.
Key takeaways:
- Databricks is launching five new Mosaic AI tools at its conference: Mosaic AI Agent Framework, Mosaic AI Agent Evaluation, Mosaic AI Tools Catalog, Mosaic AI Model Training, and Mosaic AI Gateway.
- The Mosaic AI Agent Framework and the Mosaic AI Tools Catalog are two services that Databricks is launching to help developers build their own RAG-based applications.
- Databricks is extending its Unity Catalog system to let enterprises govern which AI tools and functions these large language models (LLMs) can call upon when generating answers.
- Databricks is also launching the Mosaic AI Agent Evaluation, an AI-assisted evaluation tool that combines LLM-based judges to test how well the AI does in production, and allows enterprises to quickly get feedback from users.