New York Metro Open Data User Group
Agenda
5:00 - 5:30: Pizza / Beer
5:30- 5:45: IBM Open Data Update
Gil Isaacs, IBM
Update on the latest in Open Data frameworks where IBM is continuing to participate and grow.
5:45 - 6:05: Fix Your Retrieval, Fix Your RAG
Ramya Ravi, NetApp
Most RAG systems have a retrieval problem. The language model gets the blame, but the real culprit is upstream in the search layer deciding what context the model ever sees in the first place. Fix the retrieval, and the answers fix themselves.
This talk is for developers and ML engineers who have shipped a RAG system with OpenSearch and are wondering why the answers aren't as good as the demos suggested. No retrieval evaluation experience needed.
Through live demos on a real OpenSearch index, the session will show you how to see exactly what your retrieval layer is returning, identify the failure modes that silently kill answer quality, and apply targeted fixes without rearchitecting your stack.
6:05 - 7:00: Lightning Talks
Devin Dawson, Water Pistol
Building a Data-Sovereign AI Factory Observability Stack
As generative AI moves into production, teams shouldn't have to choose between observability and data sovereignty. This talk demonstrates a fully self-hosted, local-first AI observability stack for tracking multi-provider inference, tracing agentic workflows with Langfuse, capturing exceptions with GlitchTip, and querying runtime logs from the IDE using MCP, all without sending sensitive data, prompts, or secrets to third-party services.
Prabakaran Chandran, Columbia University
Semantic Layer for Agentic Data Engineering and Analytics
(description tba)