Completed
00:59:29 - Challenges of text‑to‑SQL translation and benchmark evolution
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Open Lakehouse and AI - Building Foundations with ClickHouse, Apache Iceberg, LLMs, and AWS S3 Tables
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00:00 - Introduction
- 2 0:06:40 - Building a foundation for AI with ClickHouse and Apache Iceberg - Altinity
- 3 00:15:08 - Challenges of shared‑nothing architecture and AI workloads
- 4 00:17:26 - Introducing Apache Iceberg and ClickHouse integration
- 5 00:24:30 - Parquet & MergeTree performance benchmarks and Iceberg catalog
- 6 00:27:57 - Hybrid tables and tiered storage strategies
- 7 00:31:10 - Demo - Query acceleration using swarm compute and caching
- 8 00:37:00 - Discussion and Q&A on open formats
- 9 00:53:49 - Teaching Databases to Speak Human with LLMs and MCP - Confluent
- 10 00:54:42 - Demo - Building a real‑time pipeline and LLM
- 11 00:59:29 - Challenges of text‑to‑SQL translation and benchmark evolution
- 12 01:06:30 - Connecting LLMs to data via MCP tools
- 13 01:09:52 - Streaming data with Apache Kafka and Trino
- 14 01:14:42 - Evaluation, security and governance considerations
- 15 01:18:30 - Adoption outlook and conclusion
- 16 01:21:00 - Conclusion and Q&A
- 17 01:27:12 - Managed Apache Iceberg With Amazon S3 Tables - AWS
- 18 01:27:50 - Amazon S3 use cases
- 19 01:29:29 - Iceberg advantages and capabilities
- 20 01:33:36 - Copy‑on‑write vs merge‑on‑read update modes
- 21 01:36:47 - Overview of Amazon S3 Tables service and momentum
- 22 01:41:55 - Maintenance and compaction features
- 23 01:51:11 - Performance tuning, streaming analytics, Agents, & MCP
- 24 01:54:25 - Iceberg REST catalog endpoints Glue vs S3 IRC and integration choices
- 25 01:56:38 - S3-to-S3 Tables migration and conclusion
