Discover the flow of building a natural language query (NLQ) translation service for SaaS distribution of Druid and handling the unique considerations for Druid and the SaaS platform. This system was built with Amazon Bedrock and Claude for LLM (large language model) assistance, aiming to make data querying more accessible and intuitive, even for non-experts.
Speaker:
Tom Fenwick, Software Engineer, Imply
[Timestamp] Table of Contents:
[0:00] Building NLQ for Apache Druid: Natural language querying for Druid using Amazon Bedrock and Claude
[4:00] Initial Development, Evaluation and Testing
[8:00] Enhancing NLQ with Schema Knowledge, Guardrails & Druid Challenges
[12:19] Issues Faced: And how we handled them
[14:00] Handling Ambiguities and Impossible Queries
[17:00] Future Enhancements & Conclusion
Keynote: Powering Event-Driven Data with Apache Druid
The distinction between OLTP and OLAP is becoming less relevant as data architectures shift toward entities and events. In this session, we’ll delve into how Apache Druid’s event-first approach synthesizes...
Watch nowClosing Keynote: Charting the Future of Druid
What lies ahead for Apache Druid? Join us as we explore the evolving landscape of Druid’s query and storage engines, and how they are positioned to address the biggest challenges in event data for the future. Speaker: Gian...
Watch nowSalesforce: Tracing Service Dependencies at Scale with Druid and Flink
At Salesforce, we manage approximately 300 million distributed spans to infer service dependencies. We have successfully utilized a combination of Druid and Flink to handle this scale with high availability....
Watch now