Summary
Full Transcript
Learn more: https://bit.ly/45BbJ0D When building generative AI applications, it's common to start in a Jupyter Notebook or script, but notebooks aren’t built for automation, monitoring, or scale. To run GenAI workflows reliably in production, you need orchestration. In Orchestrating Workflows for GenAI Applications, a new short course taught by Kenten Danas and Tamara Fingerlin from Astronomer, you’ll learn how to transform a RAG prototype into a robust, automated pipeline using Apache Airflow 3. You’ll build two production-ready workflows: one to ingest and embed book descriptions into a vector database, and another to query that database to recommend books, each composed of discrete, trackable tasks managed by Airflow dags. What you’ll learn includes: - Scheduling pipelines using both time-based and event-driven triggers - Parallelizing tasks with dynamic task mapping - Adding retries, alerts, and backfills to ensure reliability - Scaling orchestration using real-world techniques from apps like Astronomer’s Ask Astro This course is ideal for AI builders who want to move from prototype to production. No prior Airflow experience required. Enroll now: https://bit.ly/45BbJ0D
Continue this lesson in the app
Install CourseHive on Android or iOS to keep learning while you move.
