Real-Time Data for Generative Feedback Loop (GFL) Automation
summary
Concrete pipeline claim: a real‑time generative feedback loop that detects Supabase row changes, calls OpenAI to generate or enrich listing descriptions, vectorizes them and writes embeddings into Weaviate so human‑language queries hit fresh results. Demo uses Glassflow + Supabase + Weaviate, deploys and runs a production pipeline in 15 minutes to production, ingests 20 simulated inserts processed in milliseconds, and returns relevant results via Weaviate GraphQL, so the thing demonstrably works end‑to‑end.
AI-written summary · about
chapters (7)
- 0:00Introduction and Session Overview
- 2:21Understanding Generative Feedback Loops (GFL)
- 5:19Real-World Applications of GFL
- 7:58Building a Real-Time GFL Pipeline
- 10:55Technologies for GFL Pipelines
- 18:44Demo: Setting Up and Running the Pipeline
- 27:16Conclusion and Q&A
related talks
44mShaping the Future of Real-time Data Pipeline
18mAccelerate generative AI development with integrated data platforms
41mAdding Generative AI to Real Time Streaming Pipelines
24mScalable GenAI in Production
28mImproving responses in generative AI applications
27mUsing Weaviate for building Generative AI apps
47mReal-Time AI with Open Source
38mQuerying Live Data With LLM App