Build ChatGPT RAG Data Pipeline with RisingWave Stream Processor & Vector Store
summary
Builds a real-time RAG pipeline that wires Kafka -> RisingWave stream processor -> Postgres with PGVector, using OpenAI embeddings and PgVector embeddings stored in a materialized view for fast similarity search. RisingWave performs streaming analysis to pick top 3 hashtags, constructs prompts, and queries a RAG bot; the demo uses Python scripts and a virtualenv, needs Postgres + PGVector installed, and the Twitter feed example is unavailable during the session so some live steps don’t run end-to-end.
AI-written summary · about
chapters (10)
- 0:00Introduction and agenda
- 2:10About RisingWave and GenAI
- 10:40Event-driven AI and streaming data
- 15:22What is RAG and its challenges
- 23:10RisingWave for real-time RAG
- 28:01Stream processing fundamentals
- 30:30Vector search and embeddings
- 36:24Building a RAG pipeline
- 40:11Demo walkthrough
- 46:54Resources and Q&A
related talks
27mBuild a ChatGPT RAG Data Pipeline
50mBuild a ChatGPT RAG Data Pipeline
32mBuilding a ChatGPT Data Pipeline with RisingWave Stream Processor and Cassandra Vector Search
51mEvent Driven AI: Supercharging ChatGPT with RAG & LangStream
58mDemystifying GenAI: Build a ChatGPT App with Vector Store
53mBuild RAG from Scratch
01h 35mTutorial: Build AI-Supercharged RAG Apps with a Vector Database
48mCreating a Board Game Chatbot with Postgres, AI, and RAG