Build a ChatGPT RAG Data Pipeline
summary
Builds a real‑time RAG pipeline that reads a simulated X/Twitter stream via Kafka message broker, processes and aggregates tweets with RisingWave stream processor, extracts the top 3 hashtags, and constructs prompts that query a PgVector vector store of embeddings for ChatGPT inference. Demo is dockerized and wired to Postgres/PGVector with example SQL materialized views; live demo experiences a broken connection but the GitHub repo and slide deck contain the working Docker compose, sample queries, and deployment instructions.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 1:04Presenters
- 2:07Generative AI and streaming
- 8:03Rising Wave role
- 13:03Rising Wave features
- 15:33Rising Wave use cases
- 16:17Vector search in AI
- 20:11Real-time RAG demo
- 26:16Resources and closing
related talks
50mBuild a ChatGPT RAG Data Pipeline
49mBuild ChatGPT RAG Data Pipeline with RisingWave Stream Processor & Vector Store
51mEvent Driven AI: Supercharging ChatGPT with RAG & LangStream
32mBuilding a ChatGPT Data Pipeline with RisingWave Stream Processor and Cassandra Vector Search
58mDemystifying GenAI: Build a ChatGPT App with Vector Store
45mFrom ChatGPT User to RAG Implementer: A Developer's Journey
48mCreating a Board Game Chatbot with Postgres, AI, and RAG
41mFrom RAGs to riches: Build an AI document interrogation app in 30 mins