Using Postgres + OpenAI to power your AI Recommendation...
summary
Builds a working recommendation engine using Rails + ActiveRecord, stores OpenAI embeddings as vectors in Postgres and queries them with approximate nearest neighbor search, and demonstrates the end‑to‑end app and code that returns ranked results. Presents concrete optimization techniques: GIN/GiST vector indexing, batching and caching strategies, and query/throughput tradeoffs for scaling AI data. Clarifies where Postgres is sufficient and when a specialized vector store becomes necessary.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 2:41Why Postgres for AI
- 13:08Setting up OpenAI integration
- 22:18Building recommendation queries
- 31:11Live demo walkthrough
- 40:38Optimizing performance tips
- 44:20Q&A and closing
related talks
27mPutting AI in Production
44mPostgres and OpenAI - a match made in Azure
47mExtendable by Design: Building Generative AI Apps with Postgres and Vector Storage and Azure AI
44mIntegrating AI with Postgres...
37mRound Table Discussion
50mFrom Transactions to Intelligence: Postgres for Open AI & Analyti
34mAnalytics and AI with PostgreSQL - Mission Possible!
19mPOC to PROD: Hard Lessons from 200+ Enterprise GenAI Deployments