Integrating AI with Postgres...
summary
Postgres becomes a viable vector store once PGVector is available and EDB ships aidb, which automates document capture, preprocessing, embedding generation, vector indexing and retrieval so data and vectors live together. aidb tech preview supports 40 embedding models, including a multimodal CLIP, and converts a 130-line ingestion workflow into a two-line create retriever / refresh retriever flow. Demo on a Kaggle fashion set returns top‑5 semantic image/text matches offline after downloading the model, proving the pipeline works end to end.
AI-written summary · about
chapters (13)
- 0:00Introduction and speaker intro
- 3:09What is a language model
- 6:22Postgres for AI engineers
- 9:15PG Vector extension explained
- 11:01Introducing AI DB
- 16:06Use case recommendation engine
- 18:55How AI DB works internally
- 21:10Live demo of AI DB
- 23:46Simplifying with AI DB
- 27:38Text search with AI DB
- 28:21Future of AI DB
- 29:04Summary and wrap up
- 30:37Q&A session
related talks
27mPutting AI in Production
34mAnalytics and AI with PostgreSQL - Mission Possible!
12mThe mechanics of integrating AI and vector search into Azure Database for PostgreSQL
36mUnleashing the Power of Vector Databases for AI-Driven Applications
50mFrom Transactions to Intelligence: Postgres for Open AI & Analyti
34mAnalytics and AI with PostgreSQL - Mission Possible!
37mRound Table Discussion
45mUsing Postgres + OpenAI to power your AI Recommendation...