Bring AI to Your Data
summary
Oracle Database 23ai embeds AI Vector Search, Select AI, and RAG so vectors and relational rows stay transactionally consistent and queryable in place. The demo converts images to high‑dimensional vectors, stores them in a listings table, uses vector indexes and a vector distance function in ORDER BY to return the top 10 matches with six lines of SQL, and combines business filters. A Streamlit front end on GCP calls Vertex AI for RAG; the pipeline updates answers by changing source rows instead of fine‑tuning.
AI-written summary · about
chapters (6)
- 0:00Introduction to AI in data
- 1:31AI vector search basics
- 3:25Vector search in practice
- 6:46Retrieval Augmented Generation
- 10:17Natural language querying
- 13:23Conclusion and resources
related talks
27mUse AI Vector Search to Build GenAI Apps with Enterprise Data
19mAccelerate AppDev with Database 23ai
23mAI for Data Made Simple
36mUnleashing the Power of Vector Databases for AI-Driven Applications
01h 21mKeynote on the "AI for Data" Revolution
06mWhat makes vector databases essential for RAG and AI apps?
13mRAG Without the Hassle: Building AI-Powered Applications
47mRAG at scale: production-ready GenAI apps with Azure AI Search