Build GenAI Apps with Oracle Database 23ai
summary
15-minute demo builds a working AI loan recommender using Oracle Database 23ai, Python, JSON and OCI Generative AI, with ONNX embedding models imported and embeddings stored and searched inside the same database. It performs RAG on live loan and customer JSON, vectorizes records, uses cosine (or other) distance to pick the top three loan recommendations, and returns explanations via a chat model. Security stays on-premise to avoid external vector stores and the app runs end-to-end.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 1:06Where do we begin
- 1:55Oracle Database 23ai
- 4:40Fetch Data
- 5:34Prompt Engineering
- 6:09Evaluations
- 7:20Processing
- 8:20Chatbot
- 10:10Cleaning Up Data
- 11:10Oracle handles all types of data
- 11:26Oracle way to keep it current
- 12:15What is an embedding
- 13:11Converting data into embeddings
- 13:32Embedding recommendations
- 14:57Embedding questions
related talks
47mHow to query data using natural language - intro to AI features in Oracle 23ai
27mUse AI Vector Search to Build GenAI Apps with Enterprise Data
47mBlazingly Fast GenAI App Development Java and Spring AI
18m3 Oracle AI Use Cases
23mBuild Natural Language-Powered Apps with Select AI
09mBuild and Deploy AI Flows with an Agent Factory
23mAI for Data Made Simple
12mKey AI Innovations in Oracle Database 23ai