SERIES / S-03

Building a Knowledge Management App with Oracle AI Database 26ai
5,178 docs, one vector column.

Building a multimodal knowledge base on Oracle AI Database 26ai — CLIP-in-database, JSON Duality, Vector Search, and a vision-aware RAG pipeline that actually sees images instead of describing their captions.

4
POSTS IN SERIES
NOV 2025
STARTED
ACTIVE
PART 01

CLIP Inside Oracle AI Database 26ai: Fast, Multimodal RAG

How we got 10x faster by loading CLIP models directly into Oracle AI Database 26ai. Spoiler: In-database AI is production-ready.

11 NOV 2024 11 MIN
PART 02

Three LLMs, One App: Balancing Speed, Privacy, and Power

Testing LLMs in an Oracle Database 23ai app: cloud (OCI), laptop (M2 Mac), and GPU server (RTX 5090). Spoiler: My laptop needs a bigger GPU!

28 OCT 2025 6 MIN
PART 03

When the SDK Says No: Vision-Aware RAG via a 300-Line Python Bridge

After CLIP made multimodal search instant, I hit a wall: the LLM could find images but couldn't see them. Here's how an Oracle engineer's tip and 300 lines of Python broke through.

22 NOV 2025 15 MIN
PART 04

Unifying 12 Years of Knowledge: From OneNote to Local Markdown to Oracle AI Database

How I migrated 5,178 OneNote documents spanning 12 years and built auto-sync for local markdown notes—turning scattered notes into a unified, AI-searchable knowledge base powered by Oracle AI Database 26ai.

27 JAN 2026 11 MIN