AI Infrastructure

📚 Series Building a Knowledge Management App with Oracle AI Database 26ai Part 4 of 4 View all posts in this series → ⚡ TL;DR Unified 12 years of scattered notes - 5,178 OneNote pages plus daily markdown journals - into a single AI-searchable knowledge base powered by Oracle AI Database 26ai. The result: a unified knowledge base where I can ask “What did I write about AI in 2021?” and get instant, accurate answers—regardless of where the note originated. After building multimodal search with CLIP and vision-aware RAG, I had a powerful system. But most of my knowledge was trapped in two silos: ...

📚 Series Building a Knowledge Management App with Oracle AI Database 26ai Part 3 of 4 View all posts in this series → This is Part 3 — turning a text-only knowledge base into a fully vision-aware RAG system After moving CLIP embeddings into Oracle AI Database 26ai, I had something great: true multimodal search. Text queries found images. Images found related text. No OCR, no captions—just CLIP doing its magic in the database. ...

📚 Series Building a Knowledge Management App with Oracle AI Database 26ai Part 1 of 4 View all posts in this series → I spent a weekend fine-tuning a model for my knowledge management app, designed to handle notes, PDFs, and presentations with Oracle Database 23ai’s vector search (see my management AI post). It aced testing on my RTX 5090 server, but on my M2 MacBook Pro? Barely usable. A query like “Summarize last week’s customer meetings and identify risks” took over a minute, leaving me staring at a spinning wheel while my coffee got cold. ...

📚 Series Building a Knowledge Management App with Oracle AI Database 26ai Part 2 of 4 View all posts in this series → After the 3-way LLM toggle went live, I turned my attention to embeddings - the invisible glue that powers search and RAG. Oracle OCI GenAI’s Cohere endpoint had been rock-solid in my testing: fast, reliable, and gave me 80 K token context. But every chunk still meant a network round-trip, and images were stuck behind OCR, so text-only embeddings meant photos, diagrams, and whiteboards were blind spots in my knowledge base. ...