Oracle Technology Insights

  CENTRALIZED AI-POWERED ORACLE ALERT LOG MONITORING Using a Local LLM (Ollama + DeepSeek-R1) with Oracle Database Links for Automated Error Analysis & Recommendations A Practical Architecture & Implementation Walkthrough Munish Kumar Karna Senior Database Solution Architect | Oracle DBA (OCP) Oracle RAC / ASM • Data Guard • GoldenGate • OCI • 16+ Years of Experience     Overview Every DBA knows the routine: alert logs across dozens of production databases quietly accumulate ORA- errors, and by the time someone notices, the troubleshooting clock has already started late. I wanted to close that gap — not with another dashboard that just displays errors, but with a system that reads the error, understands it, and hands back a concrete recommendation before I even open a terminal. This post walks through a proof-of-concept I built: a centralized AI monitoring layer that pulls live alert log data from multiple production Oracle databases t...

Building Retrieval-Augmented Generation (RAG) Entirely Inside Oracle Database — with PL/SQL How I grounded a local LLM (Ollama + Qwen2.5) in Oracle 26ai's native Vector Search — no external vector database, no separate application layer. Munish Kumar Karna Senior Database Solution Architect | Oracle DBA | Oracle RAC, ASM, Data Guard, GoldenGate, OCI Why This Matters Retrieval-Augmented Generation (RAG) is usually built with a dedicated vector database, an orchestration framework, and an application server sitting between the data and the LLM. With Oracle Database 26ai, that entire pipeline can live inside the database itself. In this walkthrough, I demonstrate a complete, self-contained RAG pipeline built purely in PL/SQL: importing an ONNX embedding model, running a local LLM through Ollama, chunking and embedding a real PDF manual, and using Oracle's native VECTOR data type and DBMS_VECTOR package to ground the model...