Data, models & applied AI, distilled into useful references.
I'm Omar — a data scientist and ML engineer with 26+ years across credit, telecom and EDA. This site is where I keep my cheatsheets and field notes on machine learning, LLMs, agents and the tools I actually use.
Four libraries, one mission
Quick references for fast lookup, long-form articles for deeper understanding, video courses to learn step by step, and books to go the whole way.
Cheatsheets
Concise reference guides for the tools and libraries that show up in real data-science and ML work. Skim them, bookmark them, print them.
Browse cheatsheets →Blog & Articles
In-depth articles, capability tours and field notes on emerging AI models and tooling — things I learned from actually running them, not just reading about them.
Read the blog →Courses
Free module-by-module video courses on graph-based RAG, agent memory and microservices for Python developers, with a direct link to every module.
Start learning →Books
Friendly, illustrated guides to microservices for Python developers, graph-based RAG and knowledge agents, and diagrams as code. Find them on Amazon.
Browse the books →Latest from the site
A few of the newest entries from both libraries.
🤖 OpenWiki — the AI agent that writes your docs (and turns Gmail into a second brain)
A hands-on walkthrough of the LangChain team's open-source docs agent: one command documents a repository through a docs-only sandboxed backend, another distills 100 real Gmail messages into a personal wiki you can chat with from the terminal. Guardrails, the SHA-256 snapshot gate, real screenshots, and the full 13-minute video walkthrough.
Article · July 2026🕸️ FalkorDB, explained — the graph database that's secretly linear algebra
An illustrated, jargon-light explainer of FalkorDB: it stores your graph as sparse matrices and turns every query into matrix multiplication (GraphBLAS), ships as a one-Docker-command Redis module you query in openCypher, and has a native vector index — so embeddings and graph structure live in one engine for AI, RAG and agent memory.
Article · July 2026🎨 12 Illustration Styles Worth Generating in Krea 2
A visual field guide to twelve illustrator and artist styles — Axel Scheffler, Ludwig Bemelmans, Alexander Jansson, William Kentridge, Bruce Timm, Robert McGinnis, Alessandro Gottardo and more — reproduced entirely local in Krea 2 Turbo on one 24 GB RTX 4090. Each with the style described, a short artist bio, the reference look, and a same-seed triptych with its prompt recipe.
Article · July 2026🖼️ Krea 2 on a single RTX 4090 — quantizing a 12B image model with GGUF
A 12-billion-parameter diffusion transformer, quantized to a Q6_K GGUF (~10.6 GB) and run entirely local on one 24 GB 4090 under Pop!_OS: the install path (isolated ComfyUI, torch cu130, the krea2 encoder gotcha), a 16-style quality gallery with honest per-image verdicts, and where diffusion text still breaks.
Article · June 2026📄 Unlimited-OCR, hands-on — long-horizon document parsing on a 4090
Baidu's DeepSeek-OCR-based parsing VLM, served with SGLang: near-perfect on clean English with exact table extraction, much harder on 1890s Arabic. Install steps, full-page → rendered-Markdown comparisons, English & Arabic examples, table extraction, and the runaway loop that image_mode=base fixes.
Article · June 2026🕸️ LightRAG — fast graph-RAG with GPT-5 + Qdrant, hands-on
Graph-RAG without GraphRAG's bill: knowledge-graph indexing plus a dual-level retrieval paradigm, run end-to-end on OpenAI gpt-5-mini / gpt-5.5 and a Qdrant vector store — the seven core ideas, the knowledge graph it builds, and the real setup issues and fixes.
Article · June 2026🕸️ LinearRAG — relation-free GraphRAG, hands-on a 4090
GraphRAG without relation extraction: a Tri-Graph built with zero LLM tokens, single-pass multi-hop retrieval via semantic bridging and Personalized PageRank, animated walkthroughs, and an end-to-end 4090 run where gpt-5-mini scored a perfect 12/12.
Article · June 2026🎨 Boogu-Image — the Edit and Turbo models, hands-on a 4090
The Apache-2.0 10B unified image model on a 24 GB 4090: instruction-based photo editing and a 4-step Turbo text-to-image — install, prompt/config galleries, and the honest blur / OOM / group-offload / identity-CFG story.
Article · June 2026🔭 Lens — quantizing the DiT to run 1440 without offload on a 4090
Microsoft's 3.8B text-to-image model with a 4-bit GPT-OSS encoder: the no-offload OOM wall and the FP8 DiT fix that unlocks 1440, with a category gallery and honest quality notes.
Article · May 2026⚡ Doubling Qwopus 3.6 on a single RTX 4090 — Multi-Token Prediction with llama.cpp
~1.98× average speedup (peak 2.21×) on Qwopus 3.6-27B-MTP. Why Ollama refused to load it, and the working llama.cpp install path end-to-end.
Cheatsheet · New📊 bupaR — Business Process Analytics in R
Event logs, process maps, performance metrics, filtering, and the bupaverse ecosystem in one quick reference.
Cheatsheet🤖 OpenAI Agents SDK
Core concepts, agent creation, tools, guardrails, handoffs, and tracing for building AI agent applications.
About me
I'm a seasoned data scientist and ML engineer with 26+ years of experience. I've contributed to Tribal Credit, Reveel, TA Telecom, Mentor Graphics and IBM — across AI-driven underwriting, algorithm development, analytics and software-testing leadership.
I write and build around: