IT Expert Blog — since 2017
Practical knowledge on AI and technology for every IT Pro
Articles on local AI models, Python programming, developer tools and IT project management. No fluff — just what works in practice.
110+
articles
6
categories
2017
since
Latest Articles
Latest
We benchmark Multi-Token Prediction in llama-server (llama.cpp, Vulkan) on AMD PRO W7900. Real results: 49.7 → 91.8 tok/s, up to 2× on code generation — and why LM Studio MTP fails on gfx1100.
Read article
Private AI Assistant for Productivity: How Freelancers and Managers Can Get Work Done in the Background
A practical English article on private AI assistants, background work, personal context, privacy, and real productivity gains for freelancers and managers.
Describing PDF Charts with Vision Language Models
Use Vision Language Models (VLMs) to convert PDF charts into searchable text descriptions. Build complete pipelines for chart extraction, processing, and RAG…
Running Local LLMs with OpenAI-Compatible APIs
Run powerful LLMs locally using OpenAI-compatible APIs. Learn to set up LM Studio, Ollama, and vLLM servers for private, cost-free AI inference.
Hybrid Search: Combining Vector and Keyword Retrieval
Master hybrid search combining vector similarity and keyword matching. Learn BM25, Reciprocal Rank Fusion, and score merging strategies for optimal RAG retrieva
LanceDB: Lightweight Vector Database for AI Applications
Complete guide to LanceDB, a lightweight serverless vector database for AI applications. Learn indexing, querying, filtering, and best practices for RAG systems
Local Text Embeddings with Sentence Transformers — Complete Guide
Learn how to generate high-quality text embeddings locally using Sentence Transformers. Complete guide to embedding models, batch processing, and optimization f
Document Chunking Strategies for RAG Systems — Complete Guide
Master document chunking strategies for RAG systems. Learn about semantic chunking, overlapping windows, chunk size optimization, and metadata enrichment for be
Q1 2026 IT Quarterly Review | Infrastructure, Open Source, and AI Operations
Q1 2026 IT Quarterly Review: AI infrastructure becomes a macroeconomic force, the EU AI Act moves from theory to operational deadlines, and…
PDF Data Extraction with PyMuPDF (fitz) — Complete Python Tutorial
Working with PDF documents programmatically is a common challenge in data processing, document management, and machine learning pipelines. Whether you’re building a…
Q4 2025 IT Review: AI Infrastructure Goes Operational
Q4 2025 IT review tracks Python 3.14, AWS re:Invent, Apple M5, and NVIDIA Blackwell as AI infrastructure shifts into production.
Q3 2025 IT Review: Agentic Software and Cloud Toolchains
Read the Q3 2025 IT review on agentic software, cloud toolchains, and the open-source releases that turn AI systems into production infrastructure.
GPT4All vs Jan – the battle for the best desktop LLM
The landscape of artificial intelligence has undergone a revolutionary transformation with the emergence of desktop Large Language Models (LLMs). As AI technology…
Ollama like Docker for AI
Remember when Docker revolutionized how we deploy applications? Well, Ollama is doing the same thing for AI models, and it’s changing the…
Transform Photos into Embroidery Art Interactive Tool
Digital embroidery has revolutionized the way crafters and artists approach traditional needlework, creating exciting opportunities to blend photography with textile art. Whether…
