LLM Archives - ITNotes

Build a Local Git Commit Assistant with LLM and Git Hooks

July 18, 2026

Learn how to build a local Git Commit Assistant using Ollama and Git Hooks. Automatically generate professional commit messages and perform code quality checks entirely offline.

Stop Overpaying for GPT-4o: Smart Query Routing with RouteLLM

July 18, 2026

Is GPT-4o draining your budget? Learn how to use RouteLLM to automatically route simple queries to cheaper models, cutting your API costs by up to 50% without sacrificing response quality.

Running Mixtral and Qwen-MoE Locally: High-Performance AI on Consumer Gear

July 17, 2026

Run GPT-4 class models on your own desk. This guide shows you how to use Ollama to deploy Mixtral and Qwen-MoE models locally, with specific tips for VRAM optimization.

Building AI Applications with Microsoft Semantic Kernel and Python: Plugins, Memory, and Planning for Enterprise AI Agents

July 16, 2026

If LangChain version bumps have burned you before, Microsoft Semantic Kernel is worth a serious look. This guide builds a working Python AI agent from scratch — native plugins, semantic plugins, vector memory, and auto-invocation planning — with real code you can run today.

AI-Driven SQL Optimization: Using LLMs to Decode Execution Plans

July 14, 2026

Learn how to automate SQL tuning by feeding PostgreSQL Execution Plans into LLMs. This guide shows you how to reduce query costs by 85% and prevent production bottlenecks.

Building a Multi-Agent AI System with Microsoft AutoGen v0.4: Orchestrate Specialized Agents for Data Analysis and Code Generation

June 28, 2026

Learn how to build a multi-agent AI system with Microsoft AutoGen v0.4 by creating a Planner, Data Analyst, and Code Reviewer agent that collaborate to automate data analysis workflows. This step-by-step guide covers installation, agent configuration, team setup, and monitoring — everything a junior developer needs to get started.

LLM Merging with Mergekit: Build Custom Models Without the GPU Tax

June 24, 2026

Ditch the expensive GPU rentals. Learn how to use Mergekit on Linux to fuse LLMs using SLERP, TIES, and Passthrough techniques for custom AI performance.

Vercel AI SDK: Build AI Streaming Chatbots in Next.js with Multi-Provider LLM Support

June 18, 2026

Learn how to use Vercel AI SDK to build streaming AI chatbots in Next.js that hold up under real load, with support for OpenAI, Anthropic, and Google in a single unified API. Includes a full implementation guide from route handler to React UI, plus a production deployment checklist.

Running AI Models on AMD GPUs with ROCm: A Production-Ready Guide

June 14, 2026

Ditch the NVIDIA tax. This guide shows you how to set up AMD ROCm 6.1 for high-performance AI inference, featuring real-world benchmarks and setup tips for the Radeon 7900 series.

Automating Prompt Optimization with DSPy: Declarative LLM Programming That Replaces Manual Prompt Engineering

June 3, 2026

DSPy lets you define LLM pipelines declaratively — specifying inputs and outputs instead of writing prompts by hand — then automatically optimizes them using labeled examples. This guide covers the trade-offs versus manual prompt engineering and walks through a full working implementation with code examples.