AI Archives - ITNotes

Deploy SGLang with Docker on Linux: Faster LLM Inference Using RadixAttention

October 8, 2026

SGLang uses RadixAttention to cache shared prefixes across requests — making it significantly faster than vLLM for chatbots, agents, and RAG pipelines. This guide covers deploying SGLang with Docker on Linux: from GPU toolkit setup to a production-ready Docker Compose configuration.

Building a Custom MCP Server with Python: Standardize Tool and Data Integrations for Claude Desktop and AI Agents

October 3, 2026

Learn how to build a production-ready Python Model Context Protocol (MCP) server. Standardize tool calls, query incident telemetry, and integrate directly with Claude Desktop.

Database

PostgreSQL pgvector Tutorial: Storing Embeddings and Building Fast Semantic Search

October 2, 2026

Eliminate sync lag and extra infrastructure by moving semantic search into PostgreSQL. Learn how to store embeddings with pgvector, configure HNSW indexes for sub-10ms response times, and implement production-ready hybrid search.

HomeLab

Deploy a Local AI Server with Ollama and Open WebUI on Docker: Self-Hosted RAG and Web Search

October 2, 2026

Build a self-hosted AI server using Ollama, Open WebUI, and SearXNG on Docker. Complete guide with GPU passthrough, local RAG document ingestion, and private web search.

Master Prompt Caching: How We Slashed Claude and Gemini API Costs by 90%

September 16, 2026

Slash your LLM expenses and latency. This guide shows you how to use Prompt Caching in Claude and Gemini to save up to 90% on API costs with Python examples.

Mastering Context Engineering: Beyond Simple Prompting for Production AI

September 16, 2026

Prompt engineering is only the beginning. Learn how to use context engineering, structured XML tags, and token pruning to build stable, cost-effective AI applications.

Stop Building Brittle AI: Building Self-Correcting Agentic RAG with LangGraph

September 10, 2026

Standard RAG pipelines often fail when local data is missing or queries are vague. This guide shows you how to build a self-correcting Agentic RAG system using LangGraph and Tavily to reduce hallucinations and improve reliability.

Database

Deploying Milvus on Docker: A Production Guide for Enterprise AI and RAG Applications

August 19, 2026

A hands-on guide to deploying Milvus vector database on Docker, based on six months of production experience running a 50-million-vector RAG pipeline. Covers Standalone setup, configuration tuning for performance, index selection, and monitoring with Attu and Prometheus.

Stop Scrubbing: Building a Video RAG System with Keyframe Extraction and Vector Search

August 14, 2026

Manual video scrubbing is a relic of the past. Learn how to build a Video RAG system using Python, CLIP, and Qdrant to index and search visual content with precision.

AI-Powered Visual Testing: Catching UI Regressions with Playwright and Claude 3.5 Sonnet

August 14, 2026

Learn how to combine Playwright's browser automation with Claude 3.5 Sonnet's vision capabilities to detect UI bugs automatically. This guide covers setup, CI/CD integration, and cost-saving tips.