Su San, former staff at several leading tech companies, is a top creator on Juejin and a premium creator on CSDN, and runs the free coding practice site www.susan.net.cn.
This tutorial explains Retrieval‑Augmented Generation (RAG) from fundamentals to a full pipeline, covering text chunking strategies, VoyageAI embeddings, vector‑store implementation, BM25 lexical search, and a multi‑index retriever that fuses semantic and lexical results with Reciprocal Rank Fusion.
This article lists ten common IntelliJ IDEA pitfalls—such as high memory usage, indexing delays, Lombok errors, broken breakpoints, console encoding issues, unwanted Git commits, slow Maven downloads, classpath mismatches, shortcut conflicts, and automatic code reformatting—and provides step‑by‑step solutions to make the IDE run smoothly for Java and Spring projects.
This article provides a detailed, step‑by‑step analysis of Claude's Agent Skills system, explaining how skills are discovered, structured in SKILL.md files, progressively disclosed, and executed through prompt expansion and context modification, complete with code snippets, design patterns, and workflow examples.
The article analyzes how Codex is evolving from a code‑writing assistant into a broader computer work system by leveraging durable threads, tool integration, voice‑based control, automations, and verifiable goals, shifting the focus from isolated code tasks to end‑to‑end workflow completion.
The article compares Alibaba’s Druid and Spring Boot’s default HikariCP connection pools, explaining how connection pooling works, presenting benchmark results that show HikariCP’s lower latency and higher TPS, detailing HikariCP’s lock‑free ConcurrentBag and bytecode optimizations, and highlighting Druid’s rich monitoring, SQL firewall and leak detection features to help developers choose the right pool for different scenarios.
The article explains that LLMs process Markdown more effectively than raw PDFs, introduces Microsoft’s open‑source MarkItDown utility that converts a wide range of file types—including PDFs, Word, Excel, HTML, images with OCR, and YouTube videos—into clean Markdown, and provides installation, usage examples, recent feature updates, and a brief critique of its scope.
This article walks through the interview question of designing a message queue that handles billions of messages daily and peaks at millions of QPS, covering traffic calculations, core roles, storage and throughput techniques, scalability, high availability, observability, framework comparisons, a real‑world case study, and key follow‑up interview topics.
The article reviews html-ppt-skill, an AI‑driven tool that generates fully styled HTML presentations instead of PPTX files, detailing its theme, layout, and animation assets, presenter‑mode implementation, cross‑platform skill integration, practical advantages, limitations, and how it exemplifies the emerging AI skill ecosystem.
The article breaks down the reliability challenges of LLM Function Calling, categorizes five failure modes, and presents concrete engineering safeguards such as precise schema design, tool description, constraint enforcement, few‑shot calibration, structured output, validation‑feedback loops, monitoring, and risk‑aware trade‑offs.
The article explains why major tech companies discourage using NULL in MySQL, covering its meaning as an unknown state, three-valued logic pitfalls such as NOT IN subqueries, index inefficiencies, aggregate function quirks, storage overhead, Java handling issues, and offers practical alternatives like NOT NULL constraints with sensible defaults.
