First‑line development experience at multiple leading tech firms; now a software architect at a Shanghai state‑owned enterprise and founder of Programming Yanxuan. Nearly 300k followers online; expertise in distributed system design, AIGC application development, and quantitative finance investing.
This article presents a contextual retrieval technique that combines contextual embeddings and contextual BM25 to reduce RAG miss rates by up to 67%, explains the underlying methods, implementation steps, cost considerations, experimental results, and practical deployment guidance.
This guide explains how to install the JetBrains AI Assistant plugin, outlines its code‑generation and refactoring features, and provides a practical workaround for mainland China users by adjusting account region, configuring system and IDE proxies, and starting AI‑driven conversations.
The article outlines the twelve preview features introduced in JDK 23, from primitive pattern matching to structured concurrency, and argues that mastering timeless programming principles from Effective Java can help developers adapt to such language evolutions.
This article explains how to extend large language models with domain‑specific knowledge using Retrieval‑Augmented Generation (RAG) in LangChain4j, covering the concepts of RAG, its indexing and retrieval stages, simple RAG setup, detailed API usage, and advanced customization options such as query transformers and content injectors.
This article explains the different low‑level LLM API types in LangChain4j, including LanguageModel, ChatLanguageModel, and other model interfaces, and shows how to create and combine ChatMessage objects for multi‑turn conversations.
This guide explains how to use LangChain4j Spring Boot starters to configure OpenAI models, create declarative AI services with @AiService, and run practical examples such as a customer‑support agent and a simple HelloWorld program, covering required dependencies, properties, and code snippets.
LangChain4j streamlines the integration of large language models into Java applications by offering a standardized API, extensive support for over a dozen LLM providers and vector stores, a rich toolbox for RAG, chat memory, and tool calling, plus two abstraction layers that cater to both low‑level control and high‑level convenience.
The IntelliJ IDEA 2024.3 EAP preview introduces an experimental embedded AI assistant that transforms natural‑language prompts into code changes, improves Java constant‑condition analysis to better handle aliasing, adds spell‑check during indexing, displays branch names in the Welcome screen, and offers a new workspace feature for managing multiple projects.
This article explains the fundamental differences between UDP and TCP, details the TCP header fields, walks through the three‑way handshake and its necessity, describes the four‑way termination process, and illustrates the complete TCP state machine with diagrams and practical examples.
This article summarizes MySQL 9.0’s new VECTOR column type, inline and implicit foreign‑key constraints, JSON EXPLAIN ANALYZE storage, prepared event statements, performance‑schema variable tables, enhanced EXPLAIN output, LIMIT 1 subquery support, as well as deprecated and removed features with practical examples.
