Official JD Tech public account delivering best practices and technology innovation.
This guide introduces the open‑source OxyGent multi‑agent framework, walks through a quick 20‑line installation, demonstrates environment configuration, tool integration, visualization, and advanced features such as RAG, Reflexion, and distributed deployment for AI applications.
JD’s internal technical salon reveals the rapid evolution of large‑model AI tools, outlining design principles, current capabilities like JoyAgent, OxyGent and JoyCode, real‑world applications across office, code review, logistics, and policy outlook, while highlighting future multi‑agent and embodied intelligence trends.
This article explains what large AI models are, how they enhance capabilities across domains, and details their practical use in software testing—covering code review, automated test case generation, security and performance checks—while envisioning future impacts on manual testing efficiency.
This article explores how software teams can enhance architecture efficiency by focusing on three core dimensions—stability, performance, and code quality—using practical examples, orthogonal decomposition, and disciplined design to build systems that are reliable, fast, and maintainable.
This paper presents a comprehensive approach to improve Text‑to‑SQL performance by introducing J‑Schema for structured database representation, leveraging chain‑of‑thought prompting, applying iterative DPO training, and employing self‑consistency voting, achieving execution accuracy gains from 56.6% to 69.2% on the BIRD benchmark.
The article investigates frequent timeout alerts on the getUiToken API, tracing the issue to excessive PhantomReference objects causing long GC pauses, explains how MySQL’s AbandonedConnectionCleanupThread and default Druid pool settings generate these references, and presents configuration tweaks, JVM flags, and cleanup tasks that reduced GC pause times from 1.25 s to 0.1 s.
This guide walks you through deploying JD Cloud’s open‑source JoyAgent AI agent using the JoyAgent‑Genie image, covering host creation, firewall configuration, model and search engine setup, and service startup, enabling you to access the Genie interface via a public IP.
The article details JD.com’s AI‑driven supply‑chain innovations, including a billion‑scale pure time‑series model, advanced demand forecasting, intelligent inventory selection, and end‑to‑end allocation algorithms that dramatically improve efficiency, cost, and global supply‑chain transformation.
This article details the open‑source Taro on HarmonyOS framework, covering its evolution, technical architecture, performance optimizations, and cross‑platform development benefits that enable developers to write once and deploy across HarmonyOS, web, and mini‑program ecosystems.
This guide walks you through quickly trying the open‑source JoyAgent‑Genie online, then cloning the repository, running the one‑click start script, and reconfiguring the .env and application.yml files to replace the default GPT‑4.1 model with DeepSeek, all with clear step‑by‑step instructions and screenshots.
