Official JD technology sharing platform. All the cutting‑edge JD tech, innovative insights, and open‑source solutions you’re looking for, all in one place.
This article details how JD Finance tackled intermittent chart rendering failures in its mobile app by integrating Apache ECharts via ROMA, redesigning the WebView caching strategy, optimizing data flow between Native and WebView, and adding auto‑retry mechanisms to achieve near‑100% success and 200 ms faster startup rendering.
This article explains Retrieval‑Augmented Generation (RAG), an AI framework that combines external knowledge retrieval with large language models, covering its motivations, data preparation, chunking strategies, vectorization, storage, query processing, retrieval, reranking, prompt engineering, and LLM generation, plus practical optimization tips.
This article examines common high‑availability challenges across applications, databases, caches, message queues, containers, and GC, presenting real JD engineering cases, root‑cause analyses, and practical mitigation strategies to help engineers design more resilient systems.
The article recounts how a risk‑control algorithm engineer progressively refined a generic large language model through four stages of prompt engineering—role‑playing, business knowledge injection, deeper analysis, and a double‑hypothesis decision framework—to transform it into a precise e‑commerce fraud detection expert.
This guide shows how to quickly build, configure, and deploy modular AI agents using the OxyGent framework—covering environment setup, minimal code initialization, tool integration, multi‑agent orchestration, and advanced deployment techniques—all illustrated with concise examples and screenshots.
JD’s recent technical salon reveals the rapid evolution of large‑model tools, detailing industry trends, JD’s JoyAI ecosystem—including JoyAgent, OxyGent and JoyCode—real‑world applications across office, code review, logistics and local services, and future policy and multi‑agent visions.
This article examines the evolution of Text-to-SQL, introduces the J‑Schema representation and chain-of-thought prompting, applies iterative DPO training and self-consistency voting, and demonstrates how these techniques raise execution accuracy on the BIRD benchmark from 56.6% to 69.2%.
The article details the open‑source release of Taro on HarmonyOS, explaining its architectural evolution, performance optimizations, multi‑platform development workflow, and real‑world results from JD’s HarmonyOS app, while outlining future roadmap and ecosystem expansion.
This article describes a QCon talk that combines causal inference with large language models to build a retrieval‑augmented generation pricing system for e‑commerce, detailing the three‑step algorithm, LLM‑driven modeling challenges, process‑reward tree search, reinforcement‑learning fine‑tuning, and experimental gains in accuracy and speed.
JD Retail’s “JingDianDian” AI virtual try‑on platform leverages a 12‑billion‑parameter Flux‑Fill diffusion model and multimodal pose estimation to automatically create realistic model images and videos, integrates with the JingMai A/B testing system, and delivers up to an 80% boost in conversion while cutting production costs and time dramatically.
