Official JD Tech public account delivering best practices and technology innovation.
This article details how JD Finance re‑engineered its complex chart rendering pipeline on the mobile app by integrating Apache ECharts via a custom WebView, introducing a reusable cache, automatic retries, and performance measurements that cut first‑screen rendering time by 200 ms and raised success rates to near 100 %.
This article explains the core concepts, working principles, advantages, drawbacks, and typical use cases of WebSocket, Server‑Sent Events, and WebRTC, and provides a detailed comparison to help developers select the most suitable real‑time communication technology for their web applications.
Over the past year, generative recommendation has made substantial progress by leveraging large language models' powerful sequence modeling and reasoning abilities, introducing a new paradigm that replaces complex handcrafted features, addresses traditional recommendation bottlenecks, and outlines the evolution, core technologies, engineering challenges, and future directions of LLM‑based recommendation systems.
This article details a backend developer's two‑year AI journey, the challenges of rapid model advances, and how applying microservice principles to Retrieval‑Augmented Generation (RAG) creates a scalable, multi‑agent platform for insurance knowledge, memory, and intelligent agents.
This article explains Apache Hudi's architecture, including its timeline mechanism, file layout, indexing strategies, table types (COW and MOR), query options, storage format versioning, backward compatibility, and key configuration settings for managing data lake tables.
This article explains how to integrate the Chromium Embedded Framework (CEF) on both Windows and macOS, covering required libraries, resource paths, main‑process initialization, render‑process creation, message‑loop handling, window adaptation, and version management to ensure a seamless cross‑platform deployment.
This article explains Retrieval‑Augmented Generation (RAG), an AI framework that combines traditional information retrieval with large language models, detailing its core workflow—from knowledge preparation, chunking, and embedding to vector database storage and the question‑answering stage—while highlighting key challenges, tools, and optimization strategies.
This article explains how the ROMA cross‑platform framework implements dark mode, covering configuration options, theme‑mode attributes, color mapping, iOS trait handling, and practical code examples for seamless UI theme switching.
This article explains the Strategy (Policy) Pattern, illustrates its structure, and demonstrates a practical Spring-based implementation where different message types are processed by distinct strategy services, using an enum to map types to beans for flexible, interchangeable algorithms.
This article explains how the k8s‑cluster‑inspector component automates Kubernetes cluster checks, enriches the findings with AI‑generated solutions, and outlines the end‑to‑end workflow and provider design that make the inspection results more reliable and actionable.
