Tagged articles
Search Architecture
29 articles · Page 1 of 1
This article explains why running Elasticsearch in production is far more complex than a simple API tutorial, covering Lucene fundamentals, mapping design, shard planning, write‑path architecture, query optimization, hot‑warm‑cold tiering, ILM policies, capacity planning, monitoring, incident handling, and a step‑by‑step evolution roadmap for building a reliable, scalable search system.
ElasticsearchIndex ModelingLucene
0 likes · 54 min read

The article reviews cutting‑edge AI techniques for high‑concurrency, multimodal recommendation and search, detailing Alibaba Cloud's Agentic RAG evolution, Huawei Noah's LLM‑enhanced recommendation pipeline, and Baidu's generative ranking model GRAB, each with architecture diagrams, performance metrics, and real‑world deployment insights.
AI agentsAgentic RAGGenerative Ranking
0 likes · 6 min read

Facing the shift from keyword indexing to generative AI, Baidu Maps overhauled its LBS architecture by introducing a native multi‑agent system, context‑engineering (ACE) framework, and reinforcement‑learning alignment, enabling dynamic routing, knowledge evolution, and a 36% boost in planning compliance while maintaining zero‑tolerance for factual errors.
AI agentsLLMReinforcement Learning
0 likes · 10 min read

This case study details how a major internet visual platform consolidated its log, keyword, and vector search workloads onto Alibaba Cloud Elasticsearch, eliminating three separate pipelines, reducing write‑costs by 60%, cutting storage expenses over 60%, and achieving multi‑fold performance gains through serverless scaling, FalconSeek engine optimizations, and unified monitoring.
Cost OptimizationElasticsearchRAG
0 likes · 10 min read

This article explains how Baidu's vertical search platform tackled massive data growth and scaling challenges by redesigning its data management system, introducing elastic scheduling, decoupling ETCD access, implementing auto‑scaling, and advancing shard expansion to improve performance, stability, and cost efficiency.
Auto ScalingData ManagementSearch Architecture
0 likes · 18 min read

Bilibili’s large‑scale recall system separates online processing into a two‑tier merge service and an index service, supports multi‑channel text, item‑to‑item and vector indexes with real‑time updates, uses horizontal sharding, robust CI/CD, monitoring and degradation mechanisms, and is being extended toward model‑based recall and greater automation.
BilibiliSearch ArchitectureVector Search
0 likes · 16 min read

AIAPI, Baidu’s AI‑native retrieval platform for large language models, tackles hallucination, slow domain updates, and output opacity by delivering authoritative, timely, full‑content data through a dual‑channel architecture that combines traditional search and RAG, employs reusable ranking, graph‑enhanced data layers, dynamic caching that cuts storage by 70 %, and QueryPlan‑based QoS, achieving markedly higher retrieval quality and a 34 % speed gain with Wenxin 4.0.
AI-Native SystemsAIAPIQuery Planning
0 likes · 12 min read

The article walks through Elasticsearch’s document retrieval workflow, covering single‑document GET, multi‑document mget, the two‑stage query_then_fetch mechanism, shard routing, load balancing, query and fetch phases, collectors, rescore, and pagination optimizations.
Document RetrievalElasticsearchQuery_then_fetch
0 likes · 19 min read

This article describes how to combine Elasticsearch’s keyword matching with Milvus’s vector‑based semantic search to build a scalable document search service, covering data preprocessing, architecture, query handling, custom scoring, DSL configuration, and result merging.
ElasticsearchMilvusSearch Architecture
0 likes · 12 min read

Exgraph, Baidu Search’s graph execution engine, uses a human‑readable description language and a robust execution core with dependency injection, object pooling, and interruption handling to orchestrate complex, parallel or conditional tasks, improving code readability and unifying diverse execution scenarios in search architecture.
DAGGo DevelopmentSearch Architecture
0 likes · 10 min read

The article chronicles Baidu Search’s Model Architecture Group’s evolution of deep‑learning‑driven search, detailing the shift from inverted‑index to semantic vector indexing, the use of transformer‑based models for text and image queries, large‑scale offline/online pipelines, and extensive GPU‑centric optimizations such as pruning, quantization and distillation, all aimed at delivering precise, cost‑effective results to hundreds of millions of users.
ERNIEGPU InferenceSearch Architecture
0 likes · 14 min read

This article presents a cloud‑native redesign of Baidu's search middle‑platform that introduces intelligent data management, elastic scaling, on‑demand resource allocation, precise fan‑out, and localized computation to address efficiency, cost, stability, and performance challenges of large‑scale search workloads.
Data ManagementElastic ScalingSearch Architecture
0 likes · 14 min read

Cloud-native redesign of Baidu's search middle platform introduces partition, shard, replica, and addressing controllers that enable elastic scaling, on-demand resource allocation, precise fan‑out, and localized computation, reducing capacity adjustment time from weeks to hours, cutting costs by 30‑80%, raising availability above 99.9% and halving query latency.
Data ManagementElastic ScalingSearch Architecture
0 likes · 17 min read

This article compiles Baidu engineers' QCon 2021 talks, covering micro‑service evolution, large‑scale container elastic scaling, search system elasticity, AI‑chip deployment at massive scale, and cost‑focused monitoring, each with abstracts, outlines and key takeaways for practitioners.
AI chipsSearch Architecturecloud native
0 likes · 11 min read

Idlefish’s new multi‑engine concurrent search architecture replaces the tightly‑coupled single‑engine pipeline with deep engine isolation, asynchronous multi‑engine recall, and unified result merging, cutting dump build time from 14 h to 5 h, shrinking memory use dramatically, improving latency by only ~15 ms, and boosting exposure by 50 % and orders by 33 %.
LuaQuery PlanningSearch Architecture
0 likes · 10 min read


21CTOJul 29, 2020 · Backend Development
This article details how JD.com’s order center migrated from a MySQL‑only design to a high‑performance Elasticsearch cluster, evolving through isolation, replica tuning, master‑slave adjustments, and real‑time dual‑cluster architecture to achieve billions of documents, hundreds of millions of daily queries, and robust fault tolerance.
Backend EngineeringElasticsearchHigh Availability
0 likes · 12 min read

This article surveys how major Chinese tech firms such as JD.com, Ctrip, Didi, and 58.com deploy and evolve Elasticsearch clusters to handle massive order data, log analysis, real‑time monitoring, and security tasks, detailing architecture choices, shard strategies, multi‑cluster designs, and performance optimizations.
ElasticsearchSearch Architecturebig data
0 likes · 11 min read

iQIYI Douya’s emoji search evolved from ElasticSearch to a pure Lucene implementation and added semantic vector retrieval, enabling fast, scalable, and more accurate text‑based search of AI‑generated images for small‑to‑medium businesses by combining custom tokenization, dense embeddings, and hybrid ranking.
ElasticsearchLuceneSearch Architecture
0 likes · 14 min read

This article surveys how major Chinese internet companies such as JD.com, Ctrip, Qunar, 58.com and Didi have adopted Elasticsearch and the Elastic Stack for high‑volume order queries, log analysis, real‑time monitoring, security analytics, and large‑scale distributed search, describing their architecture evolution, shard strategies, and operational practices.
Log AnalyticsSearch Architecturebig data
0 likes · 16 min read

This article surveys how major Chinese tech firms such as JD.com, Ctrip, Qunar, 58.com and Didi design, scale, and operate massive Elasticsearch clusters for search, real‑time analytics, and security, detailing architecture choices, shard strategies, data pipelines and performance optimizations.
ElasticsearchSearch Architecturebig data
0 likes · 12 min read


JavaEdgeJun 26, 2019 · Backend Development
This article explains the complete workflow of Elasticsearch write, read, search, delete, and update operations, covering coordinating nodes, shard routing, buffer refresh, translog, segment files, commit/flush processes, and the underlying inverted index mechanism.
ElasticsearchNear Real-TimeSearch Architecture
0 likes · 10 min read

This article explains how Fangdd leverages Elasticsearch to boost search performance across consumer, broker, and internal products, detailing a platformized architecture that separates indexing and querying, addresses operational challenges, and outlines design patterns for index management and incremental updates.
ElasticsearchPlatform DesignSearch Architecture
0 likes · 12 min read

This article reviews the evolution of Youzan's order search architecture over two years, detailing challenges from data growth, the creation of a hot‑state index covering half of search traffic, time‑sharded indexes, and the AKF expansion cube that guides multi‑axis scalability.
ElasticsearchSearch Architecturebackend development
0 likes · 10 min read

This article explains how Mafengwo transformed its search service by replacing serial function calls with a Golang‑based concurrent proxy, reducing average latency from 400‑500 ms to around 240 ms while improving scalability, fault tolerance, and resource utilization.
ConcurrencyProxySearch Architecture
0 likes · 6 min read

The Youzan Search Platform evolved from a simple Elasticsearch cluster in 2015 to a modular, message‑driven architecture with proxy validation, caching, and management tools, and now plans a cloud‑native, Kubernetes‑based 4.0 version that automates data sync, isolates workloads, and scales elastically to support billions of records.
ElasticsearchProxySearch Architecture
0 likes · 14 min read


21CTOApr 3, 2017 · Backend Development
This article details Mogujie's end‑to‑end search system architecture, describing both offline and online components such as Topn, ABTest, QR, UPS, the search engine, precision ranking, and feature management, and walks through a concrete online request example from query to final ranked results.
Search Architecturebackend developmente-commerce
0 likes · 12 min read

This article introduces Mogujie's end‑to‑end search system architecture, detailing its online and offline components such as Topn, ABTest, QR, fine‑ranking, search engine, UPS, and feature platforms, and then walks through a real‑world online request example to illustrate how queries are processed, rewritten, personalized, and finally ranked.
MogujiePersonalizationQuery Rewrite
0 likes · 11 min read

This article details Baidu Maps' technical team’s refactoring of the indexing (build) unit, outlining existing bottlenecks, design challenges, and a new decoupled architecture that separates storage, incremental updates, and full‑index construction using distributed table storage and message‑driven pipelines to improve scalability and reliability.
Baidu MapsSearch Architecturedistributed storage
0 likes · 9 min read


21CTONov 17, 2015 · Backend Development
This article explains how a major e‑commerce platform built a horizontally scalable distributed search engine, designed efficient sharding and routing strategies, and implemented automated deployment, rapid scaling, and real‑time monitoring to handle the massive traffic of the 11.11 shopping festival.
Auto ScalingBackendDistributed Search
0 likes · 13 min read
