Skip to content
Tagged articles

RAG

500 articles · Page 1 of 5
Rain's Path to Java Mastery
Rain's Path to Java Mastery
Nov 19, 2026 · Artificial Intelligence

Beyond 512/64: Deep Dive into RAG Chunking Strategies from Theory to Java Production

This article analyzes RAG chunking strategies, explaining why default 512/64 parameters fail, how chunk size and overlap affect retrieval quality, and provides production-ready Java implementations including token-aware splitting, recursive Chinese-friendly splitters, semantic chunking, parent-child architectures, and evaluation-driven parameter tuning.

JavaRAGchunking
0 likes · 46 min read
Beyond 512/64: Deep Dive into RAG Chunking Strategies from Theory to Java Production
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Nov 18, 2026 · Artificial Intelligence

OntoL Lightweight Ontology: ABox-First Approach Skips Upfront TBox Modeling

OntoL's lightweight ontology platform enables rapid knowledge graph deployment by prioritizing ABox instance graphs over upfront TBox modeling, integrating multi-source data, entity resolution, and a custom query language to support traceability and agent-augmented RAG, with a progressive path to add semantic axioms later.

ABox-firstOntoLOntologyL_Cypher
0 likes · 7 min read
OntoL Lightweight Ontology: ABox-First Approach Skips Upfront TBox Modeling
IT Learning Made Simple
IT Learning Made Simple
Nov 18, 2026 · Artificial Intelligence

2026 AI Glossary: 88 Essential Terms Explained for Beginners

This article provides a beginner-friendly glossary of 88 essential AI terms for 2026, covering core concepts, dialogue techniques, agents, model optimization, multimodal AI, development tools, and advanced future concepts, each explained in plain language with everyday analogies.

AI agentsAI glossaryAI terminology
0 likes · 21 min read
2026 AI Glossary: 88 Essential Terms Explained for Beginners
Thought Artisan
Thought Artisan
Nov 12, 2026 · Artificial Intelligence

From Recency to Semantic Retrieval: Building On-Device Memory for Android AI Assistant

The article details the evolution of a memory system for an Android screen-reading AI assistant, from naive recency-based injection to on-device semantic retrieval using embeddings, covering research, lexical vs embedding benchmarks, model selection (bge-small-zh), runtime comparison (MNN vs LiteRT), quantization choices, and a fallback strategy ensuring zero regression.

AndroidMNNQuantization
0 likes · 13 min read
From Recency to Semantic Retrieval: Building On-Device Memory for Android AI Assistant
Frontline Investigation
Frontline Investigation
Nov 12, 2026 · Artificial Intelligence

Why AI Citations Don't Guarantee Trustworthy Answers

The article explains that AI-generated answers with source citations can still be unreliable because retrieving relevant documents doesn't ensure each claim is grounded in the cited text; subtle mismatches like "can apply" vs "can process" or added time commitments can mislead users, and better product designs should link each key assertion to its exact supporting evidence.

AI citationsAI reliabilityAmazon Bedrock
0 likes · 7 min read
Why AI Citations Don't Guarantee Trustworthy Answers

AsiaInfo's Network Ontology: Enabling AI to Understand, Judge, and Act on Networks

AsiaInfo presents a network ontology architecture centered on objects, relations, rules, and actions, integrating RAG, knowledge graphs, and agents to give AI unified professional logic for telecom operations, validated by fault location and enterprise line survey cases showing minutes-level root-cause analysis and hour-to-minute survey acceleration.

AI agentsAIOpsAsiaInfo
0 likes · 30 min read
AsiaInfo's Network Ontology: Enabling AI to Understand, Judge, and Act on Networks
IT Services Circle
IT Services Circle
Nov 10, 2026 · Artificial Intelligence

10 High-Frequency AI Agent Interview Questions: Technical Deep Dive with Code & Diagrams

This comprehensive guide covers 10 essential AI Agent interview questions, detailing core concepts like Agent vs LLM, Workflow vs Agent architectures, reasoning paradigms (ReAct, CoT, Plan-and-Execute, Self-Refine), Function Calling, MCP, error handling, memory systems, context management, RAG pipelines, and evaluation methodologies with code examples and diagrams.

AI agentAgent EvaluationContext Management
0 likes · 39 min read
10 High-Frequency AI Agent Interview Questions: Technical Deep Dive with Code & Diagrams
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Nov 8, 2026 · Artificial Intelligence

Why Rebuilding RAG Indexes Fails to Fix Stale Policy Answers

This article details how to guarantee RAG systems retrieve the correct policy version after updates, covering parsing, chunking, vector generation, index switching, cache invalidation, and request tracing, using a reimbursement policy change example to illustrate versioning pitfalls and debugging strategies.

RAGcache invalidationindex switching
0 likes · 19 min read
Why Rebuilding RAG Indexes Fails to Fix Stale Policy Answers
SpringMeng
SpringMeng
Nov 8, 2026 · Artificial Intelligence

Tencent Open-Sources WeKnora: RAG Framework for Complex Document Understanding

Tencent has open-sourced WeKnora, a RAG-based framework for understanding and semantically searching complex documents like PDFs and Word files, offering Agent-mode reasoning, hybrid retrieval, MCP tool integration, and private deployment, with over 36k GitHub stars.

AgentDocument UnderstandingLLM
0 likes · 8 min read
Tencent Open-Sources WeKnora: RAG Framework for Complex Document Understanding
Tech Freedom Circle
Tech Freedom Circle
Nov 8, 2026 · Artificial Intelligence

RRF in RAG: How Reciprocal Rank Fusion Solves ES-Milvus Score Fusion

This article explains Reciprocal Rank Fusion (RRF) for merging Elasticsearch sparse retrieval and Milvus vector retrieval scores in RAG systems, covering standard vs weighted RRF, the smoothing constant k, static weight configuration principles, and dynamic weight adjustment via intent classification and slot extraction.

Dynamic WeightingElasticsearchMilvus
0 likes · 25 min read
RRF in RAG: How Reciprocal Rank Fusion Solves ES-Milvus Score Fusion
macrozheng
macrozheng
Nov 6, 2026 · Artificial Intelligence

Tencent Open-Sources WeKnora: LLM Document Understanding & Search Framework

Tencent open-sources WeKnora, a modular RAG framework that combines multimodal document parsing, hybrid retrieval (keyword, vector, knowledge graph), and agent-based reasoning to enable semantic search and Q&A over complex documents, with support for local deployment and flexible model integration.

AgentDocument UnderstandingLLM
0 likes · 8 min read
Tencent Open-Sources WeKnora: LLM Document Understanding & Search Framework
SpringMeng
SpringMeng
Nov 6, 2026 · Interview Experience

What Technical Depth Do Agent Roles Require? Three Levels Explained

The article outlines three proficiency levels for AI agent engineering roles—basic (independent task completion with LangGraph/RAG), intermediate (production harness design, evaluation, fault handling), and advanced (long-task reliability, agentic abstention, algorithmic experiments)—and advises preparing a project retrospective with architecture diagrams, failure logs, and evaluation results.

AI agentAgentic AbstentionFault Tolerance
0 likes · 10 min read
What Technical Depth Do Agent Roles Require? Three Levels Explained
Architects Research Society
Architects Research Society
Nov 6, 2026 · Artificial Intelligence

100 AI Agent Frameworks Mapped: Architecture, Governance & Selection Guide

This article categorizes 100 distinctive AI agent frameworks across ten domains—orchestration, multi-agent collaboration, RAG, language ecosystems, governance, low-code platforms, autonomous coding agents, vertical research agents, browser/OS automation, and voice/Web3—providing selection criteria based on technical requirements like state management, multi-language support, and governance boundaries.

AI Agent frameworksGovernanceLangGraph
0 likes · 30 min read
100 AI Agent Frameworks Mapped: Architecture, Governance & Selection Guide
SpringMeng
SpringMeng
Nov 5, 2026 · Interview Experience

Unitree AI Agent Interview: Real Engineering Beats Theory, Why You Should Apply Anyway

A candidate from a non-top university interviews at Unitree for an AI Agent role and discovers the interview focuses on practical engineering challenges — RAG integration, tool calling design, Agent loop termination — rather than abstract theory, realizing interviewers face the same messy problems and that hands-on project experience matters more than credentials.

AI agentEngineering PracticeInterview Experience
0 likes · 9 min read
Unitree AI Agent Interview: Real Engineering Beats Theory, Why You Should Apply Anyway
SpringMeng
SpringMeng
Nov 3, 2026 · Artificial Intelligence

5 Agent Engineering Questions That Separate Builders from Buzzword Users

The author shares five practical engineering challenges — tool timeout handling, RAG retrieval debugging, long-context memory management, infinite loop prevention, and workflow recovery — that reveal whether Agent developers have real production experience beyond buzzwords like RAG and tool calling.

AI agentsIdempotencyLangGraph
0 likes · 11 min read
5 Agent Engineering Questions That Separate Builders from Buzzword Users
Frontline Investigation
Frontline Investigation
Nov 3, 2026 · Artificial Intelligence

Why Verbose AI Logging Keeps Sensitive Data Around Longer

The article argues that overly detailed AI application logs — capturing full user inputs, retrieved passages, prompts, and model outputs — create unnecessary copies of sensitive data without improving debuggability, and recommends logging traceable decision nodes instead of raw content.

AI loggingChinese lawDebugging
0 likes · 8 min read
Why Verbose AI Logging Keeps Sensitive Data Around Longer
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Nov 2, 2026 · Artificial Intelligence

Enterprise Ontology: When to Build, How to Pilot, and Why It Outlasts LLMs

This article explains what enterprise ontology is, how it differs from knowledge graphs, when to choose it over RAG, its long-term value, suitable scenarios, ROI measurement, pilot strategies, team roles, AI-assisted construction, and handling departmental definition differences.

AI implementationBusiness RulesEnterprise Ontology
0 likes · 18 min read
Enterprise Ontology: When to Build, How to Pilot, and Why It Outlasts LLMs
SpringMeng
SpringMeng
Oct 31, 2026 · Fundamentals

8-Month Full-Stack + AI Learning Roadmap for CS Students

This article outlines a structured 6-stage learning roadmap for university computer science students, progressing from development fundamentals through frontend, Java backend, API integration, and AI application development, with specific time allocations, technical topics, and project-based milestones to build a deployable AI-enhanced management system.

AI application developmentFull-Stack DevelopmentLearning Roadmap
0 likes · 9 min read
8-Month Full-Stack + AI Learning Roadmap for CS Students
Data Bricklaying Diary
Data Bricklaying Diary
Oct 30, 2026 · Artificial Intelligence

Agent Citing Stale Experience? How to Audit, Retire, and Replace Obsolete Knowledge Cards

This article details a systematic process for detecting and managing obsolete experience cards in RAG-based agents, covering drift classification, review metadata, staged deprecation, feedback handling, validation requirements, and in-flight task remediation, with references to Evidently, concept drift research, and PROV-O provenance.

Data DriftLLMOpsManufacturing AI
0 likes · 22 min read
Agent Citing Stale Experience? How to Audit, Retire, and Replace Obsolete Knowledge Cards
Tech Freedom Circle
Tech Freedom Circle
Oct 30, 2026 · Artificial Intelligence

Ant Group RAG Interview: Vector, GraphRAG, LLM-Wiki, PageIndex & Ontology Fusion

This article details five RAG paradigms — Vector RAG, GraphRAG, PageIndex, LLM-Wiki, and Ontology — their core differences, failure modes, and fusion strategies using a time-space orthogonal framework, with code examples and scenario-based orchestration for enterprise-grade retrieval systems.

GraphRAGKnowledge RetrievalLLM Architecture
0 likes · 29 min read
Ant Group RAG Interview: Vector, GraphRAG, LLM-Wiki, PageIndex & Ontology Fusion
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Oct 29, 2026 · Artificial Intelligence

LLMs Admit Inaccuracy — Why Trust Them as Universal? AI Infrastructure & Ontology Are Key

This article explains why large language models inherently hallucinate and cannot guarantee accuracy, yet enterprises mistakenly treat them as universal solutions; it argues that AI infrastructure and ontology modeling are essential to provide semantic rules, constraints, and knowledge boundaries that transform probabilistic generation into reliable, auditable business intelligence.

AI infrastructureLarge Language ModelsRAG
0 likes · 15 min read
LLMs Admit Inaccuracy — Why Trust Them as Universal? AI Infrastructure & Ontology Are Key
DataFunTalk
DataFunTalk
Oct 28, 2026 · Backend Development

Alibaba Cloud AI Search Tops VDBBench & MMEB: Full-Stack Optimization from Engine to Model

Alibaba Cloud AI Search achieves top rankings on VDBBench vector retrieval, Big5 and Tantivy traditional search benchmarks, and MMEB multimodal document retrieval through full-stack optimizations including FalconSeek kernel improvements for HNSW, native query execution, and the Ops-Colqwen3-4B multimodal embedding model.

AI searchBig5Elasticsearch
0 likes · 17 min read
Alibaba Cloud AI Search Tops VDBBench & MMEB: Full-Stack Optimization from Engine to Model
Rain's Path to Java Mastery
Rain's Path to Java Mastery
Oct 27, 2026 · Artificial Intelligence

Connecting LLM, RAG, Agent & MCP: A Java Engineer's Production AI Engineering Guide

This article uses a real e-commerce customer service request to thread together LLM, RAG, Agent, MCP, vector search, and cosine similarity, providing five-layer architecture diagrams, production-grade Java code, 16 pitfall tables, and 13 interview Q&As to show how to embed uncertain model capabilities into deterministic engineering systems.

AI EngineeringAgentCosine Similarity
0 likes · 59 min read
Connecting LLM, RAG, Agent & MCP: A Java Engineer's Production AI Engineering Guide
TechVision Expert Circle
TechVision Expert Circle
Oct 27, 2026 · Artificial Intelligence

Zoom's AI Companion: From Meeting Transcripts to Automated Task Dispatch

Zoom's new AI Companion Custom Add-on uses ASR, LLM structured extraction, and RAG to convert meeting conversations into structured tasks with business context, then routes them via conditional workflow automation to tools like Jira and Asana, though accuracy and data governance challenges remain.

AI CompanionASRMeeting Automation
0 likes · 12 min read
Zoom's AI Companion: From Meeting Transcripts to Automated Task Dispatch
AI Large Model Application Practice
AI Large Model Application Practice
Oct 25, 2026 · Artificial Intelligence

Fusing RAG, GraphRAG, PageIndex & LLM-Wiki for Enterprise Agent Knowledge Systems

This article analyzes four knowledge organization modes — Vector RAG, GraphRAG, PageIndex, and LLM-Wiki — explaining their distinct retrieval mechanisms, trade-offs, and how to combine them in enterprise Agent systems for tasks ranging from factual QA to cross-document relationship exploration and long-document verification.

AI agentsEnterprise Knowledge SystemsGraphRAG
0 likes · 25 min read
Fusing RAG, GraphRAG, PageIndex & LLM-Wiki for Enterprise Agent Knowledge Systems
Geek Labs
Geek Labs
Oct 25, 2026 · Artificial Intelligence

RAGFlow: 92k-Star Open-Source RAG Engine Turns Messy Documents into Reliable Knowledge Bases

RAGFlow, a 92k-star open-source RAG engine, solves enterprise document chaos by prioritizing parsing quality via its DeepDoc model for layout-aware chunking, hybrid vector/keyword retrieval with reranking, knowledge compilation into graphs and timelines, and Agentic multi-step reasoning, all deployable via Docker with a Go 1.0 rewrite for performance.

Agentic RAGDeepDocGo rewrite
0 likes · 18 min read
RAGFlow: 92k-Star Open-Source RAG Engine Turns Messy Documents into Reliable Knowledge Bases
Su San Talks Tech
Su San Talks Tech
Oct 24, 2026 · Databases

MySQL 9.0+ Goes Full AI: Native Vectors, RAG & AutoML in One Database

MySQL 9.0+ introduces native VECTOR type, built-in semantic search with RAG, and AutoML via SQL, enabling AI workloads without external services; the article details three core capabilities, two deployment modes (local enterprise edition and cloud HeatWave), complete query logic, and three runnable code examples for vector storage, similarity search, and document-based RAG.

AI IntegrationAutoMLDatabase AI
0 likes · 14 min read
MySQL 9.0+ Goes Full AI: Native Vectors, RAG & AutoML in One Database
Architect
Architect
Oct 23, 2026 · Artificial Intelligence

Uber's Legal Redlining Agent: How AI Cuts Contract Review Time by 20% in Word

Uber's Legal Redlining Agent embeds AI-powered contract review directly into Microsoft Word, combining rules, historical feedback, model suggestions, and lawyer decisions to process redlines through four engineering iterations that improved retrieval, decision-making, clause generation, and tone adjustment, achieving a 20% reduction in review time with 91% decision accuracy.

AI agentEvaluation MetricsHuman-in-the-Loop
0 likes · 38 min read
Uber's Legal Redlining Agent: How AI Cuts Contract Review Time by 20% in Word
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Oct 22, 2026 · Artificial Intelligence

Why Smarter LLMs Demand Stronger Enterprise Ontologies: The Overlooked Semantic OS

This article argues that as large language models grow more powerful, enterprises increasingly need formal ontologies—explicit, computable semantic structures—to provide the 'semantic operating system' that grounds AI in business reality, prevents silent failures, and enables reliable execution beyond chat.

AI agentsLarge Language ModelsRAG
0 likes · 17 min read
Why Smarter LLMs Demand Stronger Enterprise Ontologies: The Overlooked Semantic OS
TechVision Expert Circle
TechVision Expert Circle
Oct 21, 2026 · Artificial Intelligence

Paper2Agent: Turning Papers into Agents – Rethinking Knowledge Bases

The article explores Paper2Agent, a system that converts PDF papers into interactive agents capable of running experiments, contrasting it with traditional RAG knowledge bases and proposing three evolution strategies for knowledge management, including implementation pitfalls and cost considerations.

AI agentLLMPDF parsing
0 likes · 13 min read
Paper2Agent: Turning Papers into Agents – Rethinking Knowledge Bases
Full-Stack DevOps & Kubernetes
Full-Stack DevOps & Kubernetes
Oct 21, 2026 · Operations

K8s AIOps: 4 Capabilities to End Alert Fatigue, Automate RCA & Enable Self-Healing

This article explains how AIOps addresses Kubernetes operational challenges through four core capabilities—intelligent alert noise reduction, automated root cause analysis, predictive failure prevention, and safe self-healing—detailing implementation approaches like K8sGPT, operator-based agents, and RAG knowledge bases, and showing real-world improvements in efficiency, stability, and cost control.

AIOpsK8sGPTKubernetes
0 likes · 10 min read
K8s AIOps: 4 Capabilities to End Alert Fatigue, Automate RCA & Enable Self-Healing
Su San Talks Tech
Su San Talks Tech
Oct 20, 2026 · Artificial Intelligence

5 RAG Optimization Techniques That Actually Work in Production

The article details five practical engineering techniques to boost RAG accuracy in production: semantic chunking with metadata injection, hybrid vector/keyword search, cross-encoder reranking, query rewriting for conversational context, and dynamic evaluation to prevent hallucinations.

Dynamic EvaluationQuery RewritingRAG
0 likes · 10 min read
5 RAG Optimization Techniques That Actually Work in Production
Cloud Architecture
Cloud Architecture
Oct 20, 2026 · Backend Development

Spring AI + Milvus: Enterprise RAG Production Engineering – Verifiable Knowledge, Permissions, Capacity & Recovery

This article presents a production-grade RAG engineering methodology using Spring AI and Milvus, covering version baselines, capacity planning, security filters, schema design, retrieval quality, prompt injection defense, knowledge versioning, Milvus topology, concurrency control, caching, SSE streaming, observability, fault injection testing, and a minimal first-week delivery checklist.

MilvusMulti-tenancyProduction Engineering
0 likes · 42 min read
Spring AI + Milvus: Enterprise RAG Production Engineering – Verifiable Knowledge, Permissions, Capacity & Recovery
Rain's Path to Java Mastery
Rain's Path to Java Mastery
Oct 19, 2026 · Backend Development

Beyond API Calls: Master LLM Internals, KV Cache, RAG & Function Calling with Java

This comprehensive guide teaches backend engineers LLM fundamentals—from token prediction and attention mechanisms to KV Cache optimization—and provides production-ready Java code for token budgeting, SSE streaming, RAG, function calling, and agent loops, plus 14 real-world pitfalls and interview preparation.

AgentAttention MechanismFunction Calling
0 likes · 59 min read
Beyond API Calls: Master LLM Internals, KV Cache, RAG & Function Calling with Java
Su San Talks Tech
Su San Talks Tech
Oct 19, 2026 · Databases

Vector Database Tutorial: Embeddings, ANN Algorithms & RAG Hands-On Guide

This tutorial explains vector databases from fundamentals to production: representing data as vectors, embedding models for semantic search, ANN algorithms like HNSW and IVF, hands-on ChromaDB demo for RAG, and comparison of production databases Milvus, Qdrant, Pinecone, and Weaviate with common pitfalls.

ANN algorithmsChromaDBHNSW
0 likes · 14 min read
Vector Database Tutorial: Embeddings, ANN Algorithms & RAG Hands-On Guide
Java Tech Enthusiast
Java Tech Enthusiast
Oct 18, 2026 · Backend Development

Java vs Python: Why You Should Extend, Not Switch, for AI & Data

This article analyzes whether Java developers should switch to Python, distinguishing three motivations—AI application development, data analysis/automation, and career dissatisfaction—and argues for extending skills with Python rather than switching, detailing ecosystem boundaries, a real-world SaaS architecture, and practical learning targets.

AI application developmentFastAPIJava
0 likes · 15 min read
Java vs Python: Why You Should Extend, Not Switch, for AI & Data
Su San Talks Tech
Su San Talks Tech
Oct 18, 2026 · Artificial Intelligence

MinerU: Structure-Aware Document Parsing for RAG and Agent Workflows

This article explains why MinerU, an open-source document parser with 80k+ GitHub stars, outperforms traditional text-extraction tools by understanding document structure — handling multi-column layouts, tables, and formulas — and introduces its four-tier parsing modes, stable locators for Agent workflows, and practical integration code for Python and Java.

MinerUPDF parsingRAG
0 likes · 16 min read
MinerU: Structure-Aware Document Parsing for RAG and Agent Workflows
SpringMeng
SpringMeng
Oct 18, 2026 · Interview Experience

China Merchants Bank Java Backend Interview: 20 Technical Questions & Answers

A developer shares their successful China Merchants Bank Java backend interview experience, detailing 20 technical questions covering HashMap, ConcurrentHashMap, synchronization, thread pools, Redis cache penetration, MySQL indexing, Spring Boot auto-configuration, Agent memory, RAG, multi-agent orchestration, and more, with answers and preparation tips.

AgentAuto-ConfigurationBackend
0 likes · 35 min read
China Merchants Bank Java Backend Interview: 20 Technical Questions & Answers
Rain's Path to Java Mastery
Rain's Path to Java Mastery
Oct 15, 2026 · Artificial Intelligence

6-Round AI Interview: From ML/DL to RAG & Agent - SP Offer Breakdown

This article explains AI/ML/DL/LLM hierarchy, contrasts traditional vs AI programming, details LLM core concepts (Token, context window, emergence, hallucination, RAG, Agent), covers training paradigms, shows Java integration with Spring AI/LangChain4j, and provides a 6-round interview simulation with lifecycle closure.

AIAgentDeep Learning
0 likes · 20 min read
6-Round AI Interview: From ML/DL to RAG & Agent - SP Offer Breakdown
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Oct 15, 2026 · Artificial Intelligence

RAG Table Chunking: Why Rows Need Headers, Units, and Scoped Notes

The article explains why naive row-based table chunking for RAG loses critical context—headers, units, grouped rows, and scoped notes—and demonstrates a context-preserving approach that binds each row to its full explanatory metadata, enabling accurate retrieval without forcing models to guess meaning.

RAGchunking strategycontext preservation
0 likes · 18 min read
RAG Table Chunking: Why Rows Need Headers, Units, and Scoped Notes
51CTO HarmonyOS Developer Community
51CTO HarmonyOS Developer Community
Oct 14, 2026 · Mobile Development

HarmonyOS 7 Agent: Build Enterprise RAG Knowledge Base with Cloud Embeddings

The article demonstrates implementing a Retrieval-Augmented Generation (RAG) pipeline on HarmonyOS 7 for enterprise private knowledge base Q&A, covering document chunking with sliding window overlap, deterministic vectorization for offline testing, cosine similarity search, orchestrated index/retrieve/generate phases, system prompt constraints to prevent hallucination, UI citation display, and 27 offline unit tests.

Agent DevelopmentArkTSEnterprise Knowledge Base
0 likes · 16 min read
HarmonyOS 7 Agent: Build Enterprise RAG Knowledge Base with Cloud Embeddings
Su San Talks Tech
Su San Talks Tech
Oct 14, 2026 · Artificial Intelligence

RAG Deep Dive: Principles, Optimization & Production Implementation

This comprehensive guide explains RAG from first principles through production deployment, covering offline indexing (loading, chunking, embedding, vector storage), online query pipeline (retrieval, reranking, prompt assembly), hybrid search with BM25 and dense vectors, RRF fusion, cross-encoder reranking, evaluation metrics (recall@k, MRR, nDCG), query rewriting, metadata filtering, contextual retrieval, Agentic RAG, and a real-world case study building a style-matching writing assistant with 197 articles.

Agentic RAGChunking StrategiesContextual Retrieval
0 likes · 43 min read
RAG Deep Dive: Principles, Optimization & Production Implementation
Coder Trainee
Coder Trainee
Oct 13, 2026 · Artificial Intelligence

From AI Novice to Agent Developer: 5-Stage Roadmap to Production-Ready Agents

This guide presents a five-stage learning path for AI beginners to become production-ready Agent developers, covering cognitive foundations, hand-built prototypes, memory and tool integration, framework adoption, and production hardening with evaluation, observability, and safety practices.

AI agentsAgent DevelopmentLangChain
0 likes · 11 min read
From AI Novice to Agent Developer: 5-Stage Roadmap to Production-Ready Agents
AI Engineering
AI Engineering
Oct 13, 2026 · Artificial Intelligence

523 Lessons: Build a Working GPT from Scratch - Free AI Engineering Course

A free Chinese course 'Learn AI Engineering from Scratch' offers 523 lessons across 20 stages, guiding learners from environment setup to building a 124M-parameter GPT, distributed training, coding agents, and production RAG systems with interactive diagrams and hands-on projects.

AI EngineeringCoding AgentGPT
0 likes · 11 min read
523 Lessons: Build a Working GPT from Scratch - Free AI Engineering Course
Data Party THU
Data Party THU
Oct 13, 2026 · Artificial Intelligence

RAG Beyond Vector Databases: A Four-Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning

This survey paper introduces a four-axis taxonomy for Retrieval-Augmented Generation (RAG) systems—efficiency, defense, interactivity, and reasoning—moving beyond simple vector database integration to analyze design trade-offs in evidence retrieval, security, user alignment, and multi-step reasoning.

DefenseEfficiencyInteractivity
0 likes · 38 min read
RAG Beyond Vector Databases: A Four-Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
MaGe Linux Operations
MaGe Linux Operations
Oct 12, 2026 · Operations

Building a Production-Ready Ops Assistant with Dify: RAG, Workflows & Permissions

This comprehensive guide details how to build a production-grade enterprise operations assistant using Dify, covering knowledge base segmentation strategies, hybrid retrieval with reranking, workflow orchestration for document and real-time data queries, multi-tier permission boundaries, audit logging, and operational practices for deployment, testing, and continuous improvement.

DifyEmbedding ModelsLLM Application
0 likes · 148 min read
Building a Production-Ready Ops Assistant with Dify: RAG, Workflows & Permissions
Coder Trainee
Coder Trainee
Oct 11, 2026 · Artificial Intelligence

RAG Evolution: Four Stages from Naive to Agentic (2023-2026) & 2026 Trends

This series finale outlines RAG's evolution through four stages from Naive RAG (2023) to Agentic RAG (2026), identifies key 2026 trends including reasoning-integrated retrieval, multimodal understanding, domain-specific embeddings, and federated knowledge bases, and provides a four-level developer roadmap from beginner to expert.

Agentic RAGGraphRAGMultimodal RAG
0 likes · 6 min read
RAG Evolution: Four Stages from Naive to Agentic (2023-2026) & 2026 Trends
SpringMeng
SpringMeng
Oct 11, 2026 · Artificial Intelligence

Agent Developer Interviews: Why Building Demos Isn't Enough for Production

An interviewer shares insights from three Agent developer candidates who had impressive resumes but struggled with production concerns like tool error handling, RAG evaluation, memory design, loop control, and observability, highlighting the gap between demo-building and production-ready systems.

Agent DevelopmentLangGraphMemory Management
0 likes · 11 min read
Agent Developer Interviews: Why Building Demos Isn't Enough for Production
Coder Trainee
Coder Trainee
Oct 10, 2026 · Artificial Intelligence

Agentic RAG: Turning Passive Retrieval into Active Knowledge Agents

This article explains how to combine RAG with AI agents to create Agentic RAG, covering four collaboration patterns (RAG as Tool, Agent as Router, Multi-step RAG, Self-RAG), practical Java Spring Boot implementation with retrieval tools, self-evaluation loops, multi-step reasoning, architecture diagrams, and practical tips on iteration limits and cost monitoring.

AI agentsAgentic RAGMulti-step RAG
0 likes · 11 min read
Agentic RAG: Turning Passive Retrieval into Active Knowledge Agents
Coder Trainee
Coder Trainee
Oct 9, 2026 · Artificial Intelligence

GraphRAG: Knowledge Graph-Enhanced Retrieval for Multi-Hop Reasoning

This article explains GraphRAG, which combines knowledge graphs with RAG to solve multi-hop reasoning and global query limitations of traditional RAG, detailing Microsoft's GraphRAG approach, Java implementation with Neo4j for entity extraction and graph storage, retrieval processes, community summarization, cost trade-offs, and when to choose GraphRAG over standard RAG.

Community DetectionEntity ExtractionGraphRAG
0 likes · 11 min read
GraphRAG: Knowledge Graph-Enhanced Retrieval for Multi-Hop Reasoning
DataFunSummit
DataFunSummit
Oct 9, 2026 · Artificial Intelligence

Utopia: Open-Source Enterprise World Model Goes Beyond RAG with Bitemporal Graphs

Utopia introduces an open-source Enterprise World Model that replaces static RAG with a bitemporal knowledge graph tracking when facts were true and when systems knew them, adding conflict resolution, ontology-driven entity resolution, and MCP integration so agents query versioned business states rather than just latest documents.

Agent ContextBitemporal GraphEnterprise World Model
0 likes · 14 min read
Utopia: Open-Source Enterprise World Model Goes Beyond RAG with Bitemporal Graphs
Data STUDIO
Data STUDIO
Oct 9, 2026 · Artificial Intelligence

Perfect Retrieval, Wrong Answers: The Hidden Augmentation Layer in RAG

This article explains why RAG systems produce poor answers even when retrieval is accurate, detailing the critical augmentation layer—including position bias mitigation, reranking, deduplication, contradiction handling, token budgeting, prompt structuring, and failure modes—and provides a production-ready pipeline configuration.

Augmentation LayerCross-EncoderMMR
0 likes · 17 min read
Perfect Retrieval, Wrong Answers: The Hidden Augmentation Layer in RAG
Tech Ocean
Tech Ocean
Oct 9, 2026 · Artificial Intelligence

Do You Need a Vector Database for RAG? FastAPI Docs Benchmark Shows When Keyword Search Suffices

This article benchmarks keyword (BM25), vector (two Chinese embedding models), and hybrid retrieval on FastAPI's Chinese documentation, finding keyword search excels for exact-name queries while a larger vector model catches paraphrased questions, and hybrid helps only with strong embeddings; vector databases are unnecessary until data exceeds in-memory capacity.

BM25Embedding ModelsFastAPI
0 likes · 21 min read
Do You Need a Vector Database for RAG? FastAPI Docs Benchmark Shows When Keyword Search Suffices
SmartApe AI
SmartApe AI
Oct 8, 2026 · Artificial Intelligence

Tencent's Octop: Open-Source Local AI Workspace with Multi-Agent Architecture

Tencent open-sources Octop, a local AI workspace featuring four core components—Harness, Memory, Browser, and Gateway—that enable multi-agent collaboration, RAG knowledge bases, browser automation, terminal access, and multi-user deployment for personal and team use.

ACP protocolAI agentsFastAPI
0 likes · 9 min read
Tencent's Octop: Open-Source Local AI Workspace with Multi-Agent Architecture
Chengwu Tech Stack
Chengwu Tech Stack
Oct 8, 2026 · Artificial Intelligence

RAG from Prototype to Production: Scenarios, Pitfalls, and Deployment Strategies

This article explains Retrieval-Augmented Generation (RAG) fundamentals, identifies suitable use cases, details six common production pitfalls like document parsing errors and permission leaks, outlines required modules for production RAG systems, and describes evaluation and incremental rollout strategies for reliable deployment.

Chunking StrategiesLLMProduction Deployment
0 likes · 25 min read
RAG from Prototype to Production: Scenarios, Pitfalls, and Deployment Strategies
java1234
java1234
Oct 8, 2026 · Artificial Intelligence

Spring AI 2.0 OA System: RAG, Tool Calling & Multi-Role Approval Automation

This article details the architecture and implementation of an AI-powered OA system built with Spring AI 2.0, Spring Boot 4, and Vue 3, featuring intelligent leave form filling, approval progress querying, and RAG-based policy Q&A using Alibaba's Qwen and embedding models, with a four-role permission model, two-level approval engine, and Redis vector storage.

Alibaba BailianJWT AuthenticationMyBatis Plus
0 likes · 38 min read
Spring AI 2.0 OA System: RAG, Tool Calling & Multi-Role Approval Automation
PMTalk Product Manager Community
PMTalk Product Manager Community
Oct 8, 2026 · Product Management

AI Product Manager: Roles, Salary, Skills & How to Break In

This article analyzes the AI Product Manager role across three specializations — model/platform, application/business, and embodied/hardware — detailing daily responsibilities like prompt tuning, RAG implementation, and cost optimization, required competencies including technical boundaries and evaluation skills, salary ranges from ¥200K to ¥1M+, and a practical learning path with pitfalls to avoid.

AI Product ManagerAgentCareer Guide
0 likes · 9 min read
AI Product Manager: Roles, Salary, Skills & How to Break In
SpringMeng
SpringMeng
Oct 8, 2026 · Backend Development

Spring AI Alibaba Still Active: Why Java Remains Viable for Production AI Systems

The article debunks rumors that Spring AI Alibaba has stopped development, citing recent releases, and argues Java's strength in AI lies not in model training but in integrating AI capabilities into production enterprise systems through RAG, tool calling, and robust engineering practices.

AI IntegrationJavaLangChain4j
0 likes · 11 min read
Spring AI Alibaba Still Active: Why Java Remains Viable for Production AI Systems
Coder Trainee
Coder Trainee
Oct 7, 2026 · Artificial Intelligence

Build a Production-Ready Enterprise RAG Knowledge Base: Full Project Walkthrough

This final installment of a 12-part RAG series demonstrates a complete, deployable enterprise knowledge base system using Spring Boot 3.2, Spring AI 2.0, PgVector, BGE embeddings, hybrid retrieval with RRF fusion, reranking, multi-turn chat with memory, and a Vue 3 frontend, including Docker deployment and production checklist.

BGEEnterprise Knowledge BaseHybrid Retrieval
0 likes · 16 min read
Build a Production-Ready Enterprise RAG Knowledge Base: Full Project Walkthrough
Coder Trainee
Coder Trainee
Oct 6, 2026 · Artificial Intelligence

Production-Grade RAG Architecture: HA, Caching & Cost Control for AI Knowledge Bases

This article details a production-grade RAG architecture covering high availability design, multi-level caching strategies, asynchronous processing, cost optimization techniques, monitoring metrics, and a deployment checklist for moving AI knowledge bases from development to production environments.

AI knowledge baseHigh AvailabilityLLM
0 likes · 15 min read
Production-Grade RAG Architecture: HA, Caching & Cost Control for AI Knowledge Bases
PMTalk Product Manager Community
PMTalk Product Manager Community
Oct 6, 2026 · Product Management

AI PM Self-Assessment: 5-Dimension Framework to Quantify Skills & Gaps

This article presents a five-dimension capability model for AI product managers — Technical Understanding, Prompt Engineering, Data Thinking, Product Design, and Commercial Execution — each with five proficiency levels, enabling self-assessment in 10 minutes with concrete improvement paths and 2026 trend predictions.

AI Product ManagementData-Driven ProductRAG
0 likes · 18 min read
AI PM Self-Assessment: 5-Dimension Framework to Quantify Skills & Gaps
Lakehouse Research Base
Lakehouse Research Base
Oct 5, 2026 · Artificial Intelligence

Lakehouse + AI: Vector Database as Derived Index, Not New System

This article explains how to implement RAG within a lakehouse architecture by treating the vector database as a derived retrieval index rather than a separate system, covering embedding pipelines, Milvus index trade-offs, hybrid search, real-time updates via Flink, consistency governance, and troubleshooting common production issues.

ConsistencyEmbeddingFlink
0 likes · 22 min read
Lakehouse + AI: Vector Database as Derived Index, Not New System
AI Engineering
AI Engineering
Oct 5, 2026 · Artificial Intelligence

Why AI Agents Need Documentation, Not Memory: A Critique of RAG-Based Memory Plugins

The article critiques typical RAG-based memory plugins for AI agents, highlighting five fundamental flaws—similarity retrieval ignores correctness, fragments lose context, outdated facts persist, agents cannot recognize knowledge gaps, and storage is unauditable—and proposes a documentation-centric approach where agents read and write Markdown files in a structured workspace, exemplified by the open-source Operator Memory plugin.

AI agentsOperator MemoryRAG
0 likes · 8 min read
Why AI Agents Need Documentation, Not Memory: A Critique of RAG-Based Memory Plugins
Linyb Geek Road
Linyb Geek Road
Oct 5, 2026 · Databases

Beyond RAG: Vector Databases as General-Purpose Similarity Search Engines

This article explains why vector databases are general-purpose similarity search engines beyond RAG, covering embedding model selection (BGE), non-RAG use cases like recommendation and anomaly detection, core operations with ChromaDB and HNSW, selection criteria for ChromaDB, FAISS, Milvus, and Pinecone, and five practical engineering lessons on recall evaluation, API workarounds, distance vs similarity, chunking strategies, and metadata filtering.

ChromaDBEmbeddingHNSW
0 likes · 12 min read
Beyond RAG: Vector Databases as General-Purpose Similarity Search Engines
Coder Trainee
Coder Trainee
Oct 4, 2026 · Artificial Intelligence

RAG Prompt Engineering: Constraining Models to Use Retrieved Knowledge Correctly

This article details how to design effective RAG prompts that prevent hallucination, enforce source citation, handle missing information, concatenate multiple documents with metadata, manage multi-turn conversations with history compression, and provides a complete prompt template with a tuning checklist.

JavaLLMRAG
0 likes · 13 min read
RAG Prompt Engineering: Constraining Models to Use Retrieved Knowledge Correctly
Frontline Investigation
Frontline Investigation
Oct 2, 2026 · Industry Insights

Why Citations Don't Make Knowledge Base Answers Trustworthy

The article explains that knowledge base assistants often provide citations that don't actually support their conclusions, creating a trust gap; it argues for verifying citations rather than just displaying them, highlighting three critical distances and suggesting systems should admit uncertainty more often.

NISTOWASPRAG
0 likes · 8 min read
Why Citations Don't Make Knowledge Base Answers Trustworthy
PMTalk Product Manager Community
PMTalk Product Manager Community
Oct 1, 2026 · Product Management

From B-End PM to AI PM: Complete Transition Roadmap

The author shares a verified transition path from traditional B-end product management to AI product management, covering technical understanding of API interactions, core frameworks like LangGraph and Dify, RAG product design, tool design, open-source product teardowns, and a five-step hands-on learning roadmap culminating in an MVP project.

AI Product ManagerDifyLangGraph
0 likes · 7 min read
From B-End PM to AI PM: Complete Transition Roadmap
Linyb Geek Road
Linyb Geek Road
Oct 1, 2026 · Artificial Intelligence

MaxKB: Open-Source RAG Knowledge Base with Model-Neutral Design & Zero-Code Embedding

MaxKB is an open-source AI knowledge base Q&A system from Fit2Cloud that uses RAG with pgvector and LangChain to provide model-neutral, out-of-the-box intelligent question answering, supporting Docker deployment, multi-format documents, visual workflows, and zero-code embedding via iframe or API for enterprise knowledge bases, customer service, and developer portals.

LLMLangChainMaxKB
0 likes · 18 min read
MaxKB: Open-Source RAG Knowledge Base with Model-Neutral Design & Zero-Code Embedding
Java Captain
Java Captain
Sep 30, 2026 · Interview Experience

WXG First-Round Interview: 60 Questions from Algorithms to Agent Design

A shared WXG first-round interview experience lists 60 questions covering self-introduction, algorithms (IP-to-uint64, linked-list folding, uniform sampling), system design, AI tools, large-model hallucinations, RAG, vector search, collaborative filtering, 12306 ticketing architecture, Redis internals, MySQL B+ trees, concurrency locks, and design patterns.

AlgorithmsB+ TreeConcurrency
0 likes · 7 min read
WXG First-Round Interview: 60 Questions from Algorithms to Agent Design
Lobster Programming
Lobster Programming
Sep 29, 2026 · Databases

Why Vector Databases Are Essential Beyond Relational Databases for AI

This article explains why vector databases like Milvus and Qdrant are necessary for AI applications despite the existence of relational databases like MySQL, detailing differences in indexing (ANN vs B+ trees), query logic (similarity vs exact match), consistency models, data structures, and ideal use cases such as RAG and recommendation systems.

AI embeddingsANN indexesHNSW
0 likes · 6 min read
Why Vector Databases Are Essential Beyond Relational Databases for AI
Code Farmer Manor Chronicle
Code Farmer Manor Chronicle
Sep 28, 2026 · Artificial Intelligence

Prompt Engineering Fundamentals: Ask LLMs the Right Way

This guide covers essential prompt engineering techniques for large language models, including clear instructions, role assignment, output formatting, context injection, few-shot examples, chain-of-thought reasoning, structured outputs, troubleshooting common failures, and template-based prompting for RAG and agent applications.

AgentChain-of-ThoughtLLM
0 likes · 7 min read
Prompt Engineering Fundamentals: Ask LLMs the Right Way
AI Large Model Application Practice
AI Large Model Application Practice
Sep 28, 2026 · Artificial Intelligence

JEV in Agent Systems: 8 High-Speed Decision Patterns for LLM Agents

This article details eight practical scenarios where JEV (Judgment and Evaluation) models accelerate agent decision-making, including ReAct loop control, web automation, tool routing, safety guards, task evaluation, model routing, RAG filtering, and real-time robotics control, showing how lightweight classifiers reduce latency and token costs.

JevLLM agentsRAG
0 likes · 20 min read
JEV in Agent Systems: 8 High-Speed Decision Patterns for LLM Agents
Data Bricklaying Diary
Data Bricklaying Diary
Sep 26, 2026 · Artificial Intelligence

Why Your RAG System Still Gets Business Logic Wrong (And When Ontologies Help)

Even with accurate RAG retrieval, business logic errors persist due to field mapping mismatches, missing facts, batch rules, and implementation flaws; ontologies unify reusable definitions but cannot replace data, computation, or permissions, so teams should first diagnose the exact failure point before investing in ontology modeling.

Business LogicField MappingRAG
0 likes · 15 min read
Why Your RAG System Still Gets Business Logic Wrong (And When Ontologies Help)
DataFunTalk
DataFunTalk
Sep 26, 2026 · Artificial Intelligence

OpenAI Demotes RAG: Context Graphs Become Primary for Enterprise Agents

OpenAI's V7 case study reveals a shift where enterprise agents query a pre-built Context Graph first, falling back to RAG only when the graph lacks information, addressing retrieval bottlenecks shown by the HERB benchmark and enabling reliable multi-step agent workflows.

Context GraphHERB BenchmarkOpenAI
0 likes · 15 min read
OpenAI Demotes RAG: Context Graphs Become Primary for Enterprise Agents
MaGe Linux Operations
MaGe Linux Operations
Sep 26, 2026 · Operations

RAG System Operations: Vector Database Selection & Performance Tuning

This comprehensive guide covers end-to-end RAG system operations, from vector database selection and workload profiling to HNSW parameter tuning, filtering strategies, index freshness monitoring, embedding upgrades, capacity planning, backup validation, and troubleshooting methodologies with concrete examples and evaluation frameworks.

Backup RecoveryHNSWMilvus
0 likes · 64 min read
RAG System Operations: Vector Database Selection & Performance Tuning
DataFunSummit
DataFunSummit
Sep 24, 2026 · Industry Insights

Beyond RAG: Palantir's Ontology-Powered 85% Growth & Zero Churn Moat

Palantir's 85% revenue growth and 150% net retention stem from its Ontology semantic layer — not model superiority — which transforms commoditized AI cognition into verifiable, business-constrained decisions, creating deep vendor lock-in through battlefield-tested infrastructure.

AI commoditizationPalantirRAG
0 likes · 11 min read
Beyond RAG: Palantir's Ontology-Powered 85% Growth & Zero Churn Moat
java1234
java1234
Sep 24, 2026 · Backend Development

Spring AI 2.0 OA System: Architecture, RAG & Tool Calling Deep Dive

This article details the design of an AI-powered OA system built with Spring Boot 4, Vue 3, and Spring AI 2.0, covering three AI capabilities (smart leave forms, approval tracking, RAG policy QA), a four-role permission model, two-level approval engine, database schema, API endpoints, and vector retrieval configuration using Redis Stack and Alibaba Qwen models.

LLM integrationOA SystemRAG
0 likes · 37 min read
Spring AI 2.0 OA System: Architecture, RAG & Tool Calling Deep Dive
Lakehouse Research Base
Lakehouse Research Base
Sep 23, 2026 · Databases

Milvus 3.x: From Vector Database to Lake-Native AI Retrieval Engine

This article provides a comprehensive analysis of Milvus 3.x's evolution from a vector database to a Lake-Native retrieval engine, covering its architecture, External Collection for zero-copy indexing on data lakes, Storage V3, ANN indexes (HNSW, IVF, DiskANN), hybrid search, and production RAG architectures with performance tuning and troubleshooting guidance.

ANN IndexDiskANNHNSW
0 likes · 37 min read
Milvus 3.x: From Vector Database to Lake-Native AI Retrieval Engine
BanTech Think Tank
BanTech Think Tank
Sep 23, 2026 · Artificial Intelligence

From Knowledge Islands to Marketing Brain: Knowledge Fusion & Graph Reasoning for Corporate Products

China Postal Savings Bank built a corporate product recommendation system using multi-source knowledge fusion, a dual-engine vector database and knowledge graph, and a four-layer agent architecture (intent recognition, vector matching, graph retrieval, LLM polishing), achieving 90% accuracy—a 30% improvement over pure RAG—and deploying across 11 business channels with 36,000+ recommendations generated.

Corporate BankingKnowledge FusionLLM Agent
0 likes · 21 min read
From Knowledge Islands to Marketing Brain: Knowledge Fusion & Graph Reasoning for Corporate Products