BestHub
Sign in
Tagged articles
36 articles
Page 1 of 1
AI Engineer Programming
AI Engineer Programming
May 8, 2026 · Artificial Intelligence

Is Non-Vector RAG the Next Generation of Retrieval‑Augmented Generation?

The article analyses the relevance and accuracy shortcomings of traditional vector‑based RAG, explains how non‑vector approaches like PageIndex let LLMs navigate document trees for relevance classification and auditability, and evaluates their complexity, latency, metadata risks, and suitable use cases compared with hybrid retrieval.

Hybrid RetrievalLLMRAG
0 likes · 8 min read
Is Non-Vector RAG the Next Generation of Retrieval‑Augmented Generation?
Lao Guo's Learning Space
Lao Guo's Learning Space
May 6, 2026 · Artificial Intelligence

Why Your RAG Keeps Missing the Mark: Enterprise‑Level Pitfall Guide

This article examines why Retrieval‑Augmented Generation systems that work in demos often fail in production, detailing common pitfalls—from chunking and vector‑database selection to hybrid retrieval and re‑ranking—and offers concrete strategies, configuration tips, and a decision tree to build reliable enterprise‑grade RAG solutions.

Enterprise AIHybrid RetrievalRAG
0 likes · 12 min read
Why Your RAG Keeps Missing the Mark: Enterprise‑Level Pitfall Guide
DataFunTalk
DataFunTalk
May 4, 2026 · Artificial Intelligence

Engineering and Algorithm Innovations for RAG Engines in Office Applications

This article analyzes the challenges and practical solutions of building a Retrieval‑Augmented Generation (RAG) system for office scenarios, covering background issues, modular architecture, offline and online pipelines, hybrid retrieval, ranking models, knowledge filtering, prompt design, and two‑stage generation techniques.

AIDocument ParsingHybrid Retrieval
0 likes · 22 min read
Engineering and Algorithm Innovations for RAG Engines in Office Applications
DeepHub IMBA
DeepHub IMBA
Apr 30, 2026 · Artificial Intelligence

Why Real RAG Systems Need Both BM25 and Vector Search

The article analyzes how BM25 excels at exact token matching while vector embeddings capture semantic intent, explains their distinct failure modes, and shows that a hybrid retriever—combined with metadata filtering, proper chunking, and reciprocal rank fusion—delivers the most reliable results for RAG pipelines.

BM25EmbeddingHybrid Retrieval
0 likes · 17 min read
Why Real RAG Systems Need Both BM25 and Vector Search
MaGe Linux Operations
MaGe Linux Operations
Apr 28, 2026 · Artificial Intelligence

Why Your RAG Performance Is Poor: Common Issues and Optimization Strategies

This article systematically analyzes why Retrieval‑Augmented Generation pipelines often underperform—covering embedding model selection, chunking strategies, hybrid retrieval, reranking, context window waste, evaluation metrics, and a detailed troubleshooting checklist—while providing concrete code examples and best‑practice recommendations for engineers.

EmbeddingHybrid RetrievalRAG
0 likes · 19 min read
Why Your RAG Performance Is Poor: Common Issues and Optimization Strategies
Architect's Tech Stack
Architect's Tech Stack
Apr 27, 2026 · Artificial Intelligence

Can Your RAG System Pass the Demo and Remain Accurate Across 5,000 Documents?

The article dissects a tough interview question about building a production‑grade Retrieval‑Augmented Generation (RAG) system that not only works in a demo but also delivers stable, correct answers over a knowledge base of 5,000 documents, covering chunking, hybrid retrieval, intent routing, constrained generation, evaluation metrics, and operational safeguards.

Evaluation MetricsHybrid RetrievalIntent Routing
0 likes · 15 min read
Can Your RAG System Pass the Demo and Remain Accurate Across 5,000 Documents?
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Apr 27, 2026 · Artificial Intelligence

Can Your RAG Pass the Demo? Scaling to 5,000 Docs for Reliable Answers

The article walks through the practical challenges of turning a RAG demo into a production system for 5,000 insurance documents, covering knowledge‑base chunking, embedding model selection, recall‑threshold tuning, hybrid vector‑BM25 retrieval, intent‑aware query routing, prompt constraints, confidence scoring, and operational scaling, with concrete metrics and code examples.

EmbeddingHybrid RetrievalPrompt engineering
0 likes · 16 min read
Can Your RAG Pass the Demo? Scaling to 5,000 Docs for Reliable Answers
DataFunTalk
DataFunTalk
Apr 26, 2026 · Artificial Intelligence

Building an Enterprise‑Grade RAG 2.0 System: Architecture, Challenges, and Best Practices

This article analyses the practical construction of an enterprise‑level Retrieval‑Augmented Generation (RAG) 2.0 system, covering background issues of large models, a modular architecture, layered offline/online pipelines, hybrid retrieval, ranking strategies, prompt engineering, and deployment insights drawn from China Mobile’s production experience.

Enterprise AIHybrid RetrievalPrompt engineering
0 likes · 22 min read
Building an Enterprise‑Grade RAG 2.0 System: Architecture, Challenges, and Best Practices
DataFunTalk
DataFunTalk
Apr 24, 2026 · Databases

DM GDMBASE V4.0: HyperRAG, Long‑Term Memory & NL Agents for Graph‑Vector AI

At the 2026 China Database Technology & Industry Conference, DM unveiled GDMBASE V4.0, a graph database that natively fuses vectors and graphs, introduces HyperRAG, long‑term memory, and a natural‑language agent, and delivers sub‑500 ms retrieval, 30% higher recall and 60% lower hallucination rates for AI workloads.

AI integrationHybrid RetrievalHyperRAG
0 likes · 12 min read
DM GDMBASE V4.0: HyperRAG, Long‑Term Memory & NL Agents for Graph‑Vector AI
MaGe Linux Operations
MaGe Linux Operations
Apr 22, 2026 · Artificial Intelligence

5 Essential Design Principles for Building High‑Quality RAG Systems

This article outlines five critical design principles for constructing high‑quality Retrieval‑Augmented Generation (RAG) systems, covering document chunking strategies, embedding model selection, hybrid retrieval architectures, metadata filtering with multi‑level indexes, and reranking mechanisms, and provides concrete code snippets and evaluation metrics.

EmbeddingHybrid RetrievalRAG
0 likes · 17 min read
5 Essential Design Principles for Building High‑Quality RAG Systems
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Apr 20, 2026 · Cloud Computing

How Alibaba Cloud’s Agentic Search Redefines Enterprise AI Search

The article analyzes Alibaba Cloud Elasticsearch’s shift from keyword‑based to Agent‑native search, detailing the Agent Native architecture, hybrid retrieval 2.0, FalconSeek engine performance gains of up to 300%, cost reductions of 40‑70%, and the ecosystem of ES Skills, cloud‑native enhancements, and observability that together enable a scalable AI search platform for enterprises.

AI searchAgentic ArchitectureCost reduction
0 likes · 13 min read
How Alibaba Cloud’s Agentic Search Redefines Enterprise AI Search
DataFunTalk
DataFunTalk
Apr 15, 2026 · Artificial Intelligence

Building a Production‑Ready RAG System for Enterprise Knowledge Work

This article analyzes the challenges and practical solutions of deploying Retrieval‑Augmented Generation (RAG) in an enterprise office setting, covering background problems, modular architecture, offline and online pipelines, hybrid retrieval, multi‑stage ranking, knowledge filtering, prompt engineering, and model selection to achieve accurate, reliable answers.

Enterprise AIHybrid RetrievalRAG
0 likes · 21 min read
Building a Production‑Ready RAG System for Enterprise Knowledge Work
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Apr 10, 2026 · Artificial Intelligence

How to Build a Robust Agent Memory System: Architecture, Management, and Evaluation

This article provides a comprehensive guide to designing, implementing, and evaluating an Agent Memory module for large‑language‑model assistants, covering memory types, short‑ and long‑term storage, conflict resolution, hybrid retrieval, compliance, and practical interview answers.

Agent MemoryHybrid RetrievalInterview Preparation
0 likes · 32 min read
How to Build a Robust Agent Memory System: Architecture, Management, and Evaluation
AI Engineer Programming
AI Engineer Programming
Apr 8, 2026 · Artificial Intelligence

TF‑IDF vs BM25: Statistical Foundations of Text Retrieval for RAG

The article explains how TF‑IDF and BM25 compute term importance, compares their strengths and weaknesses, and shows how these sparse retrieval methods integrate with dense retrieval techniques such as DPR, SPLADE, and ColBERT in Retrieval‑Augmented Generation systems, concluding with a hybrid retrieval decision matrix.

BM25Hybrid RetrievalRAG
0 likes · 14 min read
TF‑IDF vs BM25: Statistical Foundations of Text Retrieval for RAG
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Apr 7, 2026 · Artificial Intelligence

Why Hybrid Retrieval Beats Pure Vector Search: BM25, RRF, and Real‑World Experiments

This article dissects the shortcomings of pure vector retrieval, explains how BM25 complements it, compares weighted‑sum and Reciprocal Rank Fusion (RRF) strategies, shows experimental results that identify optimal weight and k values, and provides practical engineering tips for deploying hybrid search in RAG systems.

BM25Hybrid RetrievalParameter Tuning
0 likes · 24 min read
Why Hybrid Retrieval Beats Pure Vector Search: BM25, RRF, and Real‑World Experiments
DataFunTalk
DataFunTalk
Apr 6, 2026 · Industry Insights

Building a Production-Ready RAG System: Architecture, Challenges, and Best Practices

This article examines the practical challenges of deploying Retrieval‑Augmented Generation (RAG) in enterprise settings, detailing its core components, modular architecture, offline and online pipelines, document parsing, query rewriting, hybrid retrieval, multi‑stage ranking, knowledge filtering, and prompt‑driven generation to achieve accurate, reliable answers.

Enterprise AIHybrid RetrievalKnowledge Filtering
0 likes · 21 min read
Building a Production-Ready RAG System: Architecture, Challenges, and Best Practices
IT Services Circle
IT Services Circle
Apr 6, 2026 · Artificial Intelligence

Mastering RAG Interview Questions: A Complete Retrieval Optimization Blueprint

This article breaks down the full RAG retrieval pipeline—from query understanding and rewriting, through hybrid retrieval and reranking, to chunking, context compression, and dynamic routing—providing concrete techniques, formulas, and performance metrics to help candidates ace interview questions on RAG systems.

Cross-EncoderHard Negative MiningHybrid Retrieval
0 likes · 16 min read
Mastering RAG Interview Questions: A Complete Retrieval Optimization Blueprint
Ray's Galactic Tech
Ray's Galactic Tech
Mar 30, 2026 · Artificial Intelligence

From Demo to Production: Building an Enterprise‑Grade RAG System with Spring AI & PGVector

This comprehensive guide explains how to design, implement, and operate a production‑ready Retrieval‑Augmented Generation (RAG) platform using Spring AI and PostgreSQL PGVector, covering architecture, indexing, hybrid retrieval, prompt engineering, scaling, security, observability, deployment, and common pitfalls for enterprise knowledge‑base applications.

Enterprise AIHybrid RetrievalObservability
0 likes · 42 min read
From Demo to Production: Building an Enterprise‑Grade RAG System with Spring AI & PGVector
DataFunTalk
DataFunTalk
Mar 27, 2026 · Artificial Intelligence

Building a Production‑Ready RAG Engine: Architecture, Challenges & Solutions

This article examines the practical challenges of deploying Retrieval‑Augmented Generation in enterprise settings, outlines a layered RAG architecture with offline document processing and online query handling, and details the hybrid retrieval, multi‑stage ranking, knowledge filtering, and generation techniques that improve accuracy and reduce hallucinations.

AI EngineeringHybrid RetrievalKnowledge Filtering
0 likes · 22 min read
Building a Production‑Ready RAG Engine: Architecture, Challenges & Solutions
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 26, 2026 · Artificial Intelligence

Why Hybrid Retrieval Beats Pure Vector Search: BM25, RRF, and Real‑World Gains

This article explains why combining BM25 with dense vector search using Reciprocal Rank Fusion (RRF) improves recall for both exact‑term and semantic queries in a financial‑insurance document corpus, details the underlying algorithms, parameter choices such as k=60, provides Python implementations, and shows measurable performance gains in production.

BM25FAISSHybrid Retrieval
0 likes · 28 min read
Why Hybrid Retrieval Beats Pure Vector Search: BM25, RRF, and Real‑World Gains
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 21, 2026 · Artificial Intelligence

Step‑by‑Step Guide to Implementing a Hybrid Retrieval Function with RRF Fusion

This article breaks down the end‑to‑end retrieval function used in a RAG system, detailing each of the five stages—from request construction, hybrid vector + BM25 search, RRF fusion, cross‑encoder reranking, to threshold filtering—and provides concrete Python code, parameter choices, and performance insights.

Cross-EncoderElasticsearchHybrid Retrieval
0 likes · 13 min read
Step‑by‑Step Guide to Implementing a Hybrid Retrieval Function with RRF Fusion
DeepHub IMBA
DeepHub IMBA
Mar 17, 2026 · Artificial Intelligence

Advanced RAG Techniques: Boosting Retrieval with Query Translation and Decomposition

The article examines how retrieval‑augmented generation suffers from poor query formulation and presents two advanced strategies—query translation, which generates multiple semantically similar variants, and query decomposition, which breaks complex questions into finer sub‑queries—detailing methods such as fan‑out retrieval, reciprocal rank fusion, HyDE, step‑back prompting, and chain‑of‑thought retrieval, and explains when to combine them.

Hybrid RetrievalLLMQuery Decomposition
0 likes · 9 min read
Advanced RAG Techniques: Boosting Retrieval with Query Translation and Decomposition
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 10, 2026 · Artificial Intelligence

RRF vs Weighted Sum in RAG: Boost Retrieval, Solve Timeliness & Interview Challenges

This article explains why Reciprocal Rank Fusion often outperforms weighted‑sum fusion in Retrieval‑Augmented Generation, presents a three‑layer approach to keep knowledge bases timely, discusses HyDE’s cost‑benefit trade‑offs, and offers concrete interview‑ready answers for common RAG follow‑up questions.

HyDEHybrid RetrievalInterview Tips
0 likes · 13 min read
RRF vs Weighted Sum in RAG: Boost Retrieval, Solve Timeliness & Interview Challenges
DataFunTalk
DataFunTalk
Mar 1, 2026 · Artificial Intelligence

How to Build a Production‑Ready RAG System for Enterprise Knowledge Workflows

This article explains the challenges of applying large language models in real‑world office scenarios and presents a detailed, step‑by‑step RAG (Retrieval‑Augmented Generation) solution—including architecture, offline document processing, query rewriting, hybrid retrieval, multi‑stage ranking, knowledge filtering, and prompt‑driven generation—backed by practical lessons from a Chinese mobile operator.

Enterprise AIHybrid RetrievalPrompt engineering
0 likes · 22 min read
How to Build a Production‑Ready RAG System for Enterprise Knowledge Workflows
Architect
Architect
Jan 28, 2026 · Artificial Intelligence

How to Build a Reliable Long-Term Memory System for AI Agents

Designing a robust AI memory for long-running agents requires separating context from persistent storage, using markdown files, pre‑compaction flushing, hybrid vector‑BM25 retrieval, session pruning, and rebuildable SQLite indexes, ensuring explainable, editable, and portable recall while preventing context bloat and security leaks.

AI memoryClawdbotHybrid Retrieval
0 likes · 19 min read
How to Build a Reliable Long-Term Memory System for AI Agents
Mingyi World Elasticsearch
Mingyi World Elasticsearch
Dec 20, 2025 · Artificial Intelligence

How to Build an Enterprise‑Grade Intelligent Document QA System with Everything plus RAG

This article walks through the need for fast, accurate answers from massive document collections, compares plain keyword search and pure LLM chat, and presents a hybrid Retrieval‑Augmented Generation solution built with open‑source components, detailing architecture, hybrid retrieval, prompt engineering, deployment, performance tuning, and common pitfalls.

ElasticsearchHybrid RetrievalPrompt engineering
0 likes · 12 min read
How to Build an Enterprise‑Grade Intelligent Document QA System with Everything plus RAG
Volcano Engine Developer Services
Volcano Engine Developer Services
Nov 18, 2025 · Artificial Intelligence

How a Single SQL Query Powers Multi‑Modal AI Search with veDB‑Search

veDB‑Search extends MySQL compatibility to enable AI‑driven hybrid retrieval—combining vector, full‑text, and scalar searches—through a single SQL statement, simplifying architecture, boosting performance, and supporting in‑database embedding for seamless "search everything" capabilities.

Hybrid RetrievalIn-DB EmbeddingMulti‑Path Recall
0 likes · 16 min read
How a Single SQL Query Powers Multi‑Modal AI Search with veDB‑Search
Tech Freedom Circle
Tech Freedom Circle
Aug 26, 2025 · Artificial Intelligence

How to Optimize RAG for Alibaba Interviews? 7 Golden Rules Explained

This article provides a step‑by‑step technical guide to optimizing Retrieval‑Augmented Generation (RAG) for interview scenarios, covering query rewriting, HyDE, fallback strategies, routing and prompt routing, multi‑representation indexing, hybrid retrieval, re‑ranking, self‑RAG, generation control, performance benchmarking, and a practical checklist with concrete code examples and metrics.

AI InterviewHybrid RetrievalIndex Optimization
0 likes · 30 min read
How to Optimize RAG for Alibaba Interviews? 7 Golden Rules Explained
Sohu Tech Products
Sohu Tech Products
Mar 19, 2025 · Databases

Redis Vector Search Technology for AI Applications: Implementation and Best Practices

The article explains how Redis vector search, powered by RedisSearch’s FLAT and HNSW algorithms and supporting various data types and precisions, enables fast AI-driven similarity queries for text, image, and audio, and provides implementation guidance, optimization tips, and a real‑world customer‑service use case.

AI applicationsDatabase OptimizationHNSW
0 likes · 17 min read
Redis Vector Search Technology for AI Applications: Implementation and Best Practices
DataFunSummit
DataFunSummit
Oct 21, 2024 · Artificial Intelligence

Retrieval‑Augmented Generation (RAG) for Office Applications: Architecture, Challenges, and Practical Practices

This article introduces Retrieval‑Augmented Generation (RAG) as a solution to the hallucination, freshness, and data‑privacy issues of large language models, details its modular architecture, explains the layered system design and hybrid retrieval pipeline, and shares the practical challenges and engineering tricks encountered when deploying RAG in enterprise office scenarios.

AIHybrid RetrievalPrompt engineering
0 likes · 19 min read
Retrieval‑Augmented Generation (RAG) for Office Applications: Architecture, Challenges, and Practical Practices
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Jun 14, 2024 · Artificial Intelligence

How Alibaba Cloud OpenSearch Powers RAG: Insights from AICon 2024

In this talk, Alibaba Cloud's OpenSearch RAG team shares their year‑long journey of building retrieval‑augmented generation systems, covering data parsing, slicing, vectorization, hybrid retrieval, model fine‑tuning, performance optimizations, cost reduction, and future directions such as multimodal queries and agents.

AI searchHybrid RetrievalLLM
0 likes · 25 min read
How Alibaba Cloud OpenSearch Powers RAG: Insights from AICon 2024
Baidu Geek Talk
Baidu Geek Talk
Nov 29, 2021 · Artificial Intelligence

Pretrained Models for First-Stage Information Retrieval: A Comprehensive Review

This comprehensive review by Dr. Fan Yixing surveys how pretrained language models have transformed first‑stage information retrieval, tracing the shift from traditional term‑based methods to neural sparse, dense, and hybrid approaches, and discussing key challenges such as hard‑negative mining, joint indexing‑representation learning, and generative‑discriminative training.

Hybrid RetrievalNeural IRSparse Retrieval
0 likes · 15 min read
Pretrained Models for First-Stage Information Retrieval: A Comprehensive Review