Skip to content
Tagged articles

vector database

290 articles · Page 1 of 3
21CTO
21CTO
Nov 15, 2026 · Databases

DocumentDB 1.0: Open-Source PostgreSQL Document DB with MongoDB Wire Compatibility

Microsoft's DocumentDB 1.0 releases as an MIT-licensed PostgreSQL extension and gateway compatible with MongoDB wire protocol, offering Kubernetes support, security focus, and a permissive license alternative to MongoDB's SSPL, while benchmarks show mixed performance versus MongoDB and FerretDB.

BenchmarkDocumentDBKubernetes
0 likes · 6 min read
DocumentDB 1.0: Open-Source PostgreSQL Document DB with MongoDB Wire Compatibility
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Nov 7, 2026 · Databases

Building Knowledge Graphs & Wiki from Enterprise Docs with Alibaba Cloud Milvus

This tutorial demonstrates how Alibaba Cloud Milvus's knowledge construction feature transforms product manuals and warranty policies into a queryable knowledge graph and team Wiki, enabling accurate AI-powered customer service answers by linking ontology definitions, graph relationships, and sourced documentation.

Alibaba CloudKnowledge GraphMilvus
0 likes · 9 min read
Building Knowledge Graphs & Wiki from Enterprise Docs with Alibaba Cloud Milvus
SmartApe AI
SmartApe AI
Nov 6, 2026 · Artificial Intelligence

Jev Decision Model Beats LLM Reranking in Graph RAG for Multi-Hop QA

Zilliz's open-source Vector Graph RAG integrates the Jev decision model with knowledge graph retrieval, achieving 86.61% Recall@5 on MuSiQue and 2Wiki datasets while reducing model call latency, outperforming LLM-based reranking methods in both accuracy and speed.

Decision ModelGraph RAGJev
0 likes · 11 min read
Jev Decision Model Beats LLM Reranking in Graph RAG for Multi-Hop QA
Ops Community
Ops Community
Oct 30, 2026 · Databases

Vector Database Operations: Milvus vs Qdrant Deployment, Scaling & Troubleshooting

This article provides a comprehensive operational comparison of Milvus and Qdrant vector databases, covering architecture differences, version baselines, deployment procedures, scaling strategies, backup/restore methods, monitoring metrics, alerting rules, and troubleshooting scenarios to guide selection based on data scale, team capability, and long-term operational costs.

MilvusQdrantbackup
0 likes · 67 min read
Vector Database Operations: Milvus vs Qdrant Deployment, Scaling & Troubleshooting
Java Captain
Java Captain
Oct 26, 2026 · Artificial Intelligence

Deploy Local LLMs Fast with Ollama and AnythingLLM: Step-by-Step Guide

This tutorial walks through installing Ollama, downloading models like Llama 3, configuring AnythingLLM with Ollama as the LLM and embedding provider, setting up LanceDB as the vector database, and creating a workspace for private local AI chat.

LanceDBOllamaanythingllm
0 likes · 5 min read
Deploy Local LLMs Fast with Ollama and AnythingLLM: Step-by-Step Guide
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
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
Shuge Unlimited
Shuge Unlimited
Oct 19, 2026 · Databases

Milvus 3.0 Segment Explosion: 12% Seal Threshold, 24h TTL, 16 Compaction Slots

This article dissects Milvus 3.0's default segment sealing behavior — 12% fill threshold, 24-hour TTL, and 16 compaction slots — explaining how sharding, large batches, and delete chains multiply segment counts, why compaction falls behind due to queue and slot bottlenecks, and the correct troubleshooting order: seal conditions first, compaction health second, manual force merge or clustering compaction last.

Configuration TuningL0 segmentsMilvus
0 likes · 21 min read
Milvus 3.0 Segment Explosion: 12% Seal Threshold, 24h TTL, 16 Compaction Slots
Shuge Unlimited
Shuge Unlimited
Oct 16, 2026 · Databases

Why Milvus 3.0 Can't Find Just-Inserted Data: The Hidden 5-Second Consistency Window

This article explains why newly inserted vectors in Milvus 3.0 may not be immediately searchable, revealing that the default Bounded consistency level sets a 5-second grace period (GracefulTime) during which recent writes fall outside the query's guaranteed timestamp (GuaranteeTs). It details the underlying mechanisms — TSO timestamps, timetick propagation, query node water-level waiting, and the four consistency levels — and provides a troubleshooting decision tree to distinguish expected behavior from actual failures.

GuaranteeTsMilvusTSO
0 likes · 14 min read
Why Milvus 3.0 Can't Find Just-Inserted Data: The Hidden 5-Second Consistency Window
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
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
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 baseCachingCost Optimization
0 likes · 15 min read
Production-Grade RAG Architecture: HA, Caching & Cost Control for AI Knowledge Bases
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.

ConsistencyData GovernanceEmbedding
0 likes · 22 min read
Lakehouse + AI: Vector Database as Derived Index, Not New System
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
Shuge Unlimited
Shuge Unlimited
Sep 29, 2026 · Databases

Milvus 3.0 Aggregation Inaccuracy: It's Missing Candidates, Not Safe Factor

The article explains that Milvus 3.0 search aggregation operates on ANN candidates, not full collections, so missing buckets stem from candidate budget limits (topK and TopHits.size), not the safe_factor parameter; it distinguishes candidate-signal counts from exact filtered counts and advises choosing the right query path for each need.

ANNMilvuscandidate budget
0 likes · 14 min read
Milvus 3.0 Aggregation Inaccuracy: It's Missing Candidates, Not Safe Factor
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
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 BankingFinancial TechnologyKnowledge Fusion
0 likes · 21 min read
From Knowledge Islands to Marketing Brain: Knowledge Fusion & Graph Reasoning for Corporate Products
Shuge Unlimited
Shuge Unlimited
Sep 16, 2026 · Databases

Why Milvus 3.0 Pagination Breaks After Reranking: When Cursor Scores Cross Worlds

Milvus 3.0's search iterator pagination fails after reranking because the cursor uses the last page's score as a boundary, but reranking replaces ANN distances with model predictions (e.g., XGBoost raw scores), causing the filter condition to exclude nothing and return duplicate pages. Milvus now explicitly rejects combining function chains with search iterators rather than fixing pagination, as the fix would require carrying original distances through the entire reduce pipeline—a feature-level change. Workarounds include using offset within single-search limits or moving reranking to the application layer.

MilvusPaginationReranking
0 likes · 21 min read
Why Milvus 3.0 Pagination Breaks After Reranking: When Cursor Scores Cross Worlds
Shuge Unlimited
Shuge Unlimited
Sep 14, 2026 · Databases

Milvus 3.0 Upgrade Is Easy, Rollback Is the Real Danger

This article analyzes why rolling back a Milvus 3.0 upgrade is far riskier than the upgrade itself, explaining how Storage V3, index version changes, WAL message semantics, and SDK/proto contracts create irreversible state boundaries that a simple image tag revert cannot undo.

Loon FFIMilvusSDK compatibility
0 likes · 21 min read
Milvus 3.0 Upgrade Is Easy, Rollback Is the Real Danger
Cloud Architecture
Cloud Architecture
Sep 13, 2026 · Backend Development

Production-Grade RAG with Spring AI: Verifiable, Rollbackable, Auditable Knowledge Base

This article details a production-ready customer service knowledge base built with Spring AI 2.0.1 and Milvus, covering immutable index versioning, tenant-isolated retrieval with parameterized filters, deterministic chunk IDs, idempotent ingestion pipelines, dual-index blue-green deployments, and comprehensive observability with automated rollback triggers.

KubernetesMilvusProduction Engineering
0 likes · 27 min read
Production-Grade RAG with Spring AI: Verifiable, Rollbackable, Auditable Knowledge Base
Cloud Architecture
Cloud Architecture
Sep 12, 2026 · Backend Development

From Monolith to Distributed: Spring AI Embedding Product Semantic Recall System

This article details the evolution of a product semantic recall system using Spring AI Embedding, covering architecture design, reliable vector indexing with Outbox pattern, hybrid search fusion, pgvector HNSW tuning, and safe migration to Milvus, with production readiness criteria and observability practices.

EmbeddingMilvusOutbox Pattern
0 likes · 20 min read
From Monolith to Distributed: Spring AI Embedding Product Semantic Recall System
Architecture Digest
Architecture Digest
Sep 9, 2026 · Artificial Intelligence

OpenViking: Self-Evolving Context Database for AI Agents Cuts 90% Tokens via File System

ByteDance's Volcano Engine open-sourced OpenViking, a self-evolving context database for AI agents that replaces vector stores with a viking:// virtual file system using three-layer progressive loading (L0/L1/L2), hierarchical retrieval with visible traces, and automatic long-term memory extraction, cutting input tokens 34-91% and boosting LoCoMo benchmark scores while integrating with Claude Code, Codex, and other tools.

AI agentsBenchmarkMemory Systems
0 likes · 11 min read
OpenViking: Self-Evolving Context Database for AI Agents Cuts 90% Tokens via File System
Linyb Geek Road
Linyb Geek Road
Sep 3, 2026 · Artificial Intelligence

How to Choose an AI Agent Memory Framework: LangMem vs MemOS vs Mem0 Compared

This article compares three AI agent memory management frameworks—LangMem, MemOS, and Mem0—detailing their architectures, core features, code integration patterns, and deployment models, with a feature comparison table and decision guidance for selecting the right solution based on complexity, graph memory needs, and enterprise requirements.

AI agentsLangGraphLangMem
0 likes · 9 min read
How to Choose an AI Agent Memory Framework: LangMem vs MemOS vs Mem0 Compared
Architects Research Society
Architects Research Society
Sep 2, 2026 · Artificial Intelligence

Why Agent Memory Goes Beyond Vector Databases: Inside MNEMOVELA’s Cognition Runtime Model

The article explains that typical agent systems store long‑term memory as raw chat logs embedded in a vector database, which only captures similarity, and introduces MNEMOVELA’s cognition runtime model that classifies memories into types, uses Git‑like branching, hybrid retrieval, and context assembly to provide semantically rich, versioned agent memory.

Agent MemoryHybrid RetrievalMnemovela
0 likes · 6 min read
Why Agent Memory Goes Beyond Vector Databases: Inside MNEMOVELA’s Cognition Runtime Model
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Aug 24, 2026 · Artificial Intelligence

How Paimon and Milvus Build an AI‑Native Multimodal Data Lake

The article analyzes the structural challenges of maintaining separate data lake and vector database systems for AI agents and multimodal workloads, and presents an open‑source integration of Apache Paimon and Milvus that unifies storage, governance, and high‑performance vector retrieval on a single data plane.

AI infrastructureAgentic AIApache Paimon
0 likes · 24 min read
How Paimon and Milvus Build an AI‑Native Multimodal Data Lake
Java Architecture Diary
Java Architecture Diary
Aug 21, 2026 · Artificial Intelligence

LangChain4j 1.19 Switches to Stateless Streamable HTTP and Adds Hybrid Milvus Search

LangChain4j 1.19 drops SSE support in favor of a stateless Streamable HTTP protocol, introduces a Milvus‑v2 module that combines dense vector similarity with BM25 keyword matching for hybrid retrieval, and bundles dozens of bug fixes and new integrations across agents, HTTP clients, vector stores, and document parsers.

JavaLLMLangChain4j
0 likes · 9 min read
LangChain4j 1.19 Switches to Stateless Streamable HTTP and Adds Hybrid Milvus Search
DeepHub IMBA
DeepHub IMBA
Aug 19, 2026 · Artificial Intelligence

Why Vector Databases Aren’t True Memory: Core Differences in Multi‑Agent Memory

Multi‑agent systems often fail not because they cannot reason but because they misremember, and treating a vector database as memory leads to flat, noisy storage; the article analyzes structured memory types, attribution, consistency, staleness, and production‑grade architectures to solve these issues.

AI agentsBenchmarkKnowledge Graph
0 likes · 17 min read
Why Vector Databases Aren’t True Memory: Core Differences in Multi‑Agent Memory
Shuge Unlimited
Shuge Unlimited
Aug 16, 2026 · Databases

Milvus 3.0 External Tables: Patch‑Add Columns and Query Snapshots as Tables

This article dissects Milvus 3.0’s External Collection feature, explaining how function‑output fields extend source schemas, how additive‑only schema refresh patches manifests without moving source data, and how the milvus‑table format lets snapshots serve as zero‑copy external tables for both batch and serving workloads.

External CollectionMilvusSchema Refresh
0 likes · 19 min read
Milvus 3.0 External Tables: Patch‑Add Columns and Query Snapshots as Tables
Linyb Geek Road
Linyb Geek Road
Aug 16, 2026 · Artificial Intelligence

Complete Spring AI Stack: Mapping the 2026 Java AI Ecosystem

The article presents a layered roadmap of the 2026 Java AI ecosystem, compares major AI frameworks, LLMs, embedding models, vector databases, and agent toolchains, and offers three concrete stack configurations with cost estimates and practical configuration snippets for architects and technical leaders.

AI StackAgentEmbedding
0 likes · 13 min read
Complete Spring AI Stack: Mapping the 2026 Java AI Ecosystem
Geek Labs
Geek Labs
Aug 14, 2026 · Artificial Intelligence

How a Fully Local AI Memory System (MemoMind) Gives AI a Brain That Never Forgets

MemoMind is a 100% local, GPU‑accelerated AI memory platform that builds a persistent knowledge graph from every interaction, enabling AI coding assistants to retain decisions, recall context across sessions, and reason over accumulated facts without exposing data to the cloud.

AI MemoryClaude CodeGPU acceleration
0 likes · 15 min read
How a Fully Local AI Memory System (MemoMind) Gives AI a Brain That Never Forgets
AI Engineer Programming
AI Engineer Programming
Aug 2, 2026 · Artificial Intelligence

Comprehensive Cost Assessment of End-to-End RAG Systems

This report breaks down production‑grade Retrieval‑Augmented Generation (RAG) system costs into five modules—LLM inference, vector database, embedding, bandwidth, and infrastructure—revealing that model choice drives over 40% of expenses, quantisation can halve vector costs, and multimodal storage may outpace vector database spending.

EmbeddingLLM inferenceRAG
0 likes · 14 min read
Comprehensive Cost Assessment of End-to-End RAG Systems
DataFunSummit
DataFunSummit
Jul 27, 2026 · Artificial Intelligence

Why Do Long‑Horizon AI Agents Still Use the Wrong Memories?

Adding memory to agents is now straightforward, but when agents run for weeks across many interactions, the real challenge shifts from merely retrieving past data to determining which past information remains valid, how to manage its lifecycle, and how to govern cost, updates, and deletion, as highlighted by Oracle's technical report and benchmark evaluations.

Agent MemoryEnterprise AILong-Horizon AI
0 likes · 14 min read
Why Do Long‑Horizon AI Agents Still Use the Wrong Memories?
Shuge Unlimited
Shuge Unlimited
Jul 25, 2026 · Databases

How Milvus 3.0 Packs 1,031 Patches in One Row with Struct + EmbList, Eliminating Chunk Flattening

The article dissects Milvus 3.0's Struct and EmbList design for storing and querying multi‑vector documents, compares flattening, JSON and named‑vector approaches, explains storage constraints, row‑level vs element‑level search semantics, MAX_SIM integration, a sealed‑segment bug, and practical checklist recommendations.

Array of StructsEmbListMAX_SIM
0 likes · 19 min read
How Milvus 3.0 Packs 1,031 Patches in One Row with Struct + EmbList, Eliminating Chunk Flattening
AI Illustrated Series
AI Illustrated Series
Jul 20, 2026 · Artificial Intelligence

RAG Basics: Indexing and Query Phases Explained for Interviews

The article breaks down Retrieval‑Augmented Generation into offline indexing (document chunking, embedding, vector storage) and online query (question embedding, similarity search, augmented generation), highlights retrieval accuracy as the main bottleneck, and shows practical use cases such as internal knowledge bases and product documentation assistants.

AI InterviewEmbeddingRAG
0 likes · 5 min read
RAG Basics: Indexing and Query Phases Explained for Interviews
Shuge Unlimited
Shuge Unlimited
Jul 19, 2026 · Databases

How Milvus 3.0 Queries External Lakehouse Files Without Copying Data

Milvus 3.0 introduces an External Collection that treats Parquet and other lakehouse files as a read‑only query view, detailing how external_source and external_spec are validated, how stable file lists are built, how the two‑stage refresh recomputes segment mappings, and how virtual primary keys and milvus‑table snapshots enable seamless querying without data duplication.

External CollectionMilvusVirtual PK
0 likes · 17 min read
How Milvus 3.0 Queries External Lakehouse Files Without Copying Data
Shuge Unlimited
Shuge Unlimited
Jul 18, 2026 · Databases

Milvus 3.0 Snapshot: Pausing a Collection Without Copying Data

Milvus 3.0 introduces a lightweight Snapshot feature that creates a point‑in‑time, read‑only view of a collection by freezing metadata and segment manifests instead of copying data, and explains how restore, GC protection, and pin mechanisms work together to enable fast, safe rollbacks.

Copy SegmentGCMilvus
0 likes · 18 min read
Milvus 3.0 Snapshot: Pausing a Collection Without Copying Data
AI Open-Source Efficiency Guide
AI Open-Source Efficiency Guide
Jul 17, 2026 · Artificial Intelligence

wigolo: Zero‑Key, Zero‑Cost Local‑First Web Search Engine for AI Coding Agents

wigolo is an open‑source, local‑first web search platform for AI coding agents that removes API keys and query costs, caches results in a SQLite + vector store, supports 18 parallel search engines, offers intelligent crawling, research pipelines, and compares favorably against cloud‑based alternatives like Firecrawl, Exa and Tavily.

AI agentsMCPWeb Crawling
0 likes · 12 min read
wigolo: Zero‑Key, Zero‑Cost Local‑First Web Search Engine for AI Coding Agents
Java Tech Enthusiast
Java Tech Enthusiast
Jul 15, 2026 · Databases

Vector Databases Made Easy: A Beginner’s Guide as Simple as Drinking Water

This article explains what vectors are, how embedding models turn text into high‑dimensional vectors, the common distance metrics, why specialized vector databases are needed, and walks through a hands‑on Python demo with ChromaDB before covering production‑grade options, advanced tuning, and typical pitfalls.

ANNChromaDBEmbedding
0 likes · 14 min read
Vector Databases Made Easy: A Beginner’s Guide as Simple as Drinking Water
AI Architecture Hub
AI Architecture Hub
Jul 15, 2026 · Artificial Intelligence

Why RAG Remains Essential in the Long-Context Era: Trends and Tech Evolution

Despite the rise of million‑token long‑context models, hybrid retrieval‑augmented generation (RAG) solutions saw a 200% quarterly procurement surge while naive single‑vector RAG was abandoned by over 70% of firms, highlighting a mature, multi‑generation RAG technology stack that remains indispensable for enterprise AI.

AI EngineeringHybrid RetrievalRAG
0 likes · 20 min read
Why RAG Remains Essential in the Long-Context Era: Trends and Tech Evolution
AgentGuide
AgentGuide
Jul 10, 2026 · Artificial Intelligence

What Is Retrieval‑Augmented Generation (RAG)? A Quick Technical Overview

Retrieval‑Augmented Generation (RAG) lets a large language model first fetch relevant documents, turn them into vectors stored in a vector database, and then generate answers based on those retrieved passages, ensuring more accurate and grounded responses for private or domain‑specific queries.

EmbeddingRAGRetrieval-Augmented Generation
0 likes · 7 min read
What Is Retrieval‑Augmented Generation (RAG)? A Quick Technical Overview
ThinkingAgent
ThinkingAgent
Jul 6, 2026 · Artificial Intelligence

Turning Data into Model-Ready Knowledge with RAG Pipelines and Vector DBs

An enterprise RAG pipeline must transform scattered documents into timely, secure, and explainable knowledge for LLMs, covering parsing, cleaning, chunking (recursive, semantic, contextual), embedding with BGE‑M3, hybrid vector‑BM25‑graph retrieval, RRF fusion, cross‑encoder rerank, ACL pre‑filtering, and minute‑level incremental updates.

ACLEmbeddingHybrid Retrieval
0 likes · 28 min read
Turning Data into Model-Ready Knowledge with RAG Pipelines and Vector DBs
Shuge Unlimited
Shuge Unlimited
Jul 5, 2026 · Databases

Four States a Milvus Delete Passes Through – Uncovering the Most Complex Operation

A Milvus delete command looks simple, but the primary key is first stored in an L0 delta segment, then triggers compaction that merges the delete mark into L1/L2 segments, passes through four distinct segment states, and involves multiple seal strategies, rollback fields, and version‑specific behaviours, illustrating why deletion is the system's most intricate operation.

L0L1L2
0 likes · 20 min read
Four States a Milvus Delete Passes Through – Uncovering the Most Complex Operation
AI Engineer Programming
AI Engineer Programming
Jul 4, 2026 · Artificial Intelligence

How Pinecone Nexus Turns Vector Search into an Agent Knowledge Engine

The article analyzes the shift to agent‑centric AI, explains why traditional retrieval creates a costly "Ten blue links" loop, and details how Pinecone Nexus’s context compiler and composable retriever, together with the KnowQL language, provide structured, governed knowledge that boosts task completion rates, cuts latency, and reduces token usage by up to 90%.

AI agentsKnowQLKnowledge Engine
0 likes · 14 min read
How Pinecone Nexus Turns Vector Search into an Agent Knowledge Engine
Shuge Unlimited
Shuge Unlimited
Jun 29, 2026 · Databases

Inside Milvus’ Index Engine: 3‑Layer Parameter Filling, Compile‑time Hardware Split, and a 16× Memory Trade‑off

The article dissects Milvus’ index engine, revealing that AUTOINDEX relies on a three‑stage default‑parameter pipeline, that CPU/GPU index selection is fixed at compile time via Go build tags, that the C++ Knowhere engine executes the algorithms, and that version aggregation, scalar V3 format, and the new AISAQ index embody deliberate memory‑vs‑IO trade‑offs.

AISAQAUTOINDEXCPU/GPU build tags
0 likes · 26 min read
Inside Milvus’ Index Engine: 3‑Layer Parameter Filling, Compile‑time Hardware Split, and a 16× Memory Trade‑off
AI Engineer Programming
AI Engineer Programming
Jun 23, 2026 · Artificial Intelligence

Why Data Lineage Is the Final Piece of RAG Governance

The article explains how data lineage in Retrieval‑Augmented Generation systems links data quality, ingestion, and incremental sync into a traceable whole, detailing the five lineage nodes, schema trade‑offs, storage choices, and how lineage supports debugging, impact analysis, and version control.

Data GovernanceRAGdata lineage
0 likes · 15 min read
Why Data Lineage Is the Final Piece of RAG Governance
AI Engineer Programming
AI Engineer Programming
Jun 22, 2026 · Artificial Intelligence

Ensuring Consistent Incremental Sync in RAG Systems (Part 2)

The article examines how incremental synchronization, index stability, shadow‑index atomic switching, checkpointing, idempotency, backpressure handling, batch‑vs‑streaming trade‑offs, and multi‑layer validation (count reconciliation, content sampling, and retrieval regression) together keep vector‑based RAG knowledge bases reliable and up‑to‑date.

Data GovernanceIncremental SyncRAG
0 likes · 13 min read
Ensuring Consistent Incremental Sync in RAG Systems (Part 2)
Shuge Unlimited
Shuge Unlimited
Jun 21, 2026 · Databases

Why Deleting 1 Million Vectors in Milvus Doesn't Shrink Disk Space: A Deep Dive into 11 CompactionTypes

When Milvus appears to keep disk usage unchanged after deleting a million vectors, the cause is not a bug but a sophisticated compaction system that splits the single compact() API into eleven enum values, six independent policies, and seven special handling paths that together manage different kinds of data waste and ensure safe, incremental reclamation.

DataCoordForceMergeL0 Delete
0 likes · 23 min read
Why Deleting 1 Million Vectors in Milvus Doesn't Shrink Disk Space: A Deep Dive into 11 CompactionTypes
AI Engineer Programming
AI Engineer Programming
Jun 21, 2026 · Artificial Intelligence

RAG Data Governance: Incremental Sync and Consistency (Part 1)

The article explains how additions, updates, and deletions affect a vector store differently, outlines three layers of incremental synchronization—change detection, change handling, and service stability—and compares timestamp polling, content‑hash diffing, and CDC while discussing consistency models and conflict resolution in distributed vector databases.

CDCConsistencyData Governance
0 likes · 16 min read
RAG Data Governance: Incremental Sync and Consistency (Part 1)
Shuge Unlimited
Shuge Unlimited
Jun 20, 2026 · Databases

From 64 to a Million Tenants: Choosing the Right Milvus Multi‑Tenant Layer and Avoiding the 65,536 Ceiling

The article dissects Milvus's four‑layer multi‑tenant architecture—Database, Collection, Partition, and Partition Key—detailing each layer's default tenant limits, isolation strength versus scalability trade‑offs, hidden constraints like the 65,536 capacity ceiling, the Partition Key isolation switch, and practical guidance for selecting the appropriate layer in SaaS and regulated scenarios.

MilvusMulti-tenancyPartition Key
0 likes · 17 min read
From 64 to a Million Tenants: Choosing the Right Milvus Multi‑Tenant Layer and Avoiding the 65,536 Ceiling
Subtle Storm
Subtle Storm
Jun 19, 2026 · Artificial Intelligence

AI Concepts Every Architect Must Master

The article outlines the essential AI fundamentals architects need—from basic machine‑learning principles, token limits, and learning paradigms to RAG pipelines, vector‑database choices, AI agents, prompt engineering, and MLOps practices—so they can design reliable, scalable AI‑driven systems.

AIAI agentsMLOps
0 likes · 7 min read
AI Concepts Every Architect Must Master
AI Engineer Programming
AI Engineer Programming
Jun 19, 2026 · Artificial Intelligence

RAG Data Quality: Old Problems in a New Bottle

Even with meticulous cleaning, residual noise, redundant legal clauses, and approximate duplicates can degrade retrieval and generation in RAG systems, while privacy risks from embedding inversion and the need for continuous, metric‑driven governance make data quality the ultimate ceiling for performance.

Embedding InversionLLM RetrievalRAG
0 likes · 8 min read
RAG Data Quality: Old Problems in a New Bottle
Programmer DD
Programmer DD
Jun 18, 2026 · Artificial Intelligence

How Cursor Instantly Understands Massive Codebases

The article dissects Cursor's code‑base indexing pipeline, explaining how semantic vector search, trigram‑based regex filtering, AST‑driven chunking, custom embeddings trained on agent trajectories, Merkle‑tree change detection, and Turbopuffer's namespace‑per‑repo vector store combine to deliver sub‑second, accurate code retrieval even in monorepos with tens of thousands of files.

Code IndexingCursorMerkle tree
0 likes · 21 min read
How Cursor Instantly Understands Massive Codebases
Shuge Unlimited
Shuge Unlimited
Jun 14, 2026 · Artificial Intelligence

Beyond Vector Storage: Inside Milvus 2.6’s Three‑Layer AI Agent Architecture

Milvus 2.6 transforms from a pure vector‑storage backend into a full‑stack AI‑Agent infrastructure by introducing a three‑layer capability system—coding‑rule, protocol, and runtime—covering memory, retrieval, and tool backends, hybrid search, strict operation ordering, and multiple integration paths, while contrasting traditional RAG with agent‑driven modes.

AI agentsMCPMemory Backend
0 likes · 20 min read
Beyond Vector Storage: Inside Milvus 2.6’s Three‑Layer AI Agent Architecture
AI Engineer Programming
AI Engineer Programming
Jun 14, 2026 · Artificial Intelligence

10 RAG Architectures Every AI Engineer Should Master

The article debunks the claim that Retrieval‑Augmented Generation is obsolete, explains why huge context windows are impractical, and systematically presents ten RAG patterns—from basic Naïve RAG to advanced Graph and Multimodal RAG—detailing their trade‑offs, costs, and suitable use cases.

AI ArchitectureEmbedding ModelsRAG
0 likes · 16 min read
10 RAG Architectures Every AI Engineer Should Master
SpringMeng
SpringMeng
Jun 14, 2026 · Artificial Intelligence

How I Built an AI Contract Review System for 60,000 RMB in One Month

In 45 days a two‑person team delivered an AI‑powered contract review platform that parses PDFs, extracts key clauses, flags risks, and integrates with enterprise tools, using Python, FastAPI, LangChain, large language models, vector databases and OCR technologies.

AIFastAPILangChain
0 likes · 7 min read
How I Built an AI Contract Review System for 60,000 RMB in One Month
DataFunTalk
DataFunTalk
Jun 13, 2026 · Artificial Intelligence

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

This article examines the practical challenges of deploying Retrieval‑Augmented Generation (RAG) in enterprise settings, detailing the modular architecture, offline and online pipelines, hybrid retrieval, multi‑stage ranking, knowledge filtering, and two‑stage generation techniques that together improve search completeness, ranking quality, and answer accuracy.

Enterprise AIKnowledge GraphRAG
0 likes · 21 min read
Building an Enterprise‑Grade RAG 2.0 System: Architecture, Challenges, and Best Practices
DataFunSummit
DataFunSummit
Jun 9, 2026 · Artificial Intelligence

From Poor RAG Performance to Production‑Ready Systems: A Deep Technical Walkthrough

The article dissects why early RAG deployments suffer from low recall, hallucinations and runaway costs, then presents a step‑by‑step diagnostic framework, hybrid search architecture, knowledge‑engineering tricks, caching and routing strategies, and explores advanced GraphRAG and Agentic RAG techniques to build reliable, enterprise‑grade solutions.

Agentic RAGGraphRAGLLM
0 likes · 20 min read
From Poor RAG Performance to Production‑Ready Systems: A Deep Technical Walkthrough
AI Architecture Path
AI Architecture Path
Jun 5, 2026 · Artificial Intelligence

Supermemory Tops Three Authority Benchmarks, Solving AI Forgetting

Supermemory, the open‑source AI memory engine, eliminates repeated forgetting by offering a zero‑configuration, multi‑modal memory layer that tops LongMemEval, LoCoMo and ConvoMo benchmarks, integrates automatic learning, mixed RAG‑Memory search, built‑in connectors, privacy tags, and multiple deployment options from no‑code web to local offline versions.

AI MemoryBenchmarkRAG
0 likes · 14 min read
Supermemory Tops Three Authority Benchmarks, Solving AI Forgetting
Java Architect Handbook
Java Architect Handbook
Jun 3, 2026 · Artificial Intelligence

What Is Retrieval‑Augmented Generation (RAG) and Why It Matters for LLM Interviews

The article explains Retrieval‑Augmented Generation (RAG), why large language models suffer from hallucination, knowledge cutoff, domain gaps and traceability issues, and how RAG’s offline‑online pipeline, comparison with fine‑tuning and long‑context approaches, and emerging trends like Agentic and Graph‑RAG can be discussed in technical interviews.

AI InterviewRAGRetrieval-Augmented Generation
0 likes · 12 min read
What Is Retrieval‑Augmented Generation (RAG) and Why It Matters for LLM Interviews
Linyb Geek Road
Linyb Geek Road
May 31, 2026 · Artificial Intelligence

From Prompt to Harness: The Three Evolutions of AI Engineering

The article traces AI engineering's three-stage evolution—from single‑turn Prompt Engineering, through multi‑turn Context Engineering, to system‑level Harness Engineering—explaining the problems each stage solves, the techniques introduced, concrete examples, and why the shift matters for scalable, reliable AI agents.

AI EngineeringAgentHarness Engineering
0 likes · 11 min read
From Prompt to Harness: The Three Evolutions of AI Engineering
Subtle Storm
Subtle Storm
May 29, 2026 · Databases

How Vector Databases Power Intelligent Medical Q&A Systems

By integrating Milvus vector database with a Retrieval‑Augmented Generation architecture, the authors built an AI‑driven multi‑turn medical Q&A system that achieved 92% knowledge retrieval accuracy, 96.3% recall with 18 ms latency, and demonstrated the strengths, trade‑offs, and engineering practices of vector‑based semantic search in healthcare.

MilvusRAGSemantic Search
0 likes · 11 min read
How Vector Databases Power Intelligent Medical Q&A Systems
Subtle Storm
Subtle Storm
May 27, 2026 · Databases

What Is a Vector Database? Core Concepts, Architecture, and Trade‑offs

A vector database stores high‑dimensional numeric embeddings instead of traditional rows, enabling semantic similarity search through specialized indexes, metadata filtering, and massive scalability, while also presenting trade‑offs such as approximate results, update costs, and high memory consumption.

EmbeddingRAGSemantic Search
0 likes · 7 min read
What Is a Vector Database? Core Concepts, Architecture, and Trade‑offs
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
May 27, 2026 · Artificial Intelligence

Building a Multimodal Search with Alibaba Cloud Elasticsearch and Qwen‑VL

This article demonstrates how to integrate Alibaba Cloud Elasticsearch with the Qwen‑VL large model and DashScope Embedding API to extract image features and perform multimodal vector search, covering text‑to‑image, text‑to‑text, image‑to‑image, and image‑to‑text queries, with step‑by‑step code, environment setup, data loading, indexing, and a Streamlit demo.

DashScopeElasticsearchMultimodal Search
0 likes · 8 min read
Building a Multimodal Search with Alibaba Cloud Elasticsearch and Qwen‑VL
Su San Talks Tech
Su San Talks Tech
May 25, 2026 · Artificial Intelligence

Mastering RAG: Chunking, Embeddings, BM25 & Multi‑Index Retrieval in Python

This tutorial explains Retrieval‑Augmented Generation (RAG) from fundamentals to a full pipeline, covering text chunking strategies, VoyageAI embeddings, vector‑store implementation, BM25 lexical search, and a multi‑index retriever that fuses semantic and lexical results with Reciprocal Rank Fusion.

BM25PythonRAG
0 likes · 48 min read
Mastering RAG: Chunking, Embeddings, BM25 & Multi‑Index Retrieval in Python

Why Offline Deployment of Dify Is So Challenging – 10 Common Pitfalls and Solutions

Deploying Dify in an offline environment is fraught with hidden traps—from missing Docker images and vector‑database dependencies to network subnet conflicts, plugin‑daemon crashes, and silent external service time‑outs—requiring careful preparation, configuration, and maintenance to achieve a stable setup.

DifyDockerOffline Deployment
0 likes · 14 min read
Why Offline Deployment of Dify Is So Challenging – 10 Common Pitfalls and Solutions
TechVision Expert Circle
TechVision Expert Circle
May 23, 2026 · Artificial Intelligence

The Hidden Technical Debt of AI: Risks of Over‑relying on External Platforms

Relying heavily on external AI services like OpenAI, LangChain, and cloud vector databases creates a hidden technical debt that threatens control, availability, and data sovereignty, and the article dissects its causes, real‑world incidents, mitigation patterns, and practical 2026‑ready alternatives for resilient AI systems.

AILLMarchitecture
0 likes · 13 min read
The Hidden Technical Debt of AI: Risks of Over‑relying on External Platforms
AI Architecture Hub
AI Architecture Hub
May 19, 2026 · Artificial Intelligence

Agent Memory: From Theory to Practical Implementation

The article explains how AI agents can acquire long‑term memory by combining three functions—coherence, context, and learning—with four memory types, describes the full retrieval‑store loop, and provides a step‑by‑step Python implementation using OpenAI embeddings, ChromaDB, and forgetting strategies.

AI agentsChromaDBMemory Systems
0 likes · 17 min read
Agent Memory: From Theory to Practical Implementation
IT Services Circle
IT Services Circle
May 17, 2026 · Artificial Intelligence

60 Essential AI Terms Every Programmer Should Master

This article walks programmers through 60 core AI concepts—from the basics of large language models and tokens to advanced topics like prompt engineering, retrieval‑augmented generation, fine‑tuning, and inference optimization—organized into progressive skill levels and illustrated with concrete examples and code snippets.

AIInference OptimizationRAG
0 likes · 25 min read
60 Essential AI Terms Every Programmer Should Master
AI Engineer Programming
AI Engineer Programming
May 16, 2026 · Artificial Intelligence

How to Boost RAG Retrieval Quality: Real‑World Cost‑Benefit Analysis

This article examines practical ways to improve Retrieval‑Augmented Generation (RAG) retrieval quality—covering vector database choices, data chunking, embedding models, query expansion, and re‑ranking—while weighing performance gains against operational costs through multiple real‑world case studies.

LLMRAGRe-ranking
0 likes · 16 min read
How to Boost RAG Retrieval Quality: Real‑World Cost‑Benefit Analysis
DataFunSummit
DataFunSummit
May 7, 2026 · Artificial Intelligence

How LanceDB Powers Enterprise‑Level Memory in Volcano Engine’s OpenClaw

The article details Volcano Engine’s LAS AI team’s analysis, selection, and deep optimization of the LanceDB vector database as the core memory plugin for the enterprise‑grade OpenClaw (ArkClaw) agent platform, covering comparative evaluation, custom enhancements, and a vision for a cloud‑edge collaborative memory lake.

ArkClawAutoDreamContext Engine
0 likes · 16 min read
How LanceDB Powers Enterprise‑Level Memory in Volcano Engine’s OpenClaw
java1234
java1234
May 5, 2026 · Artificial Intelligence

Spring AI 2.0: New Video Tutorial Series Empowers Java Developers with AI

The author announces a refreshed Spring AI 2.0 video tutorial series and provides a detailed overview of the framework’s design goals, provider‑agnostic API, full‑type model support, Spring integration, enterprise value, typical use cases, and a comparison with competing Java AI libraries.

AI frameworkJavaLangChain4j
0 likes · 7 min read
Spring AI 2.0: New Video Tutorial Series Empowers Java Developers with AI
AI Architect Hub
AI Architect Hub
May 3, 2026 · Artificial Intelligence

Choosing the Right Vector Database: Milvus, Chroma, Weaviate, Qdrant, FAISS Compared

This article compares five popular vector databases—Chroma, Milvus, Weaviate, Qdrant, and FAISS—detailing their positions, strengths, weaknesses, suitable scenarios, a selection‑dimension matrix, common pitfalls, code implementations for a unified RAG pipeline, best‑practice recommendations, and thought questions to guide engineers in choosing and migrating vector stores.

ChromaFaissMilvus
0 likes · 23 min read
Choosing the Right Vector Database: Milvus, Chroma, Weaviate, Qdrant, FAISS Compared
DataFunSummit
DataFunSummit
May 3, 2026 · Artificial Intelligence

From Flawed to Production-Ready: Deep Dive into Building Enterprise-Grade RAG Systems

The article analyzes why early RAG deployments often fall short, dissects the most common technical pain points—from document parsing to vector overload—and presents a systematic roadmap that includes hybrid search, reranking, GraphRAG, Agentic RAG, model selection, scalability tricks, and security controls for robust B‑side production.

Agentic RAGEnterprise AIGraphRAG
0 likes · 20 min read
From Flawed to Production-Ready: Deep Dive into Building Enterprise-Grade RAG Systems
AI Explorer
AI Explorer
May 2, 2026 · Artificial Intelligence

How Sim Studio Redefines Open-Source AI Agent Orchestration with 28K+ Stars

Sim Studio is an open-source AI agent orchestration platform that provides a visual workflow builder, Copilot-driven natural-language node creation, and native vector-database integration, enabling developers and product teams to construct, deploy, and manage AI-powered employee clusters without writing glue code.

AI agentsCopilotSim Studio
0 likes · 6 min read
How Sim Studio Redefines Open-Source AI Agent Orchestration with 28K+ Stars
Shuge Unlimited
Shuge Unlimited
Apr 29, 2026 · Databases

Milvus Storage Tuning in Practice: 25× Query Speedup and Three Tricks to Cut Memory Usage by Half

This article walks through Milvus 2.3‑2.6.x storage optimizations—Mmap, tiered storage, and clustering compaction—explaining their principles, configuration hierarchy, benchmark results, and concrete deployment templates that together can boost query performance up to 25‑fold while halving memory consumption.

MilvusPerformance Tuningclustering compaction
0 likes · 24 min read
Milvus Storage Tuning in Practice: 25× Query Speedup and Three Tricks to Cut Memory Usage by Half
AI Illustrated Series
AI Illustrated Series
Apr 27, 2026 · Artificial Intelligence

Comprehensive RAG Interview Q&A: 22 In-Depth Questions and Answers

This extensive interview guide covers 22 core RAG questions, detailing the definition, workflow, embedding selection, vector database choices, retrieval optimization, multi‑turn handling, context compression, evaluation metrics, knowledge‑graph integration, operational challenges, Agentic and hybrid RAG, document update strategies, similarity algorithms, and hallucination mitigation, providing concrete examples and practical advice for AI interview preparation.

AI InterviewEmbeddingKnowledge Retrieval
0 likes · 29 min read
Comprehensive RAG Interview Q&A: 22 In-Depth Questions and Answers
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 RetrievalRAG
0 likes · 16 min read
Can Your RAG Pass the Demo? Scaling to 5,000 Docs for Reliable Answers
AI Illustrated Series
AI Illustrated Series
Apr 25, 2026 · Artificial Intelligence

How AI Agents Remember Everything: A Deep Dive into Memory System Design

The article explains why large language models lack persistent memory, introduces a three‑layer memory architecture for AI agents—sensory, working, and long‑term memory—and details how vector databases, embedding models, and retrieval strategies enable cross‑session knowledge retention and personalized assistance.

AI agentEmbeddingLong-term Memory
0 likes · 24 min read
How AI Agents Remember Everything: A Deep Dive into Memory System Design
ByteDance Data Platform
ByteDance Data Platform
Apr 23, 2026 · Artificial Intelligence

How LanceDB Powers Enterprise‑Scale Memory in OpenClaw Agents

This article details the technical evaluation and deep integration of LanceDB as a memory plugin for the OpenClaw‑based ArkClaw agent platform, covering plugin selection, core enhancements such as mixed retrieval, hierarchical memory, Autodream processing, Context Engine optimizations, Git‑style version control, and the vision of a unified edge‑cloud memory lake.

AI agentsArkClawLLM memory
0 likes · 12 min read
How LanceDB Powers Enterprise‑Scale Memory in OpenClaw Agents
Linyb Geek Road
Linyb Geek Road
Apr 22, 2026 · Artificial Intelligence

How to Build Short‑Term and Long‑Term Memory for LLM Agents Using Vector DBs and RAG

The article analyzes Agent memory design by comparing human short‑term and long‑term memory, explains context‑window management strategies, outlines persistent storage options such as vector databases, relational stores, knowledge graphs and fine‑tuning, and presents a three‑layer architecture with write, retrieval and forgetting mechanisms.

Agent MemoryLLMLangChain
0 likes · 15 min read
How to Build Short‑Term and Long‑Term Memory for LLM Agents Using Vector DBs and RAG