Skip to content
Tagged articles

vector search

270 articles · Page 1 of 3
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Nov 14, 2026 · Artificial Intelligence

Meta's e-means: 45x Faster K-Means with EMA & Scaling Laws

Meta FAIR's e-means algorithm redesigns K-Means using exponential moving averages, dead cluster revival, cosine annealing, and scaling laws to achieve up to 45.5x GPU speedup over traditional Lloyd's algorithm, matching or exceeding clustering quality in just 2-3 epochs on billion-scale vector datasets, with code integrated into Faiss.

FaissK-MeansMeta FAIR
0 likes · 13 min read
Meta's e-means: 45x Faster K-Means with EMA & Scaling Laws
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Nov 6, 2026 · Big Data

EMR Serverless StarRocks + DLF Paimon: Multimodal Data Lake Retrieval for Autonomous Driving

This article details Alibaba Cloud's architecture for multimodal data lake retrieval using EMR Serverless StarRocks and DLF Paimon, covering design principles like early filtering and on-demand reading, Global Index mechanics, format selection between Paimon and Lance, real-world deployments in Alibaba's A Lake and AI Data platforms, and a complete autonomous driving loop from bad case detection to model validation.

DLF PaimonData Lake ArchitectureEMR Serverless StarRocks
0 likes · 28 min read
EMR Serverless StarRocks + DLF Paimon: Multimodal Data Lake Retrieval for Autonomous Driving
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Nov 4, 2026 · Big Data

EMR Serverless StarRocks Supports Paimon 2.0 for Multimodal Analytics & Retrieval

Alibaba Cloud's EMR Serverless StarRocks now fully supports Apache Paimon 2.0, enabling unified multimodal analytics and retrieval by integrating vector search, full-text search, scalar filtering, and BLOB handling within a single lakehouse architecture, with best practices for data management and query optimization.

Data EvolutionEMR ServerlessGlobal Index
0 likes · 29 min read
EMR Serverless StarRocks Supports Paimon 2.0 for Multimodal Analytics & Retrieval
Laravel Tech Community
Laravel Tech Community
Oct 29, 2026 · Backend Development

Laravel 13 Deep Dive: AI SDK, Vector Search & Framework-First AI Workflows

Laravel 13 ships a provider-agnostic AI SDK with agents, tool calling, and multimodal support, adds native pgvector-powered semantic search, JSON:API resources, PHP attributes for declarative configuration, CSRF hardening, centralized queue routing, and atomic cache renewal — all with a near-zero-breaking-change upgrade path from Laravel 12.

AI SDKCSRFCache Touch
0 likes · 14 min read
Laravel 13 Deep Dive: AI SDK, Vector Search & Framework-First AI Workflows
Xiaolei Talks DB
Xiaolei Talks DB
Oct 29, 2026 · Artificial Intelligence

How Zhihu Built a Unified Agent Memory Service with Mem0 and MongoDB

Zhihu shares its production-grade architecture for a multi-tenant Agent Memory service that combines Mem0's fact extraction and lifecycle management with MongoDB's vector and full-text search, enabling multiple specialized agents to accumulate, isolate, and retrieve long-term operational memories reliably.

Agent MemoryMem0Memory Isolation
0 likes · 22 min read
How Zhihu Built a Unified Agent Memory Service with Mem0 and MongoDB
Lakehouse Research Base
Lakehouse Research Base
Oct 27, 2026 · Databases

Unified Lakehouse Retrieval: One SQL for Hybrid Keyword, Filter, and Vector Search

The article explains how Alibaba Cloud EMR Serverless StarRocks converges full-text, scalar, and vector search into a single engine using RRF for score fusion, In-Filter for predicate pushdown into vector search, and Partial Update for column-level annotation writes, reducing data movement and operational complexity.

In-FilterMultimodal RetrievalPaimon
0 likes · 11 min read
Unified Lakehouse Retrieval: One SQL for Hybrid Keyword, Filter, and Vector Search
StarRocks
StarRocks
Oct 26, 2026 · Databases

StarRocks + Paimon: Multimodal Data Lake Retrieval Architecture

This article details how StarRocks and Paimon combine to build a multimodal data lake retrieval system, covering architecture design, early filtering and on-demand reading principles, Paimon's Global Index, Paimon vs Lance selection, and real-world implementations in autonomous driving and AI data platforms at Alibaba.

Global IndexPaimonStarRocks
0 likes · 26 min read
StarRocks + Paimon: Multimodal Data Lake Retrieval Architecture
DataFunTalk
DataFunTalk
Oct 25, 2026 · Artificial Intelligence

Agentic Search: Alibaba Cloud Shifts AI Search from Answers to Task Execution

At Yunqi 2026, Alibaba Cloud unveiled Agentic Search 2.0, evolving AI search from answer generation to task execution via Search Agents, Elasticsearch Agent for ops and insights, FalconSeek engine, and a knowledge engine, with benchmarks showing 96.69% on LoCoMo, 81.37% on LongMemEval-V2, 68% token savings, and 70% cost reduction.

AI searchAgentic SearchElasticsearch
0 likes · 13 min read
Agentic Search: Alibaba Cloud Shifts AI Search from Answers to Task Execution
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
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
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 StrategiesEvaluationLLM
0 likes · 25 min read
RAG from Prototype to Production: Scenarios, Pitfalls, and Deployment Strategies
DataFunTalk
DataFunTalk
Oct 5, 2026 · Artificial Intelligence

WeChat's Agentic OLAP Architecture: Observability, Memory & Access Control

WeChat's technical architecture team shares their exploration of adapting OLAP infrastructure for Agentic AI, covering distributed observability with Langfuse and ClickHouse, remote memory services using vector search and FUSE, and access protection mechanisms treating agents as authenticated identities.

Agentic AIClickHouseDiskANN
0 likes · 16 min read
WeChat's Agentic OLAP Architecture: Observability, Memory & Access Control
Big Data Technology & Architecture
Big Data Technology & Architecture
Sep 28, 2026 · Artificial Intelligence

Daft, Ray, and Lance: Rebuilding AI Data Infrastructure from Compute to Storage

This article introduces Daft, Ray, and Lance as the core layers of modern AI data infrastructure: Daft handles multimodal data computation, Ray manages distributed scheduling across heterogeneous resources, and Lance provides a lakehouse format optimized for vector search and random access, together replacing fragmented toolchains.

AI data infrastructureDaftLance
0 likes · 11 min read
Daft, Ray, and Lance: Rebuilding AI Data Infrastructure from Compute to Storage
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Sep 24, 2026 · Artificial Intelligence

Alibaba Cloud Agentic Search: From Finding Answers to Completing Tasks

At the 2026 Yunqi Conference, Alibaba Cloud unveiled Agentic Search 2.0, a new AI search paradigm that evolves from answer generation to autonomous task execution via planning, tool use, and self-evolving memory, backed by a re-architected Elasticsearch engine delivering 60ms hot-query latency and 70% cost savings at hundred-billion-vector scale.

AI searchAgentic SearchElasticsearch
0 likes · 13 min read
Alibaba Cloud Agentic Search: From Finding Answers to Completing Tasks
DataFunTalk
DataFunTalk
Sep 24, 2026 · Big Data

Alibaba Cloud ODPS Upgrade: AI-Native Multimodal Big Data Infrastructure for Agents

Alibaba Cloud unveiled a strategic upgrade to its ODPS big data platform at the 2026 Yunqi Conference, introducing AI-native, multimodal capabilities across MaxCompute, Hologres, and DataWorks to support Agentic AI workloads with vector search, heterogeneous compute, data sandboxes, and semantic knowledge graphs.

AI NativeAgentic AIDataWorks
0 likes · 19 min read
Alibaba Cloud ODPS Upgrade: AI-Native Multimodal Big Data Infrastructure for Agents
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
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Sep 23, 2026 · Big Data

ODPS 2026 Upgrade: AI-Native Multimodal Big Data Platform for Agentic Era

At Yunqi 2026, Alibaba Cloud unveiled a strategic upgrade to its ODPS big data platform, introducing agent-native architecture and multimodal computing across MaxCompute, Hologres, and DataWorks to support large model data refinement, embodied intelligence, and autonomous data operations with SQL AI, vector search, data sandboxes, and semantic knowledge graphs.

Agentic AIData SandboxDataWorks
0 likes · 21 min read
ODPS 2026 Upgrade: AI-Native Multimodal Big Data Platform for Agentic Era
Mingyi World Elasticsearch
Mingyi World Elasticsearch
Sep 21, 2026 · Databases

Easysearch 2.4.0 Vector Search: Verified Guide to Indexing, Querying & Hybrid Search Pitfalls

This article provides a step-by-step verified guide to implementing vector search in Easysearch 2.4.0, covering index creation with dense_vector fields, data ingestion with embeddings, k-NN query pitfalls including the mandatory 'k' parameter, and the critical distinction between compound queries and RRF-based hybrid search for combining keyword and semantic search.

Cosine SimilarityEasysearchEmbedding
0 likes · 10 min read
Easysearch 2.4.0 Vector Search: Verified Guide to Indexing, Querying & Hybrid Search Pitfalls
dbaplus Community
dbaplus Community
Sep 20, 2026 · Databases

SQLite: The Embedded Database That Replaces Solr, MongoDB, Kafka, and More

This article argues that SQLite, often dismissed as a toy database, can replace specialized systems like Elasticsearch, MongoDB, Kafka, ClickHouse, Redis, and even microservices due to its stability, zero-configuration deployment, built-in full-text search, JSON support, vector extensions, and local-first architecture, reducing operational complexity.

FTS5JSONMessage Queue
0 likes · 25 min read
SQLite: The Embedded Database That Replaces Solr, MongoDB, Kafka, and More
Architects Research Society
Architects Research Society
Sep 5, 2026 · Artificial Intelligence

Why Enterprise Knowledge Isn't Just Documents for LLMs: GNOSIVELA's Knowledge Fabric

The article argues that enterprise knowledge for AI agents requires more than vector retrieval; GNOSIVELA provides a knowledge fabric that unifies documents, data, semantics, rules, and provenance with governance, distinguishing source facts, normalized knowledge, and task-specific projections to ensure explainable, permissioned, and timely knowledge access.

AI agentsEnterprise AIaccess control
0 likes · 6 min read
Why Enterprise Knowledge Isn't Just Documents for LLMs: GNOSIVELA's Knowledge Fabric
JavaEdge
JavaEdge
Sep 4, 2026 · Artificial Intelligence

GBrain: Why Markdown & Knowledge Graphs Beat Databases for Agent Brains

This article dissects GBrain, an open-source AI agent brain that stores knowledge as Markdown in Git, builds a zero-LLM-cost knowledge graph via regex, and achieves 49.1% P@5 retrieval precision — 31 points higher than vector search alone — through hybrid retrieval, a nightly Dream Cycle for knowledge maintenance, and a clear separation between durable world knowledge (Brain) and operational state (Memory).

AI AgentDream CycleGBrain
0 likes · 20 min read
GBrain: Why Markdown & Knowledge Graphs Beat Databases for Agent Brains
IT Services Circle
IT Services Circle
Sep 3, 2026 · Backend Development

OpenSearch 3.0: Segment Replication, Read-Write Separation, and 9.5x Performance Boost

OpenSearch has evolved from an Elasticsearch fork into a Linux Foundation-governed Apache 2.0 platform with architectural innovations like segment replication and read-write separation, delivering 9.5x search performance gains in version 3.0, plus native GPU-accelerated vector indexing, hybrid search, and a growing ecosystem, making it a compelling alternative for license-sensitive, observability, and AI-driven search workloads.

Apache 2.0Apache LuceneElasticsearch
0 likes · 17 min read
OpenSearch 3.0: Segment Replication, Read-Write Separation, and 9.5x Performance Boost
Code Ape Tech Column
Code Ape Tech Column
Sep 3, 2026 · Databases

OpenSearch's Rise: 9.5x Faster Search, Read-Write Separation, and True Open Source

OpenSearch has evolved from an AWS fork of Elasticsearch into a Linux Foundation-hosted, Apache 2.0-licensed search platform with architectural innovations like segment replication, read-write separation, GPU-accelerated vector indexing, and native gRPC, delivering 9.5x query performance gains while offering full-stack free features and vendor-neutral governance.

Apache 2.0Apache LuceneElasticsearch
0 likes · 17 min read
OpenSearch's Rise: 9.5x Faster Search, Read-Write Separation, and True Open Source
DataFunTalk
DataFunTalk
Sep 3, 2026 · Databases

Hologres: One SQL Engine for Multimodal Data, AI Functions & Agent Memory

Hologres evolves from a real-time data warehouse into an AI data infrastructure, integrating multimodal data via Object Tables and Dynamic Tables, providing AI Functions for hybrid search within SQL, an AI Assistant for automated warehouse operations, and a long-term memory service for cross-session agent recall.

AI FunctionsAgent MemoryAlibaba Cloud
0 likes · 15 min read
Hologres: One SQL Engine for Multimodal Data, AI Functions & Agent Memory
Su San Talks Tech
Su San Talks Tech
Sep 1, 2026 · Databases

Why OpenSearch Is Gaining Massive Adoption: Architecture, Features, and Performance

OpenSearch, originally a fork of Elasticsearch, has become an independent Apache‑2.0‑licensed search and analytics platform governed by the Linux Foundation; its five‑layer architecture, segment replication, read/write separation, GPU‑accelerated vector indexing, and strong community growth deliver up to 9.5× query speed and make it a compelling choice over Elasticsearch.

Apache 2.0OpenSearchRead-Write Separation
0 likes · 15 min read
Why OpenSearch Is Gaining Massive Adoption: Architecture, Features, and Performance
Architect's Tech Stack
Architect's Tech Stack
Aug 29, 2026 · Artificial Intelligence

Redis 8's AI Overhaul: Vector Search, Vector Sets, Semantic Cache & Iris Context Engine

This article analyzes Redis 8's new AI capabilities including vector search with HNSW and int8 quantization, the native Vector Sets data type, LangCache semantic caching for LLM cost reduction, and the Iris real-time context engine for agent memory, with code examples and a comparison of when to use each feature.

AI infrastructureHNSWRedis 8
0 likes · 9 min read
Redis 8's AI Overhaul: Vector Search, Vector Sets, Semantic Cache & Iris Context Engine
Code Ape Tech Column
Code Ape Tech Column
Aug 28, 2026 · Databases

Redis Transforms into AI Data Infrastructure: Vector Search, Vector Sets, Semantic Cache & Agent Memory

This article details Redis's evolution into a comprehensive AI data infrastructure, covering its four core capabilities—vector search with hybrid queries, native Vector Sets data type, LangCache semantic caching for 70% LLM cost reduction, and Redis Iris context engine for AI agent memory—with technical implementations, performance benchmarks, and use-case recommendations.

AI agent memoryHNSWJava
0 likes · 16 min read
Redis Transforms into AI Data Infrastructure: Vector Search, Vector Sets, Semantic Cache & Agent Memory
Su San Talks Tech
Su San Talks Tech
Aug 27, 2026 · Artificial Intelligence

How Redis Becomes the Real‑Time Data Backbone for AI

Redis has evolved from a pure cache middleware into a full‑stack AI data infrastructure, offering vector search, native vector sets, semantic caching, and an AI Agent context engine, with sub‑millisecond latency, high throughput, and detailed performance benchmarks that illustrate its strengths and trade‑offs.

AIAgent MemoryJava
0 likes · 15 min read
How Redis Becomes the Real‑Time Data Backbone for AI
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Aug 26, 2026 · Artificial Intelligence

How Alibaba Cloud Elasticsearch’s Cloud‑Native Vector Engine Tops VectorDBBench

Alibaba Cloud Elasticsearch on ES 9.4, using the FalconSeek HNSW engine, achieves 82,520 QPS at 0.98 recall with a 1.8 ms P99 latency in VectorDBBench, and the article explains the end‑to‑end architectural redesign—including quantized candidate recall, batch distance computation, hot‑data layout, on‑demand re‑ranking, and segment lifecycle integration—that makes these results possible.

AI searchCloud NativeElasticsearch
0 likes · 17 min read
How Alibaba Cloud Elasticsearch’s Cloud‑Native Vector Engine Tops VectorDBBench
Mingyi World Elasticsearch
Mingyi World Elasticsearch
Aug 21, 2026 · Industry Insights

From Information Retrieval to AI Infrastructure: The Next Phase of Search Engines

Search engines are evolving from simple information‑finding tools into AI infrastructure that links enterprise data with AI capabilities, a shift highlighted by a DTCC conference slide and Elastic's AI Search event, and reflected in Elastic 9.5's new columnar mode, vector auto‑calibration, and PromQL support, as well as Easysearch's three‑step strategy for reliable, cost‑effective AI workloads.

AI InfraAI infrastructureEasysearch
0 likes · 5 min read
From Information Retrieval to AI Infrastructure: The Next Phase of Search Engines
Xiaolin Talks Programming
Xiaolin Talks Programming
Aug 14, 2026 · Backend Development

Spring Boot + OpenSearch: Building Hybrid Search with Full-Text, Vector Recall & RRF Ranking

This guide walks through building a production-ready hybrid search system using Spring Boot and OpenSearch, covering mapping design for BM25 and k-NN vector search, synonym configuration, RRF-based score fusion, connection pool tuning, multi-tenant security with DLS/FLS, CDC data sync, and cluster operations including ISM lifecycle policies.

BM25CDCISM
0 likes · 18 min read
Spring Boot + OpenSearch: Building Hybrid Search with Full-Text, Vector Recall & RRF Ranking
Java Architecture Diary
Java Architecture Diary
Aug 14, 2026 · Artificial Intelligence

Use JVM Native Vector API to Remove an External Vector Store in RAG

This guide shows how to replace external vector databases like Milvus or Qdrant with the JVM’s incubating Vector API and the integrallis/vectors library, providing built‑in distance kernels, indexing (FLAT, HNSW, IVF), and persistence, and demonstrates integration with Spring AI and LangChain4j through concise code examples and required JVM flags.

JVM Vector APIJavaLangChain4j
0 likes · 7 min read
Use JVM Native Vector API to Remove an External Vector Store in RAG
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Jul 29, 2026 · Big Data

Exploring EMR Serverless StarRocks AI Functions: Multimodal Embedding, Semantic Aggregation, and Mixed Retrieval

The article analyzes the newly released AI Function suite in Alibaba Cloud EMR Serverless StarRocks, detailing multimodal embedding, AI‑driven aggregation, semantic filtering, mixed vector‑full‑text search, architectural advantages such as SQL‑native execution, async pipelines, bounded resources, and real‑world use cases in advertising, gaming, and finance.

AI FunctionSQLStarRocks
0 likes · 16 min read
Exploring EMR Serverless StarRocks AI Functions: Multimodal Embedding, Semantic Aggregation, and Mixed Retrieval
Machine Heart
Machine Heart
Jul 22, 2026 · Artificial Intelligence

HELMSMAN Redefines Large-Scale Vector Retrieval with High-Performance ANNS

The HELMSMAN system, presented by the Xiaohongshu engine team at OSDI 2026, demonstrates a cost‑effective, high‑throughput, low‑latency approximate nearest neighbor search solution that migrates billions of vectors from DRAM to NVMe SSD arrays using a custom storage stack, clustering‑based indexing, learned pruning, and GPU‑accelerated distributed construction, achieving up to 16× throughput gains and over 90% hardware cost reduction.

Approximate Nearest NeighborGPU accelerationSSD
0 likes · 13 min read
HELMSMAN Redefines Large-Scale Vector Retrieval with High-Performance ANNS
Ray's Galactic Tech
Ray's Galactic Tech
Jul 15, 2026 · Artificial Intelligence

Scalable Knowledge Base with High‑Concurrency Crawling and Vector Search

The article explains why a production‑grade enterprise knowledge base requires more than just dumping PDFs into a vector store, detailing a distributed, event‑driven architecture with separate collection, processing, retrieval, and governance layers that handle high‑concurrency crawling, real‑time cleaning, versioned indexing, permission filtering, and feedback‑driven updates.

Data PipelineDistributed SystemsRAG
0 likes · 39 min read
Scalable Knowledge Base with High‑Concurrency Crawling and Vector Search
TechVision Expert Circle
TechVision Expert Circle
Jul 8, 2026 · Backend Development

Designing a 200M‑Request Recommendation System with 50ms P99 Latency

The team rebuilt a recommendation platform for a 80‑million‑DAU content service, scaling daily requests from 30 M to 200 M, cutting P99 latency from 800 ms to under 50 ms by introducing a four‑layer architecture, multi‑path recall (vector, real‑time, graph), transformer‑based ranking, multi‑level caching, predictive autoscaling, and comprehensive observability.

Feature StoreKubernetesRecommendation System
0 likes · 13 min read
Designing a 200M‑Request Recommendation System with 50ms P99 Latency
AI Architecture Path
AI Architecture Path
Jul 2, 2026 · Artificial Intelligence

How Cognee’s Single‑Postgres AI Memory Outperforms Traditional RAG (23K+ Stars)

Cognee is an open‑source AI memory platform that combines vector embeddings and knowledge‑graph reasoning on a single Postgres database, delivering dual retrieval, automatic ontology generation, and BEAM benchmark scores up to 0.8—more than double traditional RAG—while offering multi‑language SDKs and flexible deployment options.

AI MemoryOpen SourcePostgres
0 likes · 15 min read
How Cognee’s Single‑Postgres AI Memory Outperforms Traditional RAG (23K+ Stars)
BirdNest Tech Talk
BirdNest Tech Talk
Jun 29, 2026 · Artificial Intelligence

Packing 775 Saved Articles into a 4 MB Vector Store: A RAG Skill That Beats Karpathy’s Wiki

The author built an open‑source RAG skill called chao‑rag‑wiki that compresses 775 collected articles into a 4.8 MB vector index using TurboVec, hybrid dense‑plus‑BM25 retrieval and optional LLM reranking, then compares its zero‑compile latency and full‑recall strengths against Karpathy’s llm‑wiki approach.

AI knowledge baseHybrid RetrievalObsidian
0 likes · 16 min read
Packing 775 Saved Articles into a 4 MB Vector Store: A RAG Skill That Beats Karpathy’s Wiki
Shuge Unlimited
Shuge Unlimited
Jun 27, 2026 · Artificial Intelligence

How MFS Unifies 20+ Data Sources with a Single Verb Set and How Open Tag Replicates Claude Tag

The article dissects Zilliztech's MFS, showing how a thin‑client, stateful‑server architecture uses a unified verb set to access over twenty heterogeneous data sources, and explains how the Open Tag demo re‑creates Claude Tag's brain‑memory‑tools workflow on top of MFS while highlighting its design trade‑offs and production‑readiness limits.

AI agentsClaude TagContext Management
0 likes · 16 min read
How MFS Unifies 20+ Data Sources with a Single Verb Set and How Open Tag Replicates Claude Tag
Code Mala Tang
Code Mala Tang
Jun 25, 2026 · Artificial Intelligence

Why Rerank Is Essential: From 100 Retrieved Docs to the 5 Correct Answers in RAG

Even with a perfectly populated vector database, a RAG pipeline often returns irrelevant answers because the initial Bi‑encoder retrieval only narrows the pool to about 100 candidates, and without a Cross‑encoder rerank step the truly correct document—often buried around rank 37—never reaches the LLM for answering.

Bi-EncoderCross-EncoderEmbedding
0 likes · 9 min read
Why Rerank Is Essential: From 100 Retrieved Docs to the 5 Correct Answers in RAG
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Jun 24, 2026 · Cloud Computing

High‑Conversion Overseas E‑Commerce Search Using Alibaba OpenSearch

The GoTerra case study shows how Alibaba Cloud OpenSearch’s industry‑algorithm edition transformed a multilingual, multi‑modal e‑commerce search platform by introducing a four‑layer architecture, custom analyzers, white‑box vector indexing, parallel recall, and time‑based elastic scaling, cutting P99 latency from 250 ms to under 70 ms while boosting development efficiency and controlling costs.

Elastic ScalingOpenSearchSearch Optimization
0 likes · 16 min read
High‑Conversion Overseas E‑Commerce Search Using Alibaba OpenSearch
IT Services Circle
IT Services Circle
Jun 20, 2026 · Artificial Intelligence

How I Doubled RAG Accuracy with These Optimizations

This article walks through a complete RAG pipeline, identifying common pitfalls from document preprocessing to prompt construction, and provides concrete Python and Java examples, chunking strategies, embedding tweaks, hybrid retrieval, reranking, advanced techniques, and evaluation methods to reliably double retrieval accuracy.

EmbeddingJavaPython
0 likes · 35 min read
How I Doubled RAG Accuracy with These Optimizations
Shuge Unlimited
Shuge Unlimited
Jun 16, 2026 · Artificial Intelligence

Beyond mem0: How YC CEO’s Open‑Source AI Memory Engine Uses Regex Instead of LLMs to Power a Knowledge Graph

The article dissects GBrain, an open‑source AI memory engine from Y Combinator’s Garry Tan, showing how a dual‑engine contract, zero‑LLM regex‑based knowledge‑graph extraction, and a layered hybrid retrieval pipeline boost P@5 from ~18 to 49.1 while detailing engineering trade‑offs, batch‑write work‑arounds, weighting constants, and reliability mechanisms.

AI AgentGBrainHybrid Retrieval
0 likes · 21 min read
Beyond mem0: How YC CEO’s Open‑Source AI Memory Engine Uses Regex Instead of LLMs to Power a Knowledge Graph
Mingyi World Elasticsearch
Mingyi World Elasticsearch
Jun 7, 2026 · Artificial Intelligence

Build an Enterprise RAG Vector Search System from Scratch with LangChain, Easysearch, and MiMo

This article walks through the complete end‑to‑end pipeline for building a production‑grade RAG system—including document chunking, embedding generation via MiMo, vector storage and kNN retrieval in Easysearch, hybrid search configuration, prompt engineering, answer generation, interactive chat, and a detailed list of common pitfalls and fixes.

EasysearchKNNLangChain
0 likes · 17 min read
Build an Enterprise RAG Vector Search System from Scratch with LangChain, Easysearch, and MiMo
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Jun 4, 2026 · Big Data

Scalar‑Vector Hybrid Search in a Data Lake with One SQL on EMR Serverless Spark

EMR Serverless Spark now supports scalar‑vector hybrid search via DLF Global Index, allowing a single Spark SQL statement to perform vector similarity and scalar filtering together, eliminating data movement, reducing latency, and boosting performance for scenarios such as autonomous driving, e‑commerce, and knowledge‑base retrieval.

DLF Global IndexEMR Serverless SparkSQL
0 likes · 17 min read
Scalar‑Vector Hybrid Search in a Data Lake with One SQL on EMR Serverless Spark
PMTalk Product Manager Community
PMTalk Product Manager Community
May 30, 2026 · Product Management

5 Skills to Double an AI Product Manager’s Efficiency

The article explains why AI product managers must focus on turning AI into problem‑solving products rather than reciting jargon, outlines three development stages—from basic language understanding to retrieval‑augmented generation and autonomous agents—and shares a real‑world customer‑support case that achieved over 80% automation and a 45% boost in efficiency.

AI Product ManagementAI agentsRAG
0 likes · 8 min read
5 Skills to Double an AI Product Manager’s Efficiency
AI Engineer Programming
AI Engineer Programming
May 30, 2026 · Artificial Intelligence

Should You Pre‑filter or Post‑filter in RAG Vector Search?

The article examines RAG vector retrieval filtering strategies, comparing pre‑filtering (filter before vector search) and post‑filtering (filter after ANN search), and introduces single‑stage filtering, discussing their principles, trade‑offs, suitable scenarios, and architectural implications for accuracy and performance.

ANNRAGmetadata filtering
0 likes · 15 min read
Should You Pre‑filter or Post‑filter in RAG Vector Search?
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
May 29, 2026 · Artificial Intelligence

How Alibaba Cloud Milvus Achieves 20× Faster Billion‑Scale Vector Search with DiskANN and RaBitQ

Alibaba Cloud Milvus combines DiskANN graph indexing with the RaBitQ quantization algorithm, delivering over 20× higher QPS, sub‑10% P99 latency, 29% lower memory usage and more than 98% recall on a 100 million‑vector, 768‑dimensional benchmark, while also cutting index build time from 20 h to about 6 h.

DiskANNMilvusRaBitQ
0 likes · 7 min read
How Alibaba Cloud Milvus Achieves 20× Faster Billion‑Scale Vector Search with DiskANN and RaBitQ
James' Growth Diary
James' Growth Diary
May 23, 2026 · Artificial Intelligence

Choosing the Right Retrieval Strategy: Full‑Text vs Vector vs Graph Search

This article breaks down the underlying logic, ideal scenarios, benchmark data, decision trees, and real‑world case studies for full‑text (BM25), vector, and graph retrieval, showing why hybrid approaches dominate production while each technique has distinct strengths and trade‑offs.

Graph SearchRAGfull-text search
0 likes · 25 min read
Choosing the Right Retrieval Strategy: Full‑Text vs Vector vs Graph Search
DataFunSummit
DataFunSummit
May 21, 2026 · Big Data

Alibaba Cloud’s Agent-Ready Big Data AI Infrastructure: Boosting Data Development from Hours to Minutes

Facing a projected 85% of enterprises deploying internal agents within two years, Alibaba Cloud proposes an Agent-Ready big‑data AI infrastructure—comprising a unified data lake, real‑time processing, high‑dimensional vector retrieval, elastic model serving, and comprehensive security governance—that has already cut data‑development cycles from hours to 5‑10 minutes in internal model‑training and Taobao flash‑sale scenarios.

AISecurity Governanceagent-ready
0 likes · 15 min read
Alibaba Cloud’s Agent-Ready Big Data AI Infrastructure: Boosting Data Development from Hours to Minutes
StarRocks
StarRocks
May 20, 2026 · Big Data

How StarRocks, Paimon, and Fluss Enable Multimodal Fusion Search in a Lakehouse

The Streaming Lakehouse Meetup (May 27) explores breaking data silos by unifying structured tables, images, video, audio, and high‑dimensional vectors through StarRocks‑Paimon‑Fluss integration, covering multimodal fusion retrieval, vector search internals, native reader/writer performance gains, and real‑world ANN indexing practices.

FlussPaimonStarRocks
0 likes · 5 min read
How StarRocks, Paimon, and Fluss Enable Multimodal Fusion Search in a Lakehouse
DataFunSummit
DataFunSummit
May 20, 2026 · Databases

Apache Doris 4.1: A Unified Data Store and Retrieval Engine for AI & Search

Apache Doris 4.1 introduces a systematic evolution for AI and search workloads, adding low‑cost massive vector storage, unified structured, full‑text and vector search, 100 MB JSON document support, Segment V3 metadata decoupling, sparse column optimizations, lakehouse lifecycle management, and a suite of performance‑boosting features such as aggregate push‑down, condition cache, and spill‑to‑disk, all backed by detailed benchmark results.

AIApache DorisSQL
0 likes · 30 min read
Apache Doris 4.1: A Unified Data Store and Retrieval Engine for AI & Search
Big Data Technology & Architecture
Big Data Technology & Architecture
May 20, 2026 · Databases

Deep Dive into Apache Doris’ Multimodal Capabilities: Architecture and Enterprise Deployments

Apache Doris 4.0 introduces native vector indexes, built‑in AI functions, and hybrid search, turning the OLAP engine into an AI‑centric analytics hub; the article details the technical design, performance optimizations, and real‑world deployments at ByteDance, Squirrel AI, NetEase and a security vendor, highlighting storage savings, query speedups and reduced operational complexity.

AI FunctionsApache Dorisenterprise case study
0 likes · 19 min read
Deep Dive into Apache Doris’ Multimodal Capabilities: Architecture and Enterprise Deployments
AI Engineer Programming
AI Engineer Programming
May 20, 2026 · Artificial Intelligence

Why Chunk‑Based RAG Fails and How IdeaBlocks Improve Retrieval

The article argues that the common assumption that text chunks are the proper knowledge unit in RAG pipelines is flawed, leading to versioning, metadata, and redundancy problems, and demonstrates that replacing chunks with structured IdeaBlocks dramatically reduces corpus size, token usage, and improves vector relevance.

IdeaBlockLLMRAG
0 likes · 10 min read
Why Chunk‑Based RAG Fails and How IdeaBlocks Improve Retrieval
Tech Minimalism
Tech Minimalism
May 16, 2026 · Artificial Intelligence

One‑page guide to the three RAG architectures: Classic, Graph, and Agentic

The article explains why plain large language models cannot answer internal company questions, introduces Retrieval‑Augmented Generation (RAG) as a solution, and compares three RAG variants—Classic, Graph, and Agentic—detailing their workflows, strengths, limitations, and how to choose the right one for a given problem.

Agentic RAGGraph RAGLLM
0 likes · 17 min read
One‑page guide to the three RAG architectures: Classic, Graph, and Agentic
DeepHub IMBA
DeepHub IMBA
May 14, 2026 · Artificial Intelligence

How HyDE Transforms RAG Retrieval from Keyword Matching to Intent Understanding

The article explains how Hypothetical Document Embeddings (HyDE) improve Retrieval‑Augmented Generation by generating a synthetic answer before vector search, allowing the system to embed richer semantic intent rather than relying on shallow keyword similarity, and provides a step‑by‑step implementation using LangChain.

HyDELLMLangChain
0 likes · 6 min read
How HyDE Transforms RAG Retrieval from Keyword Matching to Intent Understanding
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
Amazon Cloud Developers
Amazon Cloud Developers
May 6, 2026 · Artificial Intelligence

How JoyCastle Accelerated a 100k+ Ad Asset Library with Amazon Nova Multimodal Embeddings

JoyCastle faced a growing ad‑asset library that slowed creative production, so it built an AI‑powered management system using Amazon Nova Multimodal Embeddings, achieving unified semantic search, automatic video segmentation, 96.7% recall and a 73.3% top‑2 precision while reducing manual labeling effort.

AWSAmazon NovaGame Advertising
0 likes · 13 min read
How JoyCastle Accelerated a 100k+ Ad Asset Library with Amazon Nova Multimodal Embeddings
Linyb Geek Road
Linyb Geek Road
May 5, 2026 · Artificial Intelligence

Optimizing Retrieval and Generation Latency in High‑Concurrency RAG Agents

The article dissects latency in high‑concurrency RAG Agent pipelines, showing how retrieval, re‑ranking, and LLM generation each contribute milliseconds of delay, and presents system‑level tactics—from ANN index tuning and partitioned search to vLLM PagedAttention, continuous batching, speculative decoding, model quantization, routing, semantic caching, and pipeline parallelism—to dramatically cut end‑to‑end response time.

ANNLLMRAG
0 likes · 15 min read
Optimizing Retrieval and Generation Latency in High‑Concurrency RAG Agents
Spring Full-Stack Practical Cases
Spring Full-Stack Practical Cases
May 3, 2026 · Artificial Intelligence

9 Advanced Retrieval‑Augmented Generation (RAG) Architectures Explained

This article introduces Retrieval‑Augmented Generation (RAG) and systematically details nine distinct RAG architectures—standard, conversational with memory, corrective (CRAG), adaptive, self‑RAG, fusion, HyDE, agentic, and Graph RAG—highlighting their workflows, real‑world examples, advantages, and trade‑offs.

AI ArchitectureGraphRAGLLM
0 likes · 17 min read
9 Advanced Retrieval‑Augmented Generation (RAG) Architectures Explained
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
May 1, 2026 · Artificial Intelligence

Zero Deployment, Zero Ops: Alibaba Cloud Milvus Embedding Service Makes Vectorization Plug‑and‑Play

The article explains how Alibaba Cloud's Milvus Embedding Service eliminates the need for self‑hosted embedding models by integrating model inference, vector generation and Milvus indexing into a managed pipeline, dramatically reducing deployment complexity, operational overhead, and time‑to‑value for semantic search, RAG and multimodal retrieval use cases.

Alibaba CloudEmbeddingMilvus
0 likes · 19 min read
Zero Deployment, Zero Ops: Alibaba Cloud Milvus Embedding Service Makes Vectorization Plug‑and‑Play
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
AI Architect Hub
AI Architect Hub
Apr 30, 2026 · Artificial Intelligence

How AI Understands Your Queries: Core Techniques of Semantic Vector Search

The article explains why traditional keyword search often fails when user questions differ from knowledge‑base wording, introduces semantic search that matches queries and documents via vector similarity, details query understanding and rewriting techniques, lists common pitfalls, provides a full Python implementation, and shares best‑practice recommendations.

AIPythonRAG
0 likes · 16 min read
How AI Understands Your Queries: Core Techniques of Semantic Vector Search
Architect's Tech Stack
Architect's Tech Stack
Apr 29, 2026 · Databases

Redis 8.0 Beyond Simple Caching: 16 Powerful Use Cases You Must Try

Redis 8.0 consolidates many previously external modules—JSON, time‑series, vector search, probabilistic data structures, and more—into a single package, and this article walks through 16 concrete scenarios ranging from field‑level cache expiration to AI‑ready vector similarity search, showing exact commands and when to prefer each feature.

LeaderboardRedis 8.0caching
0 likes · 19 min read
Redis 8.0 Beyond Simple Caching: 16 Powerful Use Cases You Must Try
AI Architect Hub
AI Architect Hub
Apr 27, 2026 · Artificial Intelligence

Why HNSW Can Speed Up Search 50× Compared to Brute‑Force? A Hands‑On Guide to Building Vector Indexes

The article explains why brute‑force vector search is painfully slow, introduces Flat, IVF, and HNSW index structures, compares their speed, memory and accuracy, shows common pitfalls, provides production‑grade Python code, and presents benchmark results that demonstrate HNSW’s superior speed‑accuracy trade‑off.

AIFaissHNSW
0 likes · 12 min read
Why HNSW Can Speed Up Search 50× Compared to Brute‑Force? A Hands‑On Guide to Building Vector Indexes
The Dominant Programmer
The Dominant Programmer
Apr 27, 2026 · Artificial Intelligence

Building a Private Document Vector Search with SpringBoot, LangChain4j, and Ollama RAG

This guide walks through why Retrieval‑Augmented Generation (RAG) is needed for large language models, explains the three‑step indexing and query workflow, details LangChain4j’s core components, and provides a complete SpringBoot example—including Maven setup, configuration, service code, and troubleshooting—to create a private document‑vector search system powered by Ollama.

EmbeddingLangChain4jOllama
0 likes · 13 min read
Building a Private Document Vector Search with SpringBoot, LangChain4j, and Ollama RAG
dbaplus Community
dbaplus Community
Apr 26, 2026 · Databases

Why PostgreSQL Is the Better Choice in 99% of Scenarios

The article argues that relying on many specialized databases creates operational complexity, higher costs, and maintenance overhead, while PostgreSQL’s extensible ecosystem—offering full‑text search, vector, time‑series, JSONB, and more—delivers comparable or superior algorithms, proven performance, and a simpler, more reliable stack for the vast majority of use cases, especially in AI applications.

AIPostgreSQLdatabase
0 likes · 19 min read
Why PostgreSQL Is the Better Choice in 99% of Scenarios
AI Engineer Programming
AI Engineer Programming
Apr 25, 2026 · Artificial Intelligence

Quantization Across Signal Processing, AI Inference, and RAG Vector Search

This article explains how quantization—originating from signal processing—reduces precision to save resources, details its application to neural network weights and activations via PTQ, QAT, GPTQ, AWQ, and SmoothQuant, and shows how vector quantization enables fast, memory‑efficient retrieval in large‑scale RAG systems.

AWQGPTQLLM
0 likes · 19 min read
Quantization Across Signal Processing, AI Inference, and RAG Vector Search
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
James' Growth Diary
James' Growth Diary
Apr 21, 2026 · Artificial Intelligence

Boosting RAG Performance with Milvus: Chunking, Hybrid Search, and Rerank Best Practices

This article analyzes why Retrieval‑Augmented Generation often underperforms, then walks through concrete engineering steps—optimal chunking, overlap settings, hybrid vector + BM25 retrieval, RRF fusion, and reranking—while providing code snippets, parameter tables, and a full pipeline diagram to turn a usable RAG system into a high‑quality one.

LangChainMilvusRAG
0 likes · 18 min read
Boosting RAG Performance with Milvus: Chunking, Hybrid Search, and Rerank Best Practices
AI Engineer Programming
AI Engineer Programming
Apr 21, 2026 · Artificial Intelligence

From Bag‑of‑Words to Semantic Vectors: Understanding Embeddings and Similarity Search (Part 1)

The article explains how diverse data can be represented as high‑dimensional vectors, describes exact and approximate nearest‑neighbor search, explores vector quantization, product quantization, locality‑sensitive hashing, and HNSW graphs, and analyzes their speed, accuracy, and memory trade‑offs for large‑scale similarity retrieval.

HNSWLSHembeddings
0 likes · 16 min read
From Bag‑of‑Words to Semantic Vectors: Understanding Embeddings and Similarity Search (Part 1)
Linyb Geek Road
Linyb Geek Road
Apr 20, 2026 · Artificial Intelligence

How to Choose the Right Embedding Model for RAG Architectures

This article explains why embedding models are the foundation of Retrieval‑Augmented Generation, outlines five evaluation dimensions, compares leading open‑source and commercial models, provides a decision tree, practical validation steps, common pitfalls, and future trends to help developers select the most suitable embedding model for their RAG system.

EmbeddingMTEBRAG
0 likes · 10 min read
How to Choose the Right Embedding Model for RAG Architectures
Mingyi World Elasticsearch
Mingyi World Elasticsearch
Apr 19, 2026 · Industry Insights

ElasticStack 2026: Beyond New Versions, It’s Becoming an Agent Platform

In early 2026 ElasticStack transformed from a traditional search‑log‑visualization stack into an Agent platform, accelerating releases across three lines, elevating Elasticsearch to a context‑engineered infrastructure, unifying ES|QL as a platform‑wide interaction layer, and integrating Workflows, MCP, and vector enhancements to drive autonomous observability and security operations.

ElasticStackElasticsearchMCP
0 likes · 20 min read
ElasticStack 2026: Beyond New Versions, It’s Becoming an Agent Platform
DataFunTalk
DataFunTalk
Apr 18, 2026 · Databases

How Will Apache Doris Evolve in 2026 to Power AI‑Driven Data Workloads?

The article outlines Apache Doris's 2026 roadmap, detailing how the database will shift from pure analytics to a unified AI‑enabled platform with enhanced semi‑structured data support, vector and hybrid search, agent‑focused capabilities, and expanded storage and lakehouse integrations to meet emerging AI workloads.

AI IntegrationApache DorisDatabase Roadmap
0 likes · 14 min read
How Will Apache Doris Evolve in 2026 to Power AI‑Driven Data Workloads?
DataFunSummit
DataFunSummit
Apr 17, 2026 · Artificial Intelligence

Why RAG Projects Fail: Real‑World Pitfalls and Proven Solutions

This article dissects the hype‑versus‑reality gap of Retrieval‑Augmented Generation in enterprises, exposing low recall, hallucinations, and cost overruns, then offers a systematic diagnosis, hybrid search, reranking, security controls, and advanced GraphRAG and Agentic RAG strategies to achieve reliable production deployments.

Best PracticesEnterprise AILLM
0 likes · 17 min read
Why RAG Projects Fail: Real‑World Pitfalls and Proven Solutions