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.
The article examines how Alibaba Cloud OSS Vector Bucket solves the data‑scattered, costly, and inefficient retrieval problems of massive multimodal media asset platforms by unifying storage, providing semantic vector search, and cutting operational expenses up to 95%.
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.
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.
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.
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.
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.
The paper presents a CCD‑level load‑aware thread orchestration framework that boosts vector ANNS throughput up to 3.7×, cuts P999 tail latency by 30%‑90%, reduces L3 cache miss rates by 6%‑30% and CPU stall time by 20%‑80% on AMD EPYC multi‑chiplet CPUs.
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.
The article examines why pure vector retrieval in RAG lacks lexical precision and traceable relevance scores, explains BM25's strengths, and presents hybrid retrieval architectures—including RRF and linear combination fusion—as well as the trade‑offs of externalizing the fusion process.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
The open‑source Cognee project lets developers give AI agents a dynamic, long‑term memory by combining vector search, graph databases and cognitive techniques, and it can be set up with only six lines of Python code, as demonstrated with a quick‑start example.
This guide explains how to dramatically reduce latency for batch semantic search, RAG multi‑path retrieval, and multimodal vector queries by running multiple OSS Vectors embed requests in parallel using CLI‑based, xargs, shell background jobs, Python asyncio, and SDK‑level concurrency techniques.
This article explains why vector databases are needed for semantic search of unstructured data and provides a detailed, step‑by‑step comparison of three core vector similarity algorithms—cosine similarity, Flat Index, IVF, and HNSW—highlighting their trade‑offs in accuracy and speed.
The article compares Easysearch and Elasticsearch vector‑search capabilities, showing that both support vector queries but use different field types and DSL structures, and it outlines migration pitfalls and practical advice for choosing the right system.
This article dissects the shortcomings of pure vector retrieval, explains how BM25 complements it, compares weighted‑sum and Reciprocal Rank Fusion (RRF) strategies, shows experimental results that identify optimal weight and k values, and provides practical engineering tips for deploying hybrid search in RAG systems.
Oracle’s 2026 AI database rollout fuses vector search, private AI agents, unified memory, and deep data security directly into the database engine, challenging the cloud‑centric data‑movement paradigm and prompting a market shift that could revive Oracle’s dominance while reshaping strategies for DBAs, AI engineers, and decision makers.
This comprehensive guide explains how to design, implement, and operate a production‑ready Retrieval‑Augmented Generation (RAG) platform using Spring AI and PostgreSQL PGVector, covering architecture, indexing, hybrid retrieval, prompt engineering, scaling, security, observability, deployment, and common pitfalls for enterprise knowledge‑base applications.
This guide walks through setting up Alibaba Cloud OSS Vector Buckets, installing the necessary SDKs, uploading image datasets, creating vector indexes, generating embeddings with the Bailei multimodal model, writing vectors, performing semantic searches, and visualizing results via a Gradio web UI.
This guide introduces PHPVector, a pure‑PHP vector database that combines HNSW‑based approximate nearest‑neighbor search with BM25 full‑text ranking, showing installation, document insertion, vector and text queries, hybrid ranking modes, configuration options, distance metrics, tuning tips, and persistence mechanisms.
This article explains how the combination of Hologres, a unified real‑time data warehouse, and Mem0, an open‑source LLM memory framework, overcomes the limited context window of large language models by providing scalable, low‑latency, and cost‑effective long‑term memory for AI applications.
The article explains two emerging RAG query‑optimization approaches—query translation and query decomposition—detailing fan‑out retrieval, reciprocal rank fusion, HyDE, step‑back prompting, and chain‑of‑thought retrieval, and shows how combining them can improve relevance and latency in LLM‑augmented systems.
The article analyzes the limitations of current AI coding agents—narrow perception, fragmented knowledge, and missing high‑dimensional context—and presents an Engineering Knowledge Engine that integrates vector retrieval, code and commit graphs, RepoWiki, memory, and Agentic Search to provide structured, evolving context, dramatically improving task success, token efficiency, and code quality.
The article dissects a failed Alibaba second‑round interview where the candidate answered only “vector‑search‑enhanced” for a RAG design, and then presents a systematic, four‑module RAG architecture together with six design principles, detailed indexing, query understanding, multi‑path recall, and context generation techniques to help candidates demonstrate comprehensive technical depth.
The article examines how retrieval‑augmented generation suffers from poor query formulation and presents two advanced strategies—query translation, which generates multiple semantically similar variants, and query decomposition, which breaks complex questions into finer sub‑queries—detailing methods such as fan‑out retrieval, reciprocal rank fusion, HyDE, step‑back prompting, and chain‑of‑thought retrieval, and explains when to combine them.
This article walks through building a practical Elasticsearch demo that lets users type a single query like “nearby clean coffee shop” and get results by combining dense‑vector semantic search, geo filtering, BM25, and a hybrid RRF‑style ranking, with both LLM‑based structuring and a fallback hash‑based embedding.
Google’s Gemini Embedding 2 introduces a native multimodal embedding model that maps text, images, video, audio, and documents into a single vector space, offers three configurable dimensions, achieves state‑of‑the‑art benchmarks across modalities, and enables cross‑modal search, RAG, and seamless integration with major vector databases.
This article explains how Lance's Python API creates scalar and vector indexes, walks through the internal Rust implementation of the create_index workflow, and details the transaction, commit, and error‑handling mechanisms that ensure atomic and consistent index creation.
This article dissects why naive Retrieval‑Augmented Generation (RAG) often yields only 60% accuracy, then presents eleven concrete ingestion, query, and hybrid techniques—complete with code samples, performance trade‑offs, and real‑world case studies—that together can raise RAG accuracy to 94% while outlining practical implementation roadmaps and common pitfalls.
The article surveys emerging vector databases, explains how various vector‑search algorithms such as FLAT, IVF, HNSW, DiskANN and ScaNN differ in accuracy, speed, memory use and build time, and provides practical guidance for choosing the right index based on data size, latency and resource constraints.
The Taobao‑Tmall customer operations team built an integrated vector‑plus‑full‑text retrieval solution on Hologres, achieving millisecond‑level recall for massive unstructured knowledge bases, boosting intelligent客服, rule comparison, and sentiment analysis across multiple business scenarios.
ByteHouse, ByteDance's cloud‑native data warehouse, evolves from a traditional warehouse to a next‑generation AI‑ready platform that handles 800+ PB of data, supports 25,000 nodes, and delivers real‑time, multimodal analytics through a decoupled storage‑compute architecture, AI‑driven query optimization, and native vector search integration.
Redis introduces a multithreaded query engine that keeps average latency under 10 ms while delivering up to 16× higher throughput for vector‑search workloads, enabling faster retrieval‑augmented generation (RAG) applications and outperforming pure vector databases and managed Redis services in benchmark tests.
This article outlines five practical engineering strategies—multi‑vector retrieval, manual splitting and labeling, scalar enhancement, context augmentation, and dense‑sparse vector integration—that together address common RAG retrieval bottlenecks and dramatically improve recall stability and answer quality.
This article explains how to use Redis 8.4.0 for vector recall and keyword filtering, covering index selection (FLAT vs HNSW), schema creation with redisvl, full‑text BM25 search, pure KNN vector queries, hybrid text‑plus‑vector retrieval, query cleaning, score fusion, and optional in‑Redis Lua re‑ranking or TAG‑based filtering extensions.
Clawdbot implements a fully local, persistent memory system for LLM agents by storing context and long‑term knowledge in editable Markdown files, indexing them with SQLite‑vec and FTS5, supporting multi‑agent isolation, compression, pruning, and configurable session lifecycles to maintain efficient, cost‑effective interactions.
This article details a lightweight, CPU‑only knowledge‑base retrieval experiment that uses Qwen3‑Embedding‑0.6B to vectorize Chinese poetry, stores vectors in Redis with HNSW indexing, and implements a hybrid keyword‑plus‑vector search pipeline with configurable weighting and performance optimizations.
The article outlines the evolution from traditional OLAP to an AI‑first Lakehouse, detailing unified multimodal storage, CPU/GPU heterogeneous scheduling, native vector search, in‑database AI inference, agent‑centric execution, and self‑evolving platform capabilities that together reshape modern data analytics.
This case study details how a major internet visual platform consolidated its log, keyword, and vector search workloads onto Alibaba Cloud Elasticsearch, eliminating three separate pipelines, reducing write‑costs by 60%, cutting storage expenses over 60%, and achieving multi‑fold performance gains through serverless scaling, FalconSeek engine optimizations, and unified monitoring.
This article explains the definitions, differences, and integration trends of Knowledge Bases and Knowledge Graphs within Retrieval‑Augmented Generation, helping developers decide which technology best fits their AI system requirements.
The article examines how PostgreSQL’s latest pgvector 0.8.0 release adds iterative index scans and smart query planning, enabling fully free vector search within an existing relational database, compares performance, cost, and architecture against dedicated vector databases like Pinecone, and outlines migration steps and best‑practice guidelines.
This article walks through the strengths, typical use cases, and Python connection code for relational databases (MySQL, PostgreSQL, SQLite), NoSQL stores (MongoDB, Redis, Neo4j), cloud‑native options (DynamoDB), and emerging vector databases such as Milvus, helping you decide which fits your project.
This article explains how high‑dimensional vectors enable semantic AI search, compares exact and approximate nearest‑neighbor algorithms, examines the challenges of large‑scale vector storage, and evaluates AWS S3 Vectors' architecture, pricing, and hybrid solutions for cost‑effective, high‑performance retrieval.
This article details how an automotive AI assistant migrated from keyword matching to a Milvus‑based vector retrieval system, overcoming semantic gaps, scaling to millions of daily queries, optimizing indexing, introducing multi‑vector and sparse‑vector search, and building a real‑time RAG pipeline with Flink.
Pixeltable introduces a unified table abstraction that treats images, text, embeddings and model outputs as columns, enabling declarative multimodal AI pipelines, eliminating glue code, supporting built‑in vector indexing, versioned experiments, extensible custom functions, and a concise 30‑line RAG implementation.
The article reviews MongoDB 8.2’s major upgrades, highlighting up to 36% read throughput gains, 59% write speed improvements, 200% faster time‑series aggregation, 50‑fold faster shard rebalancing, enhanced queryable encryption, native vector search, multi‑cloud Atlas support, and AI‑driven capabilities such as hybrid search and the MongoDB AMP platform.
This article explains why dynamic Retrieval‑Augmented Generation (RAG) requires a layered caching strategy rather than simple result caching, details a four‑level cache architecture—including embedding, search, answer, and pipeline caches—provides practical key‑generation and TTL guidelines, and outlines dirty‑data defenses to keep caches consistent and performant.
This guide introduces SeekDB, an AI‑native embedded database that unifies vector, text, and structured search, walks through installation with uv, shows a complete Python demo, and shares practical pros, cons, and usage tips for developers.
ClickHouse 25.10 introduces a suite of enhancements—including 20 JOIN performance upgrades, lazy column replication, Bloom filter runtime filters, disjunction push‑down, automatic column statistics, the QBit vector type, expanded SQL operators, negative LIMIT/OFFSET, Arrow Flight support, and delayed secondary index materialization—backed by detailed benchmarks and contributor acknowledgments.
This article explains how unstructured multimedia data is transformed into vectors for similarity search, introduces GPU parallelism and the NN‑Descent algorithm to replace traditional HNSW indexing in OpenSearch, and presents benchmark results showing up to a thirteen‑fold speed improvement while maintaining comparable recall.
This article explains how to give AI agents persistent memory, reflection, and goal‑tracking by storing interaction summaries in SQLite, embedding them for semantic retrieval with a vector database, and using LLM‑generated prompts to recall, reflect, and manage objectives across sessions.
This article explains how integrating the disk‑based DiskANN index with the ultra‑compact RaBitQ quantization dramatically boosts Milvus's vector search performance and cuts costs, delivering over five times higher QPS and more than 90% cost reduction for billion‑scale AI workloads.
This article explains Retrieval‑Augmented Generation (RAG), an AI framework that combines external knowledge retrieval with large language models, covering its motivations, data preparation, chunking strategies, vectorization, storage, query processing, retrieval, reranking, prompt engineering, and LLM generation, plus practical optimization tips.
While MySQL has long dominated relational databases with its open‑source stability and massive user base, the rise of AI and PostgreSQL’s extensible ecosystem—highlighted by extensions like pgvector, pg_bm25, TimescaleDB and PostGIS—are shifting developer preference, as shown by the 2025 Stack Overflow survey.
This article walks through MindsDB’s Knowledge Base feature, showing how to map data sources, create vector indexes, perform semantic search, combine multiple sources with SQL joins, automate updates via jobs, and construct powerful RAG pipelines and Data Agents for AI‑driven query answering.
The article provides a detailed technical analysis of RAGFlow's search engine, covering the Searcher class coordination, adaptive multi‑path retrieval (vector, keyword, and knowledge‑graph), intelligent fusion with weighted scoring, caching, performance monitoring, and both built‑in and model‑driven reranking to achieve high‑precision results.
MySQL AI, introduced for the database's 30th anniversary, integrates auto‑ML, generative AI, LLM‑driven text‑to‑SQL, and a vector engine directly into MySQL Enterprise, enabling developers to build intelligent applications on familiar SQL tools without moving data.
Redis 8.0, released on May 1, 2025, introduces a major license shift to AGPLv3, eight new native data structures—including vector sets, JSON, and time‑series—alongside a rebuilt query engine that delivers up to 16‑fold performance gains, enhanced security, and cloud‑native capabilities.
This article explores the evolving search demands of the intelligent era, explains dense and sparse vector concepts, details Elasticsearch's vector search capabilities and recent performance breakthroughs, introduces hybrid and relevance‑tuning techniques, and demonstrates RAG principles and real‑world enterprise use cases.
At DTCC2025 in Beijing, industry leaders showcased AI-driven innovations, vector database advances, RAG techniques, and distributed database performance breakthroughs, illustrating how databases are evolving from passive data stores into intelligent, autonomous systems that boost efficiency, scalability, and business value across sectors.
This tutorial explains how to use Milvus 2.5's new full‑text, BM25 keyword matching, and hybrid search capabilities—including step‑by‑step setup, schema design, code examples, and RAG integration—to achieve high recall and precision in large‑scale AI vector retrieval scenarios.
This article answers practical questions about enterprise semantic search, explaining how Reciprocal Rank Fusion normalizes mixed scoring, how to control vector result size, the trade‑offs of LSH parameters, word‑ and sentence‑based chunking strategies with version‑specific defaults, and flexible embedding dimensionality.
This article explains how PolarDB IMCI integrates vector indexing and embedding directly into the database kernel, offering a unified, transactional, and real‑time vector lifecycle management service that lets developers build RAG knowledge bases and AI applications using only standard SQL, dramatically reducing development and operational complexity.
The article analyzes the semantic gap in e‑commerce search, compares traditional keyword matching with vector‑based retrieval, and provides a step‑by‑step implementation using Elasticsearch/Easysearch pipelines, embedding models, and a hybrid search strategy to improve user intent understanding.
This article describes how a video review system combines multimodal CLIP models, image‑text feature alignment, and optimized vector‑search databases such as RedisSearch and Elasticsearch to detect prohibited content in real time and perform large‑scale historical recall, while addressing challenges of generalization, storage cost, and inference speed.
The video walks through the differences between traditional keyword search and vector search, explains the core concept of Retrieval‑Augmented Generation, and demonstrates how to construct a knowledge‑base Q&A system using a large language model integrated with Elasticsearch.
This article explains why traditional keyword search falls short, introduces Elasticsearch's vector search and hybrid retrieval capabilities, and shows how combining it with large language models enables Retrieval‑Augmented Generation (RAG) for more accurate, context‑aware AI-driven search across text and multimedia data.
This article explains a system that combines large language models with multimodal vector retrieval to automatically understand user intent and instantly recommend the most relevant icons, detailing the workflow, semantic vectorization, offline indexing, online inference, and evaluation methods.
This article explains how Elasticsearch supports vector search through three field types—semantic_text, dense_vector, and sparse_vector—detailing their definitions, ideal use cases, query syntax, advantages, limitations, and guidance for selecting the right type in real‑world search applications.
This guide explains how to use Alibaba Cloud Milvus to create a scalable, high‑performance multimodal search system that supports text‑to‑image, image‑to‑image, and cross‑modal queries across various business scenarios, detailing architecture, deployment steps, validation, and resource cleanup.
This article explores DeepSeek's open‑source large‑model breakthroughs, PingCAP's AI‑enhanced database roadmap, TiDB.AI's retrieval‑augmented generation framework, the unified TiDB data engine, and practical Q&A insights on knowledge‑graph construction, vector search, and AI‑driven SQL generation.
This guide explains how to use Alibaba Cloud DataWorks to create the necessary resources, configure Milvus and MaxCompute data sources, set up an offline single‑table synchronization task, and verify the imported vectors, enabling efficient AI‑driven vector search on large structured datasets.
The paper introduces SOGAIC, a scalable overload‑aware graph‑based index construction system for billion‑scale vector similarity search that uses adaptive overlapping partitioning and load‑balanced distributed scheduling to cut construction time by 47.3% while maintaining high recall.
This article explains the principles of vector search, compares Easysearch's approximate (LSH) and exact kNN APIs, and walks through a complete hands‑on example using Stanford's 50‑dimensional GloVe embeddings to index, import, and query semantically similar words.
Redis 8.0, released on May 1 2025, introduces a major license shift to AGPL‑v3, adds eight native data structures—including vector sets, JSON, and time‑series—enhances the query engine with up to 16× performance gains, improves scalability, security, and cloud‑native support, and provides extensive code examples for AI and real‑time analytics.
This tutorial walks through building a Retrieval‑Augmented Generation (RAG) system by combining LangChain for document processing, Elasticsearch’s vector store with the ELSER v2 model for semantic search, and Higress as a cloud‑native AI gateway, complete with deployment scripts, code examples, and query testing.
蝉妈妈 migrated its recommendation platform to Alibaba Cloud Serverless Spark and Milvus, replacing traditional vector search and Spark clusters, achieving 40% faster offline tasks, 80% lower failure rates, significant cost savings, and scalable, low‑latency similar‑product retrieval for personalized marketing.
This article presents a hands‑on evaluation of several large language models—including Mistral‑Small, Deepseek‑r1, Llama 3.3 and ChatGPT‑4‑go—on Oracle database bad‑block errors, RAG‑based document retrieval, and log‑driven reasoning, revealing performance gaps, scoring results, and practical DBA implications.
This article explains how semantic enrichment, vector retrieval, hybrid search, and clustering can be combined to evaluate large language model inputs and outputs, improve debugging, ensure compliance, and enhance user intent understanding in AI applications.
This guide explains how Dify visualizes RAG pipelines, lets developers upload and structure documents, choose segmentation modes, configure indexing and retrieval settings, and leverage embeddings and vector search to build fast, accurate, and up‑to‑date AI knowledge bases.
This article explains how semantic enrichment, vector and hybrid search, and clustering techniques can be applied to large language model logs to evaluate inputs and outputs, improve compliance auditing, and enhance model iteration across various business scenarios.
The article explains how Redis vector search, powered by RedisSearch’s FLAT and HNSW algorithms and supporting various data types and precisions, enables fast AI-driven similarity queries for text, image, and audio, and provides implementation guidance, optimization tips, and a real‑world customer‑service use case.
This article explains Elasticsearch's dense_vector field for storing dense vectors, covering its definition, how to define and index vectors, kNN search methods (brute‑force and approximate with HNSW), similarity options, quantization strategies, bit‑vector support, key parameters, and how to update mappings.
