This article explains Reciprocal Rank Fusion (RRF) for merging Elasticsearch sparse retrieval and Milvus vector retrieval scores in RAG systems, covering standard vs weighted RRF, the smoothing constant k, static weight configuration principles, and dynamic weight adjustment via intent classification and slot extraction.
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.
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.
Taotian Group built a unified product knowledge base using Milvus for vector retrieval of FAQs and product wikis, enabling AI shopping guides to answer consumer questions with business-scoped semantic search across store, product, and SKU metadata.
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.
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.
This tutorial explains vector databases from fundamentals to production: representing data as vectors, embedding models for semantic search, ANN algorithms like HNSW and IVF, hands-on ChromaDB demo for RAG, and comparison of production databases Milvus, Qdrant, Pinecone, and Weaviate with common pitfalls.
This article explains the Milvus 3.0 deletion pipeline from request to disk space reclamation, covering tombstone creation, query visibility via bitmaps, L0 segment materialization, two-phase compaction, and GC tolerance windows that delay space return by hours.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
The article outlines ten critical capabilities required for Frontline Deployment Engineers (FDE) to successfully deliver AI projects, covering business research, problem breakdown, scenario judgment, solution design, rapid demo, data preparation, system integration, process orchestration, security governance, and impact review, emphasizing end-to-end delivery from vague requirements to measurable business value.
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.
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.
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.
The article dissects Milvus 3.0's Function Chain, explaining how fine‑grained ranking is moved into the engine with a two‑stage L0 early‑prune and L2 post‑reduction design, native XGBoost scoring, typed protobuf pipelines, and the trade‑offs revealed by source‑code analysis and community discussions.
The author shares hands‑on experiences with Milvus, pgvector, and Qdrant, detailing performance at different data scales, index trade‑offs, operational complexity, and provides practical guidance on selecting the most suitable vector database for a RAG system.
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.
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.
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.
Milvus 3.0 replaces the dual‑track write path of 2.x with a unified WAL‑first design, introduces a three‑layer channel model (PChannel, VChannel, CChannel) and a five‑layer interceptor chain, adds the Woodpecker WAL that outperforms Kafka/Pulsar by up to 5.8×, and provides pluggable back‑ends, atomic broadcasting, and provable recovery mechanisms.
The article dissects Milvus 3.0's storage overhaul, explaining why the legacy per‑column binlog layout (V1) and the packed Parquet format (V2) were replaced by the Loon manifest table (V3), and how this redesign enables external collections, zero‑copy Spark reads, and efficient TEXT LOB handling.
Under a fixed monthly budget of about 7,100 CNY, Volcano Milvus combines DiskANN and RaBitQ (including Extended‑RaBitQ) with in‑memory layout and query‑path slimming to deliver 20,420 QPS, 2.5 ms average latency, 93.9 % recall, achieving nearly three times the VectorDBBench top score while using roughly one‑third of the memory, disk and compute resources of competing solutions.
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.
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.
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.
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.
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.
Hybrid search combines dense vector retrieval with sparse keyword search, using RRF fusion and optional reranking, to overcome the limitations of each method—semantic understanding versus exact matching—making it the production‑grade standard for RAG systems by 2025‑2026.
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.
This article explains why Retrieval‑Augmented Generation is needed, compares popular vector databases, provides step‑by‑step Docker and Python examples for Chroma, Pinecone, and Milvus, and shows how to optimize a full RAG agent with hybrid search, reranking, and caching.
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.
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.
This article walks through the design, environment setup, code structure, and core pipelines of an enterprise‑grade AI OnCall Agent that combines RAG‑based knowledge retrieval with a Plan‑Execute‑Replan workflow to provide automated alert handling, intelligent Q&A, and operational analysis.
In an urgent backend project, the author used Claude Code (GML‑5.1) with Go and go‑zero to generate documentation, integrate Milvus, design a vector table, and add embedding support, spending 200k‑300k tokens for about 2‑3 CNY, while discussing speed bottlenecks, workflow choices, and practical tips for parallelism and mode configuration.
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.
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 provides a source‑code level analysis of Milvus Vector Transport Service (VTS), detailing its three‑stage architecture, partition‑aware sharding logic, two distinct sink write mechanisms (BufferBatchWriter and BulkWriter), schema conversion rules, error‑handling strategies, performance tuning parameters, and practical configuration examples for efficient vector data migration across various data sources.
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.
This article breaks down why RAG pipelines often underperform and shows how proper chunking, overlap settings, hybrid vector‑plus‑BM25 retrieval, and a Rerank step can dramatically improve recall and precision, with concrete code examples and tuning tips.
This article walks through deploying Milvus with Docker Compose, creating a persistent collection, tuning HNSW indexes, integrating LangChain.js for semantic retrieval, and covering performance tips and common pitfalls to run a production‑grade vector database.
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 why RAG storage must be layered, describes the four data types involved, presents a typical three‑layer architecture with vector, content, and metadata stores, and shows how the design evolves with scale, multi‑level indexing, update handling, and tenant isolation.
This article explains what vectors are, why traditional relational databases struggle with high‑dimensional similarity queries, and how the open‑source Milvus vector database efficiently stores, indexes, and retrieves massive vectors for AI applications such as semantic search, image matching, and recommendation.
This article dissects Zilliz’s Milvus Skill and Zilliz Cloud Skill, showing how a modular set of reference files teaches AI agents to generate pymilvus Python code for vector databases and to operate Zilliz Cloud via CLI, while comparing their architecture, security design, and ecosystem role.
This article explains why AI agents need a structured memory module, outlines three memory types from cognitive science, details short‑term and long‑term storage architectures using vector databases, and provides concrete code and management strategies—including conflict resolution, TTL expiration, and privacy compliance—to build a robust Agent Memory system.
This article breaks down the end‑to‑end retrieval function used in a RAG system, detailing each of the five stages—from request construction, hybrid vector + BM25 search, RRF fusion, cross‑encoder reranking, to threshold filtering—and provides concrete Python code, parameter choices, and performance insights.
This article analyzes Milvus—its open‑source origins, three deployment modes, four‑layer architecture, eight‑plus indexing algorithms, real‑world case studies, and a detailed comparison with competitors—highlighting its strengths, weaknesses, common pitfalls, and when it’s the right choice for large‑scale AI workloads.
This article walks through the real‑world pain points of monitoring dozens of Milvus collections across multiple clusters, then details a Python‑based Skill that automates connection handling, aggregates collection metadata, evaluates index health with a three‑state model, and provides unified health checks, performance testing, and capacity analysis for reliable large‑scale vector database operations.
This article details an end‑to‑end AI system that replaces manual, error‑prone tagging of customer dialogues with a large‑language‑model‑driven, vector‑based pipeline that automatically discovers, clusters, and iteratively refines business‑level tags, dramatically cutting cycle time and improving coverage.
This article explains why vector databases are essential for AI-driven unstructured data, surveys the current landscape of professional and extended vector databases, and provides a detailed technical comparison between Milvus and OceanBase, covering architecture, features, performance, and product positioning.
This article explains the core concepts of vector database indexing, details the composition of Milvus indexes—including data structures, quantization methods, and specific algorithms like IVF, HNSW, DISKANN, PQ, RABITQ, PRQ, SCANN, AISAQ, and MINHASH_LSH—and offers speculation on future developments.
This article explains Milvus's multi‑tenant architecture, covering its layered data structures, role‑based access control, resource‑group based physical isolation, practical code examples, and future directions for cost‑effective, cloud‑native vector database deployments.
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.
This guide introduces Milvus, an open‑source vector database for AI workloads, outlines its key features and common use cases, and provides step‑by‑step Docker‑Compose commands to set up Milvus, its storage backend MinIO, and the Attu management UI.
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 how Mem0 provides a durable memory layer for AI agents, enabling them to recall past interactions, store user preferences, and continuously improve by integrating with Milvus vector databases and graph stores, complete with step‑by‑step code examples and performance comparisons.
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 explains how to combine Alibaba Cloud Milvus, a high‑performance vector database, with the low‑code workflow platform n8n to create an enterprise‑level, domain‑specific intelligent Q&A system, covering challenges, architecture, setup, workflow configuration, and verification steps.
This article explains how TAL Education leverages the open‑source Milvus vector database—covering its architecture, features, cloud‑native deployment, monitoring, and real‑world AI applications such as intelligent grading and multimodal search—to handle billions of vectors with millisecond‑level similarity retrieval.
This article explores the evolution, architecture, and operational challenges of vector databases like Milvus and Zilliz, comparing them with traditional databases, detailing indexing strategies such as HNSW and DiskANN, migration plans, performance benchmarks, and future directions for large‑scale AI‑driven search systems.
This guide explains how to combine Alibaba Cloud Milvus, a high‑performance vector database, with the low‑code AI platform Dify to create an enterprise‑level Retrieval‑Augmented Generation (RAG) application, covering architecture, installation, data ingestion, and verification steps.
This guide walks through creating a Spring Boot 3 application that loads web pages into a vector database using Spring AI, configures AI models and embeddings, and exposes REST endpoints for storing documents and answering queries with retrieval‑augmented generation.
This article details HuoLala's journey from confronting large‑model knowledge gaps and latency issues to adopting Retrieval‑Augmented Generation (RAG) with vector databases, outlining their architecture challenges, selection criteria, deployment scenarios, and future plans for AI‑driven logistics.
This article walks through the end‑to‑end process of building an image similarity solution—from vectorizing images with ResNet, storing high‑dimensional vectors in Milvus, using HNSW for fast ANN search, to applying YOLO for object detection and practical training tips.
This article introduces Milvus, an open‑source vector database for AI and machine‑learning workloads, outlines its key features and application scenarios, and provides detailed Docker‑Compose commands to set up Milvus, MinIO, and the Attu graphical management tool.
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 presents a step‑by‑step guide for constructing a scalable enterprise Retrieval‑Augmented Generation (RAG) solution using the Model Context Protocol (MCP), covering architecture comparison, system design, Milvus‑backed knowledge store, Python client implementation, deployment scripts, code examples, and best‑practice recommendations.
This guide walks through using Alibaba's new Qwen3-Embedding and Qwen3-Reranker models to build a two‑stage Retrieval‑Augmented Generation pipeline with Milvus, covering environment setup, data ingestion, vector indexing, reranking, and LLM‑driven answer generation, demonstrating production‑grade performance across multilingual queries.
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.
This guide walks you through using Alibaba Cloud's PAI‑LangStudio together with the Qwen3 large language model to create an AI‑powered question‑answering system that combines Retrieval‑Augmented Generation, web search, secure deployment, and flexible customization for production use.
This tutorial shows how to combine Alibaba Cloud Milvus vector search with the Qwen VL large model to extract image descriptions, generate multimodal embeddings, store them in Milvus, and perform fast multimodal searches such as text‑to‑image and image‑to‑text queries using Python.
This guide walks through creating a Retrieval‑Augmented Generation (RAG) system using Spring Boot 3.4.2, Milvus vector database, and the bge‑m3 embedding model via Ollama, covering environment setup, dependency configuration, vector store operations, and integration with a large language model to deliver refined, similarity‑based answers.
This article explains the Model Context Protocol (MCP) as a standard for LLM‑data integration, describes Retrieval‑Augmented Generation (RAG) techniques to reduce hallucinations, and introduces vector databases like Milvus that store high‑dimensional embeddings for efficient AI retrieval tasks.
This guide walks you through Milvus 2.5’s new full‑text, keyword‑matching, and hybrid search capabilities, showing how to set up the schema, install dependencies, prepare data with LangChain, and combine dense and sparse vectors for RAG‑enabled retrieval using Python.
This step‑by‑step guide shows how to assemble a Retrieval‑Augmented Generation (RAG) system using Alibaba Cloud Milvus vector search, the DeepSeek large language model, and PAI LangStudio, covering instance creation, data upload, model deployment, connection setup, flow design, and service invocation.
This guide explains why DeepSeek4j is needed, its core features, and provides step‑by‑step instructions—including dependency setup, configuration, code examples, and a complete RAG pipeline using Milvus—to help developers quickly create a private AI knowledge base with Spring Boot.
This guide walks through building a Java RAG system with DeepSeek R1, Milvus, and Spring, covering environment setup, vector model integration via OpenAI protocol, Maven dependencies, data embedding, and a chat endpoint that combines semantic retrieval with LLM generation.
This guide walks you through creating a RAG‑enhanced AI solution for education using Alibaba PAI, covering prerequisite setup, knowledge‑base construction with PAI‑Designer, model deployment, connection configuration, workflow assembly, and a side‑by‑side comparison of RAG versus non‑RAG answers.
Learn how to create a Retrieval‑Augmented Generation (RAG) system for medical applications using Alibaba's PAI platform, covering knowledge‑base construction with PAI‑Designer, template setup in PAI‑LangStudio, deployment of LLM and embedding models, vector database integration, and end‑to‑end workflow configuration.
This guide walks you through setting up Alibaba Cloud Milvus, configuring public access, deploying a RAG system via PAI, uploading a knowledge base, interacting with the model through the Web UI, and inspecting vector collections with Attu, all with step‑by‑step instructions and configuration details.
This guide walks you through creating a Retrieval‑Augmented Generation (RAG) question‑answering application by integrating Alibaba Cloud Milvus vector search, DashScope embedding models, and PAI EAS LLM services, covering prerequisites, service deployment, configuration, Python code setup, and execution steps.
This article analyzes why organizations are seeking domestic replacements for Elasticsearch due to policy, licensing, and cost constraints, and evaluates several options—including OpenSearch, XunSearch, Lucene/Solr, native database extensions, Milvus, and EasySearch—highlighting their strengths, weaknesses, and suitable scenarios.
This article explains how combining dense vector‑based semantic search with traditional keyword matching using a unified vector database such as Milvus delivers superior performance, scalability, and simplicity compared to maintaining separate Elasticsearch and vector‑search stacks.
This article introduces vector databases as the foundation for efficient high‑dimensional data retrieval in generative AI, covering their background, Milvus’s cloud‑native architecture, key indexing techniques, performance‑trade‑offs, AI‑driven optimizations, and a Q&A session.
The article chronicles the evolution of database technology from early hierarchical and network models through relational, column‑store, document, key‑value, graph, time‑series, HTAP, and finally vector databases, detailing each system’s architecture, strengths, limitations, typical uses, and future trends toward specialization, distributed cloud‑native designs, and AI‑driven applications.
This guide explains vector embeddings, OpenAI's text‑embedding models, and how to use PyMilvus with Zilliz Cloud to create a Retrieval‑Augmented Generation (RAG) system for fast, accurate semantic search.
This article presents a comprehensive overview of Zilliz’s cloud‑native vector database ecosystem, detailing Milvus’s distributed architecture, indexing and query capabilities, related tools such as Towhee and GPTCache, storage challenges, tiered storage designs, performance metrics, and real‑world AI use cases like code‑assist and RAG‑based Q&A systems.
This case study details how ShiHuo, an e‑commerce recommendation platform, overcame rapid product growth, cluster instability, and high operational overhead by adopting Alibaba Cloud’s fully managed Milvus vector search service, achieving higher performance, better availability, and reduced management costs.
This article describes how to combine Elasticsearch’s keyword matching with Milvus’s vector‑based semantic search to build a scalable document search service, covering data preprocessing, architecture, query handling, custom scoring, DSL configuration, and result merging.