DB-EnginesextremeDB - Data management wherever you need itEnglish
Knowledge Base of Relational and NoSQL Database Management Systemsprovided by Redgate Software

DBMS > Milvus

Milvus System Properties

Please select another system to compare it with Milvus.

Our visitors often compare Milvus with Weaviate, Qdrant and PostgreSQL.

Editorial information provided by DB-Engines
DescriptionA DBMS designed for efficient storage of vector data and vector similarity searches
Primary database modelVector DBMS
DB-Engines Ranking infomeasures the popularity of database management systemsranking trend
Trend Chart
Rank#89  Overall
#4  Vector DBMS
Technical documentationmilvus.io/­docs/­overview.md
Initial release2019
Current release2.4.4, May 2024
License infoCommercial or Open SourceOpen Source infoApache Version 2.0
Cloud-based only infoOnly available as a cloud serviceno
DBaaS offerings (sponsored links) infoDatabase as a Service

Providers of DBaaS offerings, please contact us to be listed.
Zilliz Cloud – Cloud-native service for Milvus
Implementation languageC++, Go
Server operating systemsLinux
macOS info10.14 or later
Windows infowith WSL 2 enabled
Typing infopredefined data types such as float or dateVector, Numeric and String
XML support infoSome form of processing data in XML format, e.g. support for XML data structures, and/or support for XPath, XQuery or XSLT.no
Secondary indexesno
SQL infoSupport of SQLno
APIs and other access methodsRESTful HTTP API
Supported programming languagesC++
JavaScript (Node.js)
Server-side scripts infoStored proceduresno
Partitioning methods infoMethods for storing different data on different nodesSharding
MapReduce infoOffers an API for user-defined Map/Reduce methodsno
Consistency concepts infoMethods to ensure consistency in a distributed systemBounded Staleness
Eventual Consistency
Immediate Consistency
Session Consistency
Tunable Consistency
Foreign keys infoReferential integrityno
Transaction concepts infoSupport to ensure data integrity after non-atomic manipulations of datano
Concurrency infoSupport for concurrent manipulation of datayes
Durability infoSupport for making data persistentyes
In-memory capabilities infoIs there an option to define some or all structures to be held in-memory only.yes
User concepts infoAccess controlRole based access control and fine grained access rights
More information provided by the system vendor
Specific characteristics
Milvus is an open-source and cloud-native vector database built for production-ready AI. It was created to store,
index, and manage billion, or even trillion-scale embedding vectors generated by deep neural networks and other machine learning (ML) models.

As a database specifically designed to handle queries over vectors, it is capable of indexing vectors on a trillion
scale. Unlike existing relational databases which mainly deal with structured data following a pre-defined
pattern, Milvus is designed from the bottom-up to handle embedding vectors converted from unstructured data
like emails, papers, IoT sensor data, Facebook photos, protein structures, and much more.
Competitive advantages
  • Highly available, versatile, and robust with millisecond latency.
  • Supports batch and stream data processing in real time.
  • Supports flexible scaling of each component by using Kubernetes to manage its execution engine and separating read, write and other services with microservices.
  • Supports Time Travel with distributed logging.
  • Supports heterogenous computing, which includes support for different types of hardware (CPU, GPU, FPGA, MLU) and instruction sets.
  • Supported by Rich APIs (Python, Node.js, Go, etc.) and tools (Milvus CLI, Attu, etc.) to facilitate DevOps.
  • Supports high performance ANN algorithms like FAISS,HNSW,ANNOY, etc.
Typical application scenarios
  • RAG: retrieval augmented generation
  • Video media: video understanding, video deduplication.
  • E-commerce and mobile applications: image understanding, reverse image search.
  • Finance/Telecommunications/Retail: AI-aided customer support, QA chatbots.
  • Internet: personalized recommender systems, personalized search.
  • Autonomous vehicles: automated data labeling and annotation, object detection.
  • Biopharmaceutical: virtual compound screening, compound retrosynthetic analysis, protein property prediction, and DNA testing.
  • Cybersecurity: malware detection and cyberattack alert.
  • Quantitative trading: data analysis and prediction.
  • Metaverse: environmental perception and interaction in virtual world.

See more in Milvus Bootcamp.

Key customers
Milvus is trusted by thousands of enterprises, including PayPal, eBay, IKEA, LINE, Shopee, Shutterstock, SmartNews, Tencent, Tokopedia, TrendMicro, Walmart, and much more.

See Milvus Adopters for more Milvus users.
Market metrics
As of January 2024,
  • 25k+ GitHub stars
  • 10M+ downloads and installations​
  • 3k+ enterprise adopters
Licensing and pricing models
Milvus was released under the open-source Apache License 2.0 in October 2019.

Related products and services

We invite representatives of vendors of related products to contact us for presenting information about their offerings here.

More resources
DB-Engines blog posts

Vector databases
2 June 2023, Matthias Gelbmann

show all

Recent citations in the news

How NVIDIA GPU Acceleration Supercharged Milvus Vector Database
26 March 2024, The New Stack

AI-Powered Search Engine With Milvus Vector Database on Vultr
31 January 2024, SitePoint

IBM watsonx.data’s integrated vector database: unify, prepare, and deliver your data for AI
9 April 2024, ibm.com

Milvus 2.4 Unveils Game-Changing Features for Enhanced Vector Search
20 March 2024, GlobeNewswire

Using Evaluations to Optimize a RAG Pipeline: from Chunkings and Embeddings to LLMs
9 July 2024, Towards Data Science

provided by Google News

Share this page

Featured Products

SingleStore logo

Database for your real-time AI and Analytics Apps.
Try it today.

Milvus logo

Vector database designed for GenAI, fully equipped for enterprise implementation.
Try Managed Milvus for Free

RaimaDB logo

RaimaDB, embedded database for mission-critical applications. When performance, footprint and reliability matters.
Try RaimaDB for free.

Neo4j logo

See for yourself how a graph database can make your life easier.
Use Neo4j online for free.

Datastax Astra logo

Bring all your data to Generative AI applications with vector search enabled by the most scalable
vector database available.
Try for Free

Present your product here