O que é o Milvus?

LFAI & DATAProjeto de Graduação

Milvus é um banco de dados de vetores de código aberto, projetado para lidar com bilhões de vetores e impulsionar as maiores aplicações de IA do mundo.

Criado porZilliz Logo
Milvus video background

Construído sobre uma comunidade vibrante e crescente

  • 46K+

    Estrelas no GitHub

  • 4,000+

    Comunidade

  • 100M+

    Downloads

  • 300+

    Contribuidores

Milvus community

Como o Milvus funciona?

  • check markServiços do Coordenador

    Orquestra o balanceamento de carga e a gestão de dados através de coordenadores, garantindo uma gestão eficiente de dados, consultas e índices.

  • check markCamada de Acesso

    Gerencia solicitações externas utilizando proxies sem estado para gerenciar conexões, realizar verificações e balancear carga.

  • check markNós de Trabalho

    Executa tarefas como pods escaláveis, implementando comandos do coordenador, permitindo ajustes dinâmicos para dados, consultas e exigências de indexação em mudança.

  • check markCamada de Armazenamento

    Garante a persistência de dados através de três componentes: lojas de metadados, brokers de logs e armazenamento de objetos.

How does Milvus work?

Por que Milvus?

Milvus é um banco de dados de vetores, nativo da nuvem e de código aberto, alimentando o Zilliz.

Escale conforme necessário

Lida com bilhões de vetores através de sua arquitetura distribuída, separando armazenamento e computação. Seu design de microsserviços permite escalar funções específicas, otimizando o uso de recursos à medida que você cresce.

Saiba mais
Scale as needed

Alto Desempenho

Milvus oferece diversos tipos de índices (HNSW, DiskANN, Quantização, Binário, etc.) e designs otimizados para hardware, tanto para CPU quanto para GPU. Isso garante uma recuperação rápida de vetores com alta precisão em vários casos de uso.

Benchmark
High Performance

Suporte Completo ao Ciclo de Vida

Milvus oferece três modelos de implantação com uma API unificada: Lite para protótipos, Standalone para testes e produções em pequena escala, e Distribuído para produção em larga escala—permitindo uma escalabilidade contínua sem reescrever o código.

Saiba mais
Full Development Lifecycle Support

Funcionalidades Avançadas

Suporta tipos de busca múltiplos (top-K & Range ANN, esparso & denso, multi-vetor, agrupamento), filtragem de metadados e multi-tenant. Inclui ferramentas administrativas e integra-se com várias ferramentas e modelos de IA.

Explore os Notebooks do Milvus
Feature Rich
“

Milvus has become the only technical choice for vector databases in our upcoming business expansion across the life sciences industry."

Xiaoming Zhang

VP of Technology at Biomap

“

If I were to choose again, I would still choose Milvus at this point. The scalability, documentation quality, and continuous innovation make it the right foundation for our plagiarism detection platform."

Teis Petersen

Engineering Team Lead, UNIwise

“

When we identify a need for specific data, we can often find the required data in our database the same day using text or image search with Milvus. This greatly improves our data processing efficiency and has a positive effect on our business operations."

Mr. Zhang

BOSCH’s principal software engineer

“

I really like how Milvus' hybrid search allowed me to blend semantic and keyword search, which is crucial in a domain as technical and complex as EU policy."

Alessandro Saccoia

Co-Founder @ Veridien.ai

“

Milvus is renowned as one of the most advanced vector database platforms for AI applications. Rakuten Symphony engineers identified the Milvus Vector Database - an open source database which is horizontally scalable - as their platform of choice for LLM use and developing and maintaining AI applications."

Rakuten Symphony Engineering Team

“

When it comes to vector databases, Milvus has impressed us with its performance and scalability, meeting our stringent criteria for handling our AI use case backlog."

Team Lead

AI, ML, and Platform Solutions

“

Milvus has become the bridge that connects our multi-modal foundation models with real-world applications. It's not just about performance – it's about enabling entirely new approaches to biological discovery that were previously impossible."

Xiaoming Zhang

VP of Technology at Biomap

“

During batch ingestion tests, Milvus demonstrated that it could complete an entire collection dump into the database at speeds 5–10 times faster than competitors."

Team Lead

AI, ML, and Platform Solutions

“

We've got millions of monthly active users and all of the underlying data when we're trying to go find related conversations, find updates to an action item, find referenced documents...Milvus serves as the central repository and powers our information retrieval among billions of records."

Rob Williams

Co-Founder and CTO at Read AI

“

Milvus transformed our ability to detect semantic plagiarism at scale. We can now process variable workloads ranging from 10 to 10,000+ documents daily while maintaining cost-effectiveness, which would have been impossible with traditional solutions."

Teis Petersen

Engineering Team Lead, UNIwise

“

Milvus’s real advantage was how easy and friendly it made things to understand and execute."

Hanlian Lyu

a Product Owner and BI Expert at Volvo Cars

“

Among Milvus's rich vector search capabilities, features such as support for multiple ANN index types, multi-vector support, and hybrid search have proven especially valuable in real-world service environments. As Milvus continues to evolve with new capabilities, NAVER expects even broader applications across its services."

NAVER Engineering Team

“

Whenever we demonstrate our solution with Milvus, we’re effectively crushing the cloud vendor solution’s performance. It’s a great benchmark because most enterprise users already know the vendor solution, so the comparison is immediate."

Hanlian Lyu

a Product Owner and BI Expert at Volvo Cars

“

Milvus has become the only technical choice for vector databases in our upcoming business expansion across the life sciences industry."

Xiaoming Zhang

VP of Technology at Biomap

“

If I were to choose again, I would still choose Milvus at this point. The scalability, documentation quality, and continuous innovation make it the right foundation for our plagiarism detection platform."

Teis Petersen

Engineering Team Lead, UNIwise

Construa Aplicações de IA com suas Ferramentas Favoritas

Quer economizar tempo e dinheiro rodando o Milvus?

Cada cluster do Zilliz Cloud roda o Milvus por trás dos panos. Deixe-nos escolher os índices certos, gerenciar as atualizações do Milvus, escalar automaticamente para você, e muito mais.

Comece grátis