Cos'è Milvus?

LFAI & DATAProgetto di Laurea

Milvus è un database vettoriale open-source progettato per gestire miliardi di vettori e alimenta le più grandi applicazioni AI al mondo.

Creato daZilliz Logo
Milvus video background

Costruito su una comunità vibrante e in crescita

  • 46K+

    Stelle su GitHub

  • 4,000+

    Comunità

  • 100M+

    Download

  • 300+

    Contributori

Milvus community

Come funziona Milvus?

  • check markServizi di Coordinamento

    Gestisce il bilanciamento del carico e la gestione dei dati tramite i coordinatori, garantendo una gestione efficiente dei dati, delle query e degli indici.

  • check markStrato di Accesso

    Gestisce le richieste esterne utilizzando proxy senza stato per gestire le connessioni, eseguire verifiche e bilanciare il carico.

  • check markNodi di Lavoro

    Esegue compiti come pod scalabili implementando i comandi del coordinatore, consentendo un aggiustamento dinamico per la gestione dei dati, delle query e degli indici.

  • check markStrato di Archiviazione

    Garantisce la persistenza dei dati attraverso tre componenti: meta store, broker dei log e archiviazione a oggetti.

How does Milvus work?

Perché Milvus?

Milvus è un database vettoriale open-source e nativo nel cloud che alimenta Zilliz.

Scalabilità a necessità

Gestisce miliardi di vettori attraverso la sua architettura distribuita, separando archiviazione e calcolo. Il suo design a microservizi consente di scalare funzioni specifiche, ottimizzando l'uso delle risorse man mano che cresci.

Scopri di più
Scale as needed

Alta Performance

Milvus offre diversi tipi di indice (HNSW, DiskANN, Quantization, Binary, ecc.) e design ottimizzati per hardware sia CPU che GPU. Ciò garantisce un recupero rapido dei vettori con alta precisione per vari casi d'uso.

Benchmark
High Performance

Supporto Completo per il Ciclo di Vita

Milvus offre tre modelli di distribuzione con un'unica API: Lite per prototipazione, Standalone per test e produzione su piccola scala, e Distribuito per produzione su larga scala, consentendo una scalabilità senza riscrivere il codice.

Scopri di più
Full Development Lifecycle Support

Funzionalità Avanzate

Supporta tipi di ricerca multipli (top-K & Range ANN, sparsa & densa, multi-vettore, raggruppamento), filtro metadati e multi-tenancy. Include strumenti di amministrazione e si integra con vari strumenti e modelli AI.

Esplora Milvus Notebooks
Feature Rich
“

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

“

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

“

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 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

“

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

“

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

“

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

“

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

“

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

“

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

“

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

“

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

Costruisci applicazioni AI con i tuoi strumenti preferiti

Vuoi risparmiare tempo e denaro gestendo Milvus?

Ogni cluster Zilliz Cloud esegue Milvus in background. Lascia che scegliamo gli indici giusti, gestiamo gli aggiornamenti di Milvus, scalando automaticamente per te e altro.

Inizia gratis