Qu'est-ce que Milvus ?

LFAI & DATAProjet Universitaire

Milvus est une base de données vectorielle open-source conçue pour gérer des milliards de vecteurs et alimente les plus grandes applications d'IA au monde.

Créé parZilliz Logo
Milvus video background

Bâti sur une communauté dynamique et en croissance

  • 46K+

    Étoiles GitHub

  • 4,000+

    Communauté

  • 100M+

    Téléchargements

  • 300+

    Contributeurs

Milvus community

Comment fonctionne Milvus ?

  • check markServices Coordinateurs

    Orchestre l'équilibrage de charge et la gestion des données via des coordinateurs, assurant une gestion efficace des données, requêtes et index.

  • check markCouche d'Accès

    Gère les requêtes externes via des proxies sans état pour administrer les connexions, effectuer des vérifications et équilibrer la charge.

  • check markNœuds de Travail

    Exécute les tâches via des pods scalables en implémentant les commandes des coordinateurs, permettant un ajustement dynamique aux besoins changeants en données, requêtes et indexation.

  • check markCouche de Stockage

    Assure la persistance des données via trois composants : meta stores, log brokers et stockage objet.

How does Milvus work?

Pourquoi choisir Milvus ?

Milvus est une base de données vectorielle cloud-native et open-source alimentant Zilliz.

Évolutivité flexible

Gère des milliards de vecteurs grâce à son architecture distribuée séparant stockage et calcul. Son design microservices permet de scaler des fonctions spécifiques, optimisant l'utilisation des ressources.

En savoir plus
Scale as needed

Haute Performance

Milvus propose divers types d'index (HNSW, DiskANN, Quantization, Binaire, etc.) et des designs optimisés pour CPU et GPU. Cela garantit une recherche vectorielle rapide avec un haut rappel pour divers cas d'usage.

Benchmark
High Performance

Support complet du cycle de vie

Milvus offre trois modèles de déploiement avec une API unifiée : Lite pour le prototypage, Standalone pour tests et petites productions, et Distribué pour productions à grande échelle - permettant un scaling transparent sans réécriture de code.

En savoir plus
Full Development Lifecycle Support

Fonctionnalités avancées

Prend en charge plusieurs types de recherche (top-K & Range ANN, sparse & dense, multi-vecteurs, grouping), le filtrage par métadonnées et le multi-tenant. Il inclut des outils d'administration et s'intègre à divers outils et modèles d'IA.

Explorer les Notebooks Milvus
Feature Rich
“

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

“

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 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

“

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

“

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 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

“

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

“

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’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

“

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

“

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

Développez des applications IA avec vos outils préférés

Vous souhaitez gagner du temps et de l'argent avec Milvus ?

Chaque cluster Zilliz Cloud utilise Milvus en arrière-plan. Laissez-nous choisir les bons index, gérer les mises à jour, scaler automatiquement pour vous, et plus encore.

Commencer gratuitement