Skip to content
SPECIFICTION
Get listed

Milvus

milvus.io

Free plan LinuxAPISelf-hosted
Visit milvus.io
Spec score 8.3 #8 of 40 in Ai Databases

What it is

Milvus is an open-source vector database from Zilliz for GenAI and scalable vector search. It supports approximate-nearest-neighbor, filtered, range, hybrid, and full-text search, along with reranking, fetch, and query operations. Metadata filtering, sparse vectors, and index types including HNSW, IVF, FLAT, DiskANN, and SCANN are documented. Deployment choices are Milvus Lite as a Python library, Standalone as a single-machine server, and Distributed on Kubernetes. Documentation recommends Lite for up to a few million vectors, Standalone up to 100 million, and Distributed for 100 million to tens of billions. Lite can run locally without a cloud service for private or sensitive data; an online upgrade from Standalone to a cluster is not currently supported. Official interfaces include REST plus Python, Go, Java, Node.js, and C++ APIs or SDKs. C# is contributed by Microsoft and Rust is under development. Security documentation covers authentication, TLS for gRPC and REST, and role-based access control at collection, database, and instance levels. The Apache 2.0 software is free, and Zilliz Cloud is offered as a managed option.

Spec sheet

What it does
Milvus is an open-source vector database developed by Zilliz for high-performance, scalable vector search.Read 4 Oct 2026 · milvus.io
Product
Milvus is an open-source vector database built for GenAI applications.Read 4 Oct 2026 · milvus.io
Intended users
The documentation describes Distributed as suited to enterprise users running large-scale vector search systems in production.Read 4 Oct 2026 · milvus.io
Deployment
Milvus offers Lite as a Python library, Standalone as a single-machine server, and Distributed for Kubernetes clusters.Read 4 Oct 2026 · milvus.io
Free plan
YesRead 22 Sep 2026 · milvus.io
Integrations
The integrations documentation lists tools including LangChain, LlamaIndex, Haystack, DSPy, Dify, Langflow, OpenAI, Cohere, and HuggingFace.Read 4 Oct 2026 · milvus.io
Security
Milvus documents user authentication, TLS encryption for gRPC and REST traffic, and role-based access control.Read 4 Oct 2026 · milvus.io
Support
The Milvus site lists community channels including Slack, Discord, GitHub, and Milvus Office Hours.Read 4 Oct 2026 · milvus.io
Maker
The documentation says Milvus was developed by Zilliz and is associated with the LF AI & Data Foundation under the Linux Foundation.Read 4 Oct 2026 · milvus.io
Access control
RBAC can control operations at collection, database, and instance levels.Read 4 Oct 2026 · milvus.io
Dependencies
A default Milvus 3.x deployment uses Woodpecker for messaging, etcd for metadata, and MinIO for object storage.Read 4 Oct 2026 · milvus.io
Deployment caveat
The documentation says an online upgrade from a standalone Milvus instance to a cluster is not currently supported.Read 4 Oct 2026 · milvus.io
Deployment limits
The docs recommend Lite for up to a few million vectors, Standalone up to 100 million, and Distributed for 100 million to tens of billions.Read 4 Oct 2026 · milvus.io
Deployment options
Milvus offers Lite as a Python library, Standalone as a single-machine server, and Distributed for Kubernetes clusters.Read 4 Oct 2026 · milvus.io
Local use
Milvus Lite can run on a device without a cloud service for local search of private or sensitive data.Read 4 Oct 2026 · milvus.io
Managed option
Milvus links to Zilliz Cloud as its fully managed offering and describes a free option on its documentation site.Read 4 Oct 2026 · milvus.io
Scale
Milvus supports deployments from local notebook demos to Kubernetes clusters handling tens of billions of vectors.Read 4 Oct 2026 · milvus.io
Scale limits by deployment
The documentation recommends Milvus Lite for up to a few million vectors, Standalone for up to 100 million, and Distributed for 100 million to tens of billions.Read 4 Oct 2026 · milvus.io
SDKs
Milvus provides official REST, Python, Go, Java, Node.js, and C++ APIs or SDKs; C# is contributed by Microsoft and Rust is under development.Read 4 Oct 2026 · milvus.io
Search
Milvus supports approximate nearest neighbor, filtering, range, hybrid, and full-text search, plus reranking, fetch, and query operations.Read 4 Oct 2026 · milvus.io
Search features
Milvus supports approximate nearest neighbor, filtered, range, hybrid, and full-text search, as well as reranking and queries.Read 4 Oct 2026 · milvus.io

Plans and prices

Milvus (open-source software) Free Apache 2.0 licensed · Milvus Lite: recommended for datasets up to a few million vectors · Standalone: suitable for datasets up to 100 million vectors Read 4 Oct 2026 · milvus.io

Every Milvus plan and price →

Strong points and limits

Strong points

  • Supports hybrid and full-text search
  • Offers local, standalone, and Kubernetes deployments
  • Scales to tens of billions of vectors
  • Provides official SDKs across six languages
  • Includes TLS, authentication, and RBAC

Limits

  • Standalone-to-cluster online upgrade is unsupported
  • Distributed deployment requires Kubernetes
  • Rust support is still under development
  • Default 3.x deployment has several dependencies

Who it suits

Milvus suits developers building vector search for GenAI applications, from local experiments to Kubernetes systems. Distributed is described for enterprise production workloads with very large vector collections.

Verdict

Milvus provides a free, open-source path from local vector search to very large distributed deployments. Deployment limits and the unsupported online upgrade path are important when planning growth.

Where Specifiction places it

Alternatives to MilvusAll alternatives →