# Milvus

Open-source vector database that scales from an embedded library to distributed retrieval clusters.

- Company: Zilliz
- Category: Platforms & Infrastructure
- Business model: Open (open weights/source)
- Availability: unknown
- Launched: Not recorded
- Tags: vector, developer-tools
- Website: https://milvus.io/
- Documentation: Not recorded
- Pricing page: Not recorded
- License: Not recorded
- Canonical URL: https://globalaiproductindex.com/products/milvus/
- Record updated: 2026-11-03

Typical uses include Semantic retrieval for RAG; Search over embedded application data. Documented capabilities: Store embeddings and search with structured metadata; Lite, standalone and distributed deployment modes; Hybrid search and support for multiple vector types.

## Key features

- Store embeddings and search with structured metadata
- Lite, standalone and distributed deployment modes
- Hybrid search and support for multiple vector types

## Use cases

- Semantic retrieval for RAG
- Search over embedded application data

## Pricing

The open-source software can be run on your own infrastructure. Compute, storage and any external model API usage are separate costs; a managed service is not included.

## FAQ

**Where does Milvus fit in a workflow?**

Open-source vector database that scales from an embedded library to distributed retrieval clusters. Store embeddings and search with structured metadata.

**What costs and limits should I compare before choosing Milvus?**

The open-source software can be run on your own infrastructure. Compute, storage and any external model API usage are separate costs; a managed service is not included.

## Sources

- [Milvus — official product](https://milvus.io/)
- [Milvus — official documentation and terms](https://milvus.io/docs/overview.md)
- [Milvus — official documentation and terms](https://github.com/milvus-io/milvus)

---
Data from the [Global AI Product Index](https://globalaiproductindex.com/), licensed CC BY 4.0.