← Back to all projects

Milvus
Distributed vector database built for very large collections
OfficialApache-2.0
What is Milvus?
Separates storage from compute so indexing and querying scale independently — the architecture you want at billions of vectors. That capability comes with operational weight; below a few million vectors, something simpler will serve you better.
What can you do with Milvus?
- Prototype without running a server — pymilvus[milvus-lite] lets MilvusClient persist to a local file, and the same client code reaches a self-hosted cluster or Zilliz Cloud by swapping uri and token.
- Mix full-text and vector search — Sparse and dense vectors sit in one collection, so BM25 full-text search and learned sparse embeddings such as SPLADE and BGE-M3 can be fused with dense results through a rerank function.
- Choose an index per workload — HNSW, IVF, FLAT, SCANN and DiskANN are all available, along with quantization variants such as IVFPQ, mmap for memory pressure, and GPU indexing via NVIDIA CAGRA.
- Scale reads and writes separately — The distributed architecture splits compute from storage, so read-heavy traffic is served by adding query nodes and write-heavy ingestion by adding data nodes, with replicas for fault tolerance.
- Isolate tenants in one cluster — Isolation can be set at database, collection, partition or partition-key level, combined with RBAC, TLS and hot/cold storage tiers to keep frequently accessed data in memory or on SSD.
Star history
15 Aug to 30 Oct · +891
45.6k46.5k
Frequently asked questions
Is Milvus free for commercial use?
Milvus is released under the Apache-2.0 licence — OSI-approved open source, which permits commercial use.
How can Milvus be deployed?
Milvus is available as Self-hosted / Managed cloud.