milvus-io /milvus
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
★ 46,668⑂ 4,332👁 337⑃ 34,167● 17,498▤ 182
+3
Daily
+54
Weekly
46,668
stars
4,332
forks
337
watchers
34,167
prs
17,498
issues
182
releases
README
What is Milvus?
🐦 Milvus is a high-performance vector database built for scale. It powers AI applications by efficiently organizing and searching vast amounts of unstructured data, such as text, images, and multi-modal information.
🧑💻 Written in Go and C++, Milvus implements hardware acceleration for CPU/GPU to achieve best-in-class vector search performance. Thanks to its fully-distributed and K8s-native architecture, Milvus can scale horizontally, handle tens of thousands of search queries on billions of vectors, and keep data fresh with real-time streaming updates. Milvus also supports Standalone mode for single machine deployment. Milvus Lite is a lightweight version good for quickstart in python with pip install.
Want to use Milvus with zero setup? Try out Zilliz Cloud ☁️ for free. Milvus is available as a fully managed service on Zilliz Cloud, with Serverless, Dedicated and BYOC options available.
For questions about how to use Milvus, join the community on Discord to get help. For reporting problems, file bugs and feature requests in GitHub Issues or ask in Discussions.
The Milvus open-source project is
under LF AI & Data Foundation, distributed with Apache 2.0 License, with Zilliz as its major contributor.
Quickstart
python
$ pip install -U pymilvus
This installs pymilvus, the Python SDK for Milvus. Use MilvusClient to create a client:
python
from pymilvus import MilvusClient
You can also try Milvus Lite for quickstart by installing pymilvus[milvus-lite]. To create a local vector database, simply instantiate a client with a local file name for persisting data:
python
client = MilvusClient("milvus_demo.db")
You can also specify the credentials to connect to your deployed Milvus server or Zilliz Cloud:
python
client = MilvusClient(
uri="",
token="")
With the client, you can create collection:
python
client.create_collection(
collection_name="demo_collection",
dimension=768, The vectors we will use in this demo have 768 dimensions
)
Ingest data:
python
res = client.insert(collection_name="demo_collection", data=data)
Perform vector search:
python
query_vectors = embedding_fn.encode_queries(["Who is Alan Turing?", "What is AI?"])
res = client.search(
collection_name="demo_collection", target collection
data=query_vectors, a list of one or more query vectors, supports batch
limit=2, how many results to return (topK)
output_fields=["vector", "text", "subject"], what fields to return
)
Why Milvus
Milvus is designed to handle vector search at scale. It stores vectors, which are learned representations of unstructured data, together with other scalar data types such as integers, strings, and JSON objects. Users can conduct efficient vector search with metadata filtering or hybrid search. Here are why developers choose Milvus as the vector database for AI applications:
High Performance at Scale and High Availability
Milvus features a distributed architecture thTop issues
#23232[Feature]: Support HNSW SQ42 comments · 2023-04-04#31581[Feature]: Will milvus suppoert BGE-M3['Colbert'] storage and search? 37 comments · 2024-03-25#39027[Enhancement]: Merge insert message of multi partitions in one shard as one message.33 comments · 2025-01-07#43638[Enhancement]: Update Woodpecker Version Track24 comments · 2025-07-30#24272[Feature]: Support Graceful Shutdown of Worker Nodes in Milvus23 comments · 2023-05-19#25343[Feature]: Distinct field values22 comments · 2023-07-05#2771Add support for ScaNN index21 comments · 2020-07-07#41035[Feature]: Support gRPC-based custom tokenizer20 comments · 2025-04-01
Discussions
#55539Chopper: a small open model that cuts only the needed sentences out of retrieved text0 comments · 2026-11-14#55500v3.0.6 的 rpm/deb 包什么时候发布?后续 3.0.x 是否每个版本都发?1 comments · 2026-11-13#55438Running Milvus 2.6.x on an Ubuntu 24.04 base image (from 22.04): any functional or performance concerns?3 comments · 2026-11-12#55078Error while vendoring tantivy-binding dependencies to build Milvus1 comments · 2026-11-03#54554Best Practices for Milvus Schema Migrations Across Environments1 comments · 2026-10-22#54507Where can I download the official RPM/DEB packages? (Documentation links return 404)1 comments · 2026-10-21#54073milvus集群在大文件的时候,dataNode执行索引构建任务速度慢2 comments · 2026-10-09#54048Woodpecker: segments with V6 footer (LAC) can't be read after downgrading Milvus 3.0.x -> 2.6.x (failed to decode footer record: buffer too short for record: expected N, got 45) — is downgrade supported?1 comments · 2026-10-08
Latest release
milvus-3.0.6 v3.0.6 2026-11-11Release note is coming soon...