ai-agent

Milvus: Fast Vector Search

Name: Milvus: Fast Vector Search
Author: milvus-io

Get scalable vector ANN search with Milvus, a cloud-native database for founders, backed by 45k+ GitHub stars

44,588 stars4,035 forksGoQuality 9/10Updated 6/2/2026100% free · open source

What it does

Milvus is a cloud-native database that enables scalable vector Approximate Nearest Neighbors (ANN) search for founders to efficiently manage and query large datasets of vectors.

Install / run

docker run -d --name milvus-db \
  -p 19530:19530 \
  -v /tmp/milvus:/var/lib/milvus \
  milvusdb/milvus:latest

When to use it

•Building a recommendation system that requires fast and accurate similarity searches
•Developing a computer vision application that needs to efficiently query large datasets of image embeddings
•Creating a natural language processing model that requires scalable semantic search capabilities

Quick start

1Create a new Milvus server instance by running the command: `docker run -d --name milvus-db -p 19530:19530 -v /tmp/milvus:/var/lib/milvus milvusdb/milvus:latest`
2Use the Milvus Python SDK to connect to the server: `from milvus import Milvus, Client`
3Create a new index and insert data into the Milvus database: `client.create_index('test', 'ivf_sq8')` and `vectors = [[1.0, 2.0], [3.0, 4.0]]`
4Perform a vector search query: `client.search('test', 'ivf_sq8', vectors)`
5Check the search results: `print(res)`

Ready-to-paste prompt

python -c 'from milvus import Milvus, Client; client = Client(); client.connect(); client.create_collection('test'); client.insert('test', [[1.0, 2.0], [3.0, 4.0]])'

Heads up: Make sure to allocate sufficient GPU resources when running Milvus, as it requires significant GPU memory to perform efficient vector searches, and ensure that the Docker container has the necessary permissions to access the host machine's GPU

Saves to your device