milvus
by milvus-io
Milvus is a vector database that stores and searches numerical representations of text, images and other data, so apps can find similar items quickly. It is used to power AI features such as semantic search and retrieval-augmented generation (RAG) chatbots.
- Stars
- 46.5k +7 a day
- Licence
- Apache-2.0
- Runs on
- A small server
- Setup
- Moderate
- Language
- Go
- Age
- 2598 days
What you can do with it
- Store text or image embeddings and search them by similarity
- Build a RAG chatbot that answers questions from your own documents
- Combine vector search with metadata filters, for example for product or image search
Make money with it
A freelancer could build and host custom AI search or document chatbot systems for small businesses, using Milvus as the storage layer.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Add semantic search to a shop or knowledge base so customers find products or answers faster
- Build a document question-answering service for clients without paying for a hosted vector database
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install the Python SDK with pip (Milvus Lite runs locally from a file), or run the Standalone version with Docker; large deployments use Kubernetes.
Follow the official instructions in the project README.
Things to check
- Needs programming knowledge; it is a component, not a finished app
- Full distributed setup is complex and needs Kubernetes
- You must supply your own embedding model, which may need paid API keys
Checked 27 Oct 2026. Summary drafted by AI from the project's README.
