Milvus is a cloud-native vector database designed for scalable approximate nearest neighbor (ANN) search and real-time streaming updates across vast amounts of unstructured data. It supports hybrid search, hardware acceleration, and multiple data connectors, and can be run locally via a Python library or deployed as a managed service.
Project overview
The project scales horizontally to handle tens of thousands of search queries on billions of vectors and natively integrates full text search with dense and sparse vectors.
Project type
RAG · AI Search · Vector Database
Use cases
Knowledge Q&A · Search & Research
Deployment
Docker / Docker Compose
License
Apache-2.0
Best for
Developers, data teams, and AI engineers building enterprise RAG and AI search applications who require scalable vector ANN search and real-time streaming updates.
Key capabilities
Executes efficient vector ANN search, range search, and hybrid search with metadata filtering.
Natively supports full text search with BM25 and learned sparse embeddings (SPLADE, BGE-M3) alongside dense vectors.
Ensures data security via mandatory user authentication, TLS encryption, and Role-Based Access Control (RBAC).
Implements hardware acceleration for CPU/GPU to achieve vector search performance targets.
Python SDK to interact with Milvus for creating collections, ingesting data, and performing searches.
Limitations and risks
Building the system from source requires specific toolchain versions and operating system constraints.
Interaction via the library or API requires coding to create collections, ingest data, and perform searches.
The system architecture allows for optional external services and paid dependencies, such as the optional Zilliz Cloud managed service.
Getting started
Setup is rated as easy for local execution. The first success path involves installing the PyMilvus SDK via 'pip install -U pymilvus', instantiating a MilvusClient with a local database file, and calling create_collection.
Evidence and sources
GitHub project description: Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
README: The Milvus open-source project is under LF AI & Data Foundation, distributed with Apache 2.0 License, with Zilliz as its major contributor.
README: 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, im…
README: 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 eff…
README: Milvus integrates with a comprehensive suite of AI development tools, such as LangChain, LlamaIndex, OpenAI and HuggingFace, making it an ideal vector store for GenAI applications…