Downloads
Download Milvus
The most scalable vector database for your GenAI Workloads. Check out the Getting Started Guide.
Don’t want to manage it? Sign up for Zilliz Cloud (managed Milvus service) for free. Get Started here.
MilvusThe open source vector database
Milvus is a highly scalable open-source vector database designed for demanding workloads. It supports 10+ index types, including HNSW, DiskANN, Quantization, and Binary, enabling efficient vector similarity search across various use cases. Optimized for different compute hardware, including GPUs, Milvus delivers robust performance for vector search.
Beyond basic vector search, Milvus offers advanced features such as hybrid search, metadata filtering, and grouping search. These capabilities allow developers to build more sophisticated search systems, enhancing the functionality of AI and machine learning applications in areas like recommendation engines, image similarity search, natural language processing (NLP), and retrieval augmented generation (RAG).
Version
Platform
export MILVUS_VERSION=v2.5.0-beta
curl -sfL https://assets.zilliz.com/milvus/standalone_embed.sh -o standalone_embed.sh
bash standalone_embed.sh start
PymilvusMilvus Python SDK & Milvus Lite
PyMilvus is the Python SDK for Milvus. It provides direct methods to insert, search, and manage vector embeddings using Python. It enables Python developers to perform vector similarity searches, build indexes, and handle data operations efficiently. This SDK simplifies Milvus integration, offering an intuitive API that fits naturally into Python projects. PyMilvus allows developers to leverage Milvus's vector database capabilities without writing low-level queries.
Milvus Lite is the lightweight version of Milvus that can run locally within your Python application. It shares the Milvus API, ensuring that your client-side code works for both small-scale local deployments and Milvus servers deployed on Docker or Kubernetes with billions of vectors. Milvus Lite is already included in PyMilvus, so you can simply deploy it with pip install pymilvus.
Version
pip3 install pymilvus
pip3 install pymilvus[model] # for milvus-model
pip3 install pymilvus[bulk_writer] # for bulk_writer