milvus-io/pymilvus

Python SDK for Milvus Vector Database

What it solves

It provides a Python interface for interacting with Milvus, a vector database designed for managing and searching high-dimensional vector embeddings. This allows developers to integrate vector search capabilities into their Python applications without needing to write low-level API calls.

How it works

PyMilvus acts as a Python SDK that communicates with the Milvus server. It handles the translation of Python commands into requests that the Milvus server can process, providing a convenient wrapper around the database's core functionality.

Who it’s for

Python developers building AI applications that require efficient storage, indexing, and retrieval of vector embeddings (such as for RAG or similarity search).

Highlights

  • Support for a wide range of Milvus server versions (from 1.0 to 3.0).
  • Optional installation components for milvus-model and bulk_writer.
  • Comprehensive test suites including unit and integration tests.
  • Apache License 2.0.

Related

  • Project
    milvus-io/milvus-sdk-java

    The Milvus Java SDK is the official Java client for the Milvus vector database, letting Java developers connect to and use Milvus from their applications.

  • Project
    milvus-io/milvus

    Milvus is a high-performance, distributed vector database built for scaling AI applications that require efficient search and organization of massive amounts of unstructured data.

  • Project
    milvus-io/milvus-lite

    Milvus Lite is a pure‑Python, local‑only version of the Milvus vector database. It provides a drop‑in `pymilvus`‑compatible API for storing dense and sparse vectors, scalar fields, and full‑text data, and supports similarity search, filtering, and hybrid (vector + text) queries. Designed for notebooks, tests, and small prototypes, it runs either as a local `.db` file, an embedded engine, or a lightweight gRPC server, and can later be swapped to a full Milvus deployment with minimal code changes.

  • Project
    pinecone-io/python-sdk

    A Python client for Pinecone’s vector database, enabling creation of indexes, upserting JSON‑document records with dense vectors, and performing similarity searches (sync or async).

  • Project
    qdrant/qdrant-client

    Qdrant Client is the official Python SDK for Qdrant, a vector search engine. It provides sync and async APIs, local in-memory or persistent storage for prototyping, and support for REST, gRPC, and cloud connections, plus an inference API for generating embeddings.