Python SDK Reference

MilvusClient provides a simple and easy-to-use alternative to the legacy ORM approach. It adopts a purely functional approach to simplify interactions with the server. Each MilvusClient establishes a gRPC connection to the server you specified. To set up multiple connections, you can create multiple MilvusClient instances.

Install & Update

You can run the following command in your terminal to install the latest PyMilvus or update your PyMilvus to this version.

pip install --upgrade pymilvus==v2.3.7

After the installation, you can check the pymilvus version by running the following

from pymilvus import __version__

print(__version__)

# v2.3.7

Connect to Cluster

from pymilvus import MilvusClient

# Authentication enabled with a cluster user
client = MilvusClient(
    uri="https://inxx-xxxxxxxxxxxx.api.gcp-us-west1.zillizcloud.com:19530",
    token="user:password", # replace this with your token
)

What's New

In this version, PyMilvus adds a MilvusClient module that incorporates several functional methods, aligning its functionality overall with that of the legacy ORM module.

DataImport [READ MORE]

Modules and classes related to the import of large-volume data into a collection.

EmbeddingModels [READ MORE]

Embedding models for you to embed unstrucctured data into vector embeddings.

MilvusClient [READ MORE]

An easy-to-use alternative to the legacy PyMilvus SDK.

ORM [READ MORE]

PyMilvus ORM modules, classes, and methods

Rerankers [READ MORE]

Reranking models for a sophisticated evaluation and refinement on retrieved results.

Examples

In addition to the documents, you can also refer to the example sets in our GitHub repo.