Skip to main content

Model components for PyMilvus, the Python SDK for Milvus

Project description

Milvus Model Lib

The milvus-model library provides the integration with common embedding and reranker models for Milvus, a high performance open-source vector database built for AI applications. milvus-model lib is included as a dependency in pymilvus, the Python SDK of Milvus.

milvus-model supports embedding and reranker models from service providers like OpenAI, Voyage AI, Cohere, and open-source models through SentenceTransformers.

milvus-model supports Python 3.8 and above.

Installation

If you use pymilvus, you can install milvus-model through its alias pymilvus[model]:

pip install pymilvus[model] 
# or pip install "pymilvus[model]" for zsh.

You can also install it directly:

pip install pymilvus.model

To upgrade milvus-model to the latest version, use:

pip install pymilvus.model --upgrade

If milvus-model was initially installed as part of the PyMilvus optional components, you should also upgrade PyMilvus to ensure compatibility. This can be done with:

pip install pymilvus[model] --upgrade

If you need to install a specific version of milvus-model, specify the version number:

pip install pymilvus.model==0.3.0

This command installs version 0.3.0 of milvus-model.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pymilvus_model-0.3.0.tar.gz (34.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pymilvus.model-0.3.0-py3-none-any.whl (44.1 kB view details)

Uploaded Python 3

File details

Details for the file pymilvus_model-0.3.0.tar.gz.

File metadata

  • Download URL: pymilvus_model-0.3.0.tar.gz
  • Upload date:
  • Size: 34.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.5

File hashes

Hashes for pymilvus_model-0.3.0.tar.gz
Algorithm Hash digest
SHA256 d79b9c410e362262e1bf42ef9e2fa63dd37e75c981bb61c6988df08d250f6a43
MD5 5f1f8944fd32acc8d0ff5639444108f9
BLAKE2b-256 54925e632e3b711acc53e70b25189a4d429ef77e38821fd185277be803046ec0

See more details on using hashes here.

File details

Details for the file pymilvus.model-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: pymilvus.model-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 44.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.5

File hashes

Hashes for pymilvus.model-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 05c0ce5cbd073f7dab77d1ab805110b31059ffe53811a78f99a6b5729b7a2b6b
MD5 ae8a0b536b33fd4ac963b0a3d0ed7f69
BLAKE2b-256 adcbbff523501ac914388bf504d4de190b9c9722692fffd75422e3b0c452a625

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page