Skip to main content

Deploy SentenceTransformers embedding models to a ray cluster

Project description

ray-embedding

A Python library for deploying SentenceTransformers models to a ray cluster. This tool encapsulates inference logic that uses SentenceTransformers to load any compatible embedding model from the Hugging Face hub and compute embeddings for input text.

This library is meant to be used with the embedding-models Ray cluster.

Refer to this Ray Serve deployment config to see how this library is used.

Supports the following backends

  • pytorch-gpu
  • pytorch-cpu

Planned:

  • onnx-gpu
  • onnx-cpu
  • openvino-cpu

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distribution

ray_embedding-0.13.8.tar.gz (8.1 kB view details)

Uploaded Source

Built Distribution

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

ray_embedding-0.13.8-py3-none-any.whl (9.8 kB view details)

Uploaded Python 3

File details

Details for the file ray_embedding-0.13.8.tar.gz.

File metadata

  • Download URL: ray_embedding-0.13.8.tar.gz
  • Upload date:
  • Size: 8.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for ray_embedding-0.13.8.tar.gz
Algorithm Hash digest
SHA256 0803f24ee7bdaea0f0df0f2378e8f1352241c58b0769384e380d74016bd68086
MD5 050036c78b91b0bd1fdf8eb8d506e6bb
BLAKE2b-256 f986e1ba730a8b779383199d2766572ddc23970f8ce72a89335943177fb44713

See more details on using hashes here.

File details

Details for the file ray_embedding-0.13.8-py3-none-any.whl.

File metadata

  • Download URL: ray_embedding-0.13.8-py3-none-any.whl
  • Upload date:
  • Size: 9.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for ray_embedding-0.13.8-py3-none-any.whl
Algorithm Hash digest
SHA256 5948cb8f6e387dad5091eaee6b25da1453882598449183136fb79687feb50cba
MD5 ba9d50bbb975d8087a51d8896a404676
BLAKE2b-256 a1000dba52c7ec995a28dc236ea165578257bebdf18f5cec795d6bd17424f6c4

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