GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — GitHub - hulsedev/hulse-py: The Python client for the Hulse platform

BranchesTags
Open more actions menu

Latest commit

 

History

76 Commits
76 Commits

Folders and files

NameName
Last commit message
Last commit date
.github/workflows
.github/workflows
 
 
docs
docs
 
 
examples
examples
 
 
hulse
hulse
 
 
scripts
scripts
 
 
.gitignore
.gitignore
 
 
LICENSE
LICENSE
 
 
README.md
README.md
 
 
requirements.txt
requirements.txt
 
 
setup.py
setup.py
 
 

Repository files navigation

hulse-py

Welcome to Hulse's Python Client! Hulse is currently in beta.

With your team's untapped computing power, Hulse makes self-hosting state-of-the-art open-source AI models easier. Start reading below to learn how to use the Hulse API, and set up the Hulse desktop app.

If you have questions or want to talk about anything related to Hulse, you are welcome to join the discussion on Github!

Installation

To install hulse-py:

pip install hulse

or from source, using this repository:

git clone [email protected]:hulsedev/hulse-py.git
pip install -e .

Setting Up

To run the example below, you'll need an active Hulse API key, to be part of a Hulse cluster, and at least one running host in your cluster. If you're not sure whether you have these three things set up, follow these steps:

hulse login
hulse create-cluster --name=<your-cluster-name> --description=<your-cluster-description>
hulse host

An alternative to running the host from the CLI is to download the macOS app (currently only available for Intel CPUs) from the dashboard. You may also manage your clusters and API key there.

Getting Started

At this stage, make sure you've retrieved your API key either using the CLI by running hulse get-api-key or from the dashboard.

Here is a simple example of how to run queries using Hulse, and the Hugging Face Transformers' pipeline:

import hulse

API_KEY = "<your-api-key>"
task = "text-classification"
# tweet https://twitter.com/GretaThunberg/status/1460159146720997377
data = "A reminder: the people in power don’t need conferences, treaties or agreements to start taking real climate action. They can start today. When enough people come together then change will come and we can achieve almost anything. So instead of looking for hope - start creating it."
client = hulse.Hulse(api_key=API_KEY)
client.query(task=task, data=data)

Here, we run a query using a text-classification model, which gives a prediction of the text's sentiment. The provided data comes from this tweet from Greta Thunberg.

Learn more

  • Hulse Tutorials
  • hulse-py Docs
  • the example folder for more information

About

The Python client for the Hulse platform

hulse.app

Topics

betadistributed-computinggrid-computingnlp

Resources

Readme
MIT license
Activity
Custom properties

Stars

6 stars

Watchers

0 watching

Forks

1 fork
Report repository

Releases

Packages

Used by

Contributors

Languages

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.