https://github.com/NeonGeckoCom/neon_utterance_zeroshot_clf_plugin

https://github.com/NeonGeckoCom/neon_utterance_zeroshot_clf_plugin

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/NeonGeckoCom/neon_utterance_zeroshot_clf_plugin
• Owner: NeonGeckoCom
• Created: 2021-11-23T10:55:25.000Z (about 3 years ago)
• Default Branch: master
• Last Pushed: 2022-02-15T02:12:17.000Z (almost 3 years ago)
• Last Synced: 2024-02-15T15:33:14.514Z (10 months ago)
• Language: Python
• Size: 3.91 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

• awesome-ovos-plugins - neon_utterance_zeroshot_clf_plugin - inject context (OPM plugins / Utterance Transformers)

README

        
```python

tars = TarsZeroShotClassifier()

# NOTE: this usually comes from config and is not set like this

tars.classifiers = {"sentiment": ["happy", "sad"]}

utts = ["I am so glad you liked it!",

        "I get really sad when nobody reviews my PRs"]

_, context = tars.transform(utts)

# context is a dict of clf_name: [prediction(utt) for utt in utterances]

print(context)

# {'zeroshot_classifier': 

# {'sentiment': [[('happy', 0.8667009472846985)], [('sad', 0.9921779036521912)]]}}

```