Metadata-Version: 2.4
Name: easekit
Version: 1.0.0
Summary: A metric to evaluate empathy in dialogue systems
Home-page: https://github.com/srishtigupta253/easekit
Author: Srishti Gupta
Author-email: srishtig253@gmail.com
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: torch
Requires-Dist: transformers
Requires-Dist: scikit-learn
Requires-Dist: nltk
Requires-Dist: vaderSentiment
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# EASE Metric

`easekit` is a composite metric to evaluate empathy in dialogue systems. It incorporates:

- **Semantic Relevance**
- **Sentiment Alignment**
- **Contextual Word Overlap**

## Installation

```bash
pip install easekit
```

To use the metric:
```bash
from transformers import AutoTokenizer, AutoModel
from easekit import compute_empathy_score

context = "I am very upset"
response = "Why? Is everything alright?"
reference = "Why? What happened?"

model_name = "sentence-transformers/paraphrase-MiniLM-L6-v2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)

result = compute_empathy_score(context, response, reference, model, tokenizer)
print(result)
