Metadata-Version: 2.4
Name: docling-metrics-text
Version: 0.8.0
Summary: Text metrics
Keywords: docling,metrics,evaluation,example,text,BLEU, edit-distance, METEOR, precision, recall, f1,cpp
Author-Email: Nikos Livathinos <nli@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
License-Expression: MIT
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: Microsoft :: Windows
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3
Project-URL: homepage, https://github.com/docling-project/docling-metrics
Project-URL: repository, https://github.com/docling-project/docling-metrics
Project-URL: issues, https://github.com/docling-project/docling-metrics/issues
Requires-Python: <4.0,>=3.10
Requires-Dist: docling-metrics-core>=0.0.1
Requires-Dist: pydantic
Requires-Dist: RapidFuzz
Requires-Dist: evaluate<0.5.0,>=0.4.3
Requires-Dist: nltk<4.0.0,>=3.9.1
Description-Content-Type: text/markdown

# Docling metric for text

Text metrics:

- BLEU
- edit-distance
- METEOR
- Precision
- Recall
- F1


## Installation

```bash
uv sync --all-packages
```


## Usage

```python
from docling_metrics_text import (
    TextMetrics,
    TextPairEvaluation,
    TextPairSample,
)


# Example 1: Compare two similar texts
sample_1 = TextPairSample(
    id="s1",
    text_a="The quick brown fox jumps over the lazy dog.",
    text_b="The fast brown fox leaps over the lazy dog.",
)

text_metrics = TextMetrics()
evaluation_1: TextPairEvaluation = text_metrics.evaluate_sample(sample_1)
print(f"Sample 1 - Similar texts:\n{evaluation_1}\n")


# Example 2: Compare two very different texts
sample_2 = TextPairSample(
    id="s2",
    text_a="Machine learning is a subset of artificial intelligence.",
    text_b="The weather forecast predicts rain tomorrow afternoon.",
)

evaluation_2: TextPairEvaluation = text_metrics.evaluate_sample(sample_2)
print(f"Sample 2 - Different texts:\n{evaluation_2}\n")
```

