Metadata-Version: 2.4
Name: auto-labeler-ai
Version: 0.1.3
Summary: A pragmatic AI-powered data labeling library.
Project-URL: Homepage, https://github.com/ajit3259/Auto-Labeler
Project-URL: Repository, https://github.com/ajit3259/Auto-Labeler
Project-URL: Documentation, https://ajit3259.github.io/Auto-Labeler
Author: Ajit Kumar
Keywords: ai,annotation,data-science,labeling,llm,nlp
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Requires-Dist: click
Requires-Dist: diskcache
Requires-Dist: jinja2>=3.0.0
Requires-Dist: litellm>=1.0.0
Requires-Dist: numpy
Requires-Dist: pandas>=2.0.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: python-dotenv
Requires-Dist: pyyaml
Requires-Dist: scikit-learn
Requires-Dist: tenacity
Provides-Extra: test
Requires-Dist: pytest; extra == 'test'
Requires-Dist: pytest-asyncio; extra == 'test'
Description-Content-Type: text/markdown

# Auto-Labeler

An AI-powered data labeling library for Python.

## Key Features
- **🔍 Discovery**: Automatically suggest labels/taxonomy using Iterative or Embedding-based discovery.
- **🏷️ Assignment**: Labels your dataset using LLMs (Gemini, OpenAI, Anthropic, etc.).
- **⚡ Batching & Async**: High-throughput processing for large datasets.
- **💾 Disk Caching**: Save costs and time with local persistence.
- **💰 cost Tracking**: Real-time USD cost estimation for every run.
- **🛡️ Validation**: Pydantic-powered fail-fast checks for your data.

## Installation
```bash
pip install auto-labeler-ai
```

## Quick Start
```python
from auto_labeler import AutoLabeler
import pandas as pd

labeler = AutoLabeler(model_name="gemini/gemini-2.5-flash")
results = labeler.label_dataset(
    pd.read_csv("data.csv"),
    labels=["Urgent", "Billing", "General"],
    context="Customer support tickets"
)
print(results[["text", "label"]])  # output column is always 'label'
print(labeler.get_usage())
```

## Documentation
For full guides on Advanced discovery, Caching, and API reference, visit our:
👉 **[Documentation Site](https://ajit3259.github.io/Auto-Labeler)**

## Testing
```bash
pytest
```

## License
MIT

