Metadata-Version: 2.1
Name: soli-data-generator
Version: 0.1.0
Summary: Python library for SOLI data generation
Home-page: https://openlegalstandard.org/
License: MIT
Keywords: legal,information,standard,soli,open
Author: ALEA Institute
Author-email: hello@aleainstitute.ai
Requires-Python: >=3.10,<4.0.0
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Legal Industry
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Text Processing :: Markup :: XML
Classifier: Topic :: Utilities
Provides-Extra: search
Requires-Dist: alea-llm-client (>=0.1.0,<0.2.0)
Requires-Dist: faker (>=28.4.1,<29.0.0)
Requires-Dist: soli-python (>=0.1.4,<0.2.0)
Project-URL: Documentation, https://github.com/alea-institute/soli-data-generator
Project-URL: Repository, https://github.com/alea-institute/soli-data-generator
Description-Content-Type: text/markdown

# SOLI Data Generator

SOLI Data Generator is a Python package for generating synthetic legal data using the SOLI (Standards for Open Legal Information) knowledge graph. It provides both procedural and LLM-based generation techniques to create realistic legal text and data.

## Features

- Procedural generation using templates with SOLI and Faker tags
- LLM-based text generation using various AI models
- Easy integration with the SOLI knowledge graph
- Flexible and extensible architecture

## Installation

You can install SOLI Data Generator using pip:

```bash
pip install soli-data-generator
```

## Usage

### Procedural Template Generation

```python
from soli import SOLI
from soli_data_generator.procedural.template import TemplateFormatter

# Initialize the SOLI graph
soli_graph = SOLI()

# Initialize the TemplateFormatter
formatter = TemplateFormatter()

# Define a template with SOLI and Faker tags
template = """
Company: <|company|>
Industry: <|industry|>
Legal Issue: <|area_of_law|>
Document Type: <|document_artifact|>
"""

# Format the template
formatted_text = formatter.format(template)

print(formatted_text)
```

### LLM-based Text Generation

```python
from alea_llm_client import VLLMModel
from soli_data_generator.llm.text import TextGenerator

# Initialize the VLLM model
model = VLLMModel()

# Initialize the TextGenerator
generator = TextGenerator(model)

# Generate text
generated_text = generator()

print(generated_text)
```

## Examples

For more detailed examples, please check the `examples/` directory in this repository.

## Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

## License

This project is licensed under the MIT License.

## Contact

For any questions or concerns, please open an issue on the GitHub repository.

