Metadata-Version: 2.4
Name: guepard-relml
Version: 0.1.1
Summary: RelML — relational deep learning with a natural-language agent over your database.
Keywords: relational,machine-learning,graph-neural-network,graphsage,database,agent,duckdb
Author: Guepard Corp
License-Expression: MIT
License-File: LICENSE
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: C++
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Operating System :: MacOS
Classifier: Operating System :: POSIX :: Linux
Project-URL: Homepage, https://github.com/Guepard-Corp/relml
Project-URL: Repository, https://github.com/Guepard-Corp/relml
Project-URL: Issues, https://github.com/Guepard-Corp/relml/issues
Requires-Python: >=3.9
Requires-Dist: duckdb>=0.9
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: pytz
Requires-Dist: anthropic>=0.40
Requires-Dist: prompt_toolkit
Requires-Dist: scikit-learn
Provides-Extra: api
Requires-Dist: fastapi; extra == "api"
Requires-Dist: uvicorn; extra == "api"
Provides-Extra: plots
Requires-Dist: matplotlib; extra == "plots"
Description-Content-Type: text/markdown

# guepard-relml

A natural-language agent over your relational database: ask a question in plain
English and it explores your schema, builds a predictive model, and answers.

## Install

Requires Python 3.9+. Install into a virtual environment:

```bash
python3 -m venv .venv && source .venv/bin/activate
pip install guepard-relml
```

> On Debian/Ubuntu, `error: externally-managed-environment` just means the venv
> step was skipped — the two commands above are the fix.

## Configure

The agent uses a language model. Set one API key:

```bash
export ANTHROPIC_API_KEY=...
```

## Use

```bash
relml-agent --source ./data                              # interactive
relml-agent "who is likely to churn next month?" --source ./data   # one-shot
```

`--source` accepts a folder of CSVs, a CSV/Parquet file, or a Postgres DSN.

## License

MIT
