aviary is the pythonic way to run your AI models on geospatial data with minimal boilerplate – from quick prototyping to production-grade pipelines.
-
High-level Python API
Define and run pipelines from composable components instead of writing ad‑hoc scripts -
Config‑driven CLI
Define and run the same pipelines with the command-line interface using a simple declarative config file -
Extensible by design
Add custom components via a plugin registry and distribute them as a plugin package -
AI framework-agnostic
Use models from PyTorch, TensorFlow, ONNX, or scikit‑learn
Installation
pip install geospaitial-lab-aviary
Note that aviary requires Python 3.10 or later.
Have a look at the installation guide for further information.
uv pip install geospaitial-lab-aviary
Note that aviary requires Python 3.10 or later.
Have a look at the installation guide for further information.
docker pull ghcr.io/geospaitial-lab/aviary
Have a look at the installation guide for further information.
Next steps
Have a look at the how-to guides to get started.
License
aviary is licensed under the GPL-3.0 license .