Installation

To get started using Toponymy you first have to get Toponymy installed. Fortunately, this is easy to do. Toponymy is available on PyPI, so you can install it using pip:

pip install toponymy

To get the latest and greatest version of Toponymy, you can also install it from source.

git clone https://github.com/TutteInstitute/toponymy.git
cd toponymy
pip install .

If you would like all the optional dependencies, you can install Toponymy with the dev extra:

pip install .[dev]

This provides the basics to get started, but Toponymy makes use of LLMs and embedding models as well. Instead of havign a very large dependency list, we allow you to install what you need, and different options will become available within Toponymy based on what you have installed.

If you are interested in working with local models, you can install llama-cpp-python or huggingface’s transformers. This will enable you to use the LlamaCpp and HuggingFace models, respectively. For LlamaCpp you will also need to download the models you want to use. You can find the models on HuggingFace or other model repositories. For the HuggingFace models, you can specify the model name and the HuggingFace class will handle the downloading for you.

pip install llama-cpp-python
pip install transformers