opengeolab-geocopilot 0.3.0

GeoCopilot: a Codex-powered geospatial research agent for JupyterLab

GeoCopilot for JupyterLab

GeoCopilot is a Codex-powered geospatial research agent embedded in the right side of JupyterLab. The Python distribution installs all three parts together:

• the prebuilt JupyterLab 4 frontend extension;
• the Jupyter Server backend and notebook execution tools;
• the bundled OpenGMS platform skill, activated only by an explicit user request.

Install

GeoCopilot requires Python 3.9 or later, JupyterLab 4, Node.js, and the Codex CLI.

npm install -g @openai/codex
python -m pip install opengeolab-geocopilot

Open GeoCopilot in JupyterLab and select the settings button in the panel header. Enter the API key, base URL, and model in the LLM settings dialog. The key is stored for the current Jupyter user in ~/.jupyter/geocopilot/settings.json with owner-only permissions, is never returned to the browser, and is applied to new tasks immediately.

Environment variables remain available for managed deployments:

export OPENAI_API_KEY="your-api-key"
export JUPYTER_AGENT_CODEX_MODEL="gpt-5-mini"
# Optional for an OpenAI-compatible gateway:
export JUPYTER_AGENT_CODEX_BASE_URL="https://example.com/v1"

jupyter lab

The package automatically enables its Jupyter Server Extension. Verify the installation with:

jupyter labextension list
jupyter server extension list
opengms-notebook --help

Install In A Docker Image

For an existing JupyterLab 4 image, install the Codex CLI and this package during the image build:

RUN npm install -g @openai/codex \
&& python -m pip install --no-cache-dir opengeolab-geocopilot==0.2.14

API keys and provider URLs must not be stored in the image. They can be entered through the GeoCopilot settings dialog after launch or injected at container startup for managed deployments. Settings entered through the UI are local runtime data and are not included in the Python package or Docker image. OpenGMS model discovery and metadata use the bundled static catalog; model execution uses the configured OpenGeoLab API gateway. Data-method discovery, metadata lookup, and execution connect directly to the OpenGMS Data Method service. Configure private deployments with OPENGMS_DATA_METHOD_API_URL and OPENGMS_DATA_METHOD_TOKEN; keep the token outside the image and repository.

Build A Release

Install release tooling and run the checked release builder:

python -m pip install -e ".[release]"
./scripts/build-release.sh

The wheel and source archive are written to dist/<version>/. Test an unpublished release with a fresh environment or TestPyPI before uploading it to PyPI.

Publish

Create an API token in PyPI and keep it outside the repository:

export TWINE_USERNAME=__token__
export TWINE_PASSWORD="pypi-your-token"
python -m twine upload dist/0.2.14/*

After publication, downstream systems only need the installation command shown above. A new package version must be published for every update because PyPI does not allow replacing an existing release.