Skip to content


Cog plays nicely with Jupyter notebooks.

Install the jupyterlab Python package#

First, add jupyterlab to the python_packages array in your cog.yaml file:

    - "jupyterlab==3.3.4"

Run a notebook#

Cog can run notebooks in the environment you've defined in cog.yaml with the following command:

cog run -p 8888 jupyter lab --allow-root --ip=

Use notebook code in your predictor#

You can also import a notebook into your Cog Predictor file.

First, export your notebook to a Python file:

jupyter nbconvert --to script my_notebook.ipynb # creates

Then import the exported Python script into your file. Any functions or variables defined in your notebook will be available to your predictor:

from cog import BasePredictor, Input

import my_notebook

class Predictor(BasePredictor):
    def predict(self, prompt: str = Input(description="string prompt")) -> str:
      output = my_notebook.do_stuff(prompt)
      return output