SETUP.md

Running CS-Tutor Locally

While cs-tutor is hosted on a Huggingface space, it's easy to run locally on your development machine.

Pre-requisites

You'll need Python installed, preferably 3.10 or higher. Run python --version to check. On systems where you have both Python 2 and 3 installed, you may need to run python3 --version.

Clone the repo

Create a new directory and git clone the repo. From the command line, use git clone https://huggingface.co/spaces/simonguest/cs-tutor

Use pip to install the required Python libraries

From within the cloned cs-tutor directory, run pip install -r requirements.txt' (Note: Depending on your system, you may need to run pip3 instead).

Install Gradio

Run pip install gradio to install the main Gradio library.

Run the application

To run the application, use the following command:

OPENAI_API_KEY=[key] gradio app.py

Replace key with an OpenAI key from your organization. If everything is successful, you should see this message:

Running on local URL: http://127.0.0.1:7861

Open a Web browser to this URL to access the application.

Adding more levels

To add a new level, create a new level number folder in the levels folder. Within this new level folder, create three files:

• metadata.json: a JSON file pointing to the instructions and starter code. See the other levels for the exact format.
• instructions.md: a markdown file with instructions for the AI tutor
• sample_code.py: a Python file with the starter code for the student

To run the level, browser to http://127.0.0.1:7861?level=[level] - replace [level] with the title of the level folder that you created (e.g., http://127.0.0.1:7861?level=4)