To connect to your endpoint you need a client that knows how to work with that type of endpoint.
Make sure to check the pyrit.chat
module for existing clients such as AzureOpenAIChat
.
If no corresponding class exists, you can write your own and implement the ChatSupport
interface.
If you do this please consider contributing your new client back to PyRIT.
First, you need to find the corresponding conda environment for your project. You can do this with the following command:
conda env list
Then activate it using
conda activate <env_name>
Next, you need to install the IPython kernel in the virtual environment.
pip install ipykernel
python -m ipykernel install --user --name=pyrit_kernel
Now you can start Jupyter Notebook:
jupyter notebook
Once the notebook is open, you can select the kernel that matches the name you gave earlier.
To do this, go to Kernel > Change kernel > pyrit_kernel
.
Now your Jupyter Notebook should be able to find and import the libraries installed in your conda environment.