Azure / PyRIT

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
https://azure.github.io/PyRIT/
MIT License
1.95k stars 372 forks source link

DOC combine datasets notebooks into one #400

Open romanlutz opened 2 months ago

romanlutz commented 2 months ago

Describe the issue linked to the documentation

We started with one notebook per dataset (in the doc/code/orchestrators directory) and now it's becoming a lot. Since they all pretty much follow the same structure we should just have one overall and show the various datasets in their own sections.

Additional Information

Here are the current notebooks about datasets, which should be consolidated into one standard notebook:

bhavanaeh commented 1 month ago

Hi, is the expectation such that you just have one notebook which has all the code for all the datasets?

nina-msft commented 1 month ago

Hey @bhavanaeh !

That's the idea. We have one notebook per dataset at the current moment. Roman is asking for one Python Notebook on datasets since they have the same structure. You can then use each Dataset as an example in that notebook.

For example: https://github.com/Azure/PyRIT/blob/main/doc/code/targets/3_custom_targets.ipynb The custom targets notebook is one notebook with several examples.

I'd imagine the Datasets notebook would look similar, with examples for each dataset integration. I just updated the description of the issue to have links to all of the notebooks which currently talk about Datasets.

bhavanaeh commented 1 month ago

Awesome, thank you so much! If this is still up for grabs, I'd like to take a stab at it :)

nina-msft commented 1 month ago

You got it - thank you @bhavanaeh 🦝