The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems.
This change makes scoring using SelfAskLLM scorers more reliable because JSON tags are stripped (this is a known weird response and we handle it centrally for our JSON converters)
This change makes scoring using SelfAskLLM scorers more reliable because JSON tags are stripped (this is a known weird response and we handle it centrally for our JSON converters)