WhyLabs Launches LangKit for Safe and Responsible Large Language Models

Seattle-based startup, WhyLabs has announced the release of its open-source technology, LangKit, which is designed to assist enterprises in monitoring and safeguarding their large language models (LLMs). LangKit enables users to locate and prevent toxic language, data leakage, hallucinations, and jailbreaks and is easy to use and integrate with several popular platforms and frameworks such as Hugging Face Transformers, AWS Boto3, and more. The LangKit is built on two core principles of open sourcing and extensibility, allowing it to accommodate diverse customer needs, particularly in industries with higher safety standards such as healthcare and fintech. Early feedback shows the solution’s out-of-the-box metrics, ease of use, and plug-and-play capabilities are proving particularly valuable to stakeholders in regulated industries. The solution will be integrated into WhyLabs’ AI observability platform, which also offers solutions for monitoring other types of AI applications such as embeddings, model performance, and unstructured data drift.