whylabs / langkit

🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀
https://whylabs.ai
Apache License 2.0
839 stars 67 forks source link

Split options out of validator into dedicated options class #272

Closed naddeoa closed 7 months ago

naddeoa commented 7 months ago

Doing things this way makes policy parsing a lot easier over on the container side and doesn't impact the library interface. We should consider updating the library to just take in an options object though to make it consistent with the policy/more predictable with regard to the policy.