ContextCheck: An open-source framework for testing and evaluating LLMs, RAGs, Chatbots

Hey devs!

We just open-sourced ContextCheck, a framework for testing and evaluating LLMs, RAGs, and chatbots 🚀

What it does:

• Generates queries and handles completions
• Detects regressions and hallucinations
• Runs penetration tests
• Works in CI pipelines (YAML-configurable)

We built it while developing our AI Knowledge Base Assistant to solve real headaches with testing and validating LLMs. Now it’s out there for you to use, break, and improve.

Try it out and let us know what you think! ➡️ Github repo