Hi! I was using ghostrun in one of my RAG projects and realized I needed a way to verify whether the generated answer was actually grounded in the retrieved context. I ended up implementing a solution on my own, and while exploring the repository I noticed ghostrun already provides semantic assertions like contains_intent, tone_is, and matches, but doesn't yet have a dedicated RAG grounding assertion.
I'd love to contribute this back to the project by adding something like:
ghostrun.expect(answer).is_grounded_in(context)
If this aligns with the project's direction, I'd be happy to work on it and open a PR.
Hi! I was using ghostrun in one of my RAG projects and realized I needed a way to verify whether the generated answer was actually grounded in the retrieved context. I ended up implementing a solution on my own, and while exploring the repository I noticed ghostrun already provides semantic assertions like
contains_intent,tone_is, andmatches, but doesn't yet have a dedicated RAG grounding assertion.I'd love to contribute this back to the project by adding something like:
If this aligns with the project's direction, I'd be happy to work on it and open a PR.