Zayd

updated as part of latest sprint

Hey James, this is a great idea. The team talked it through, and this is the correct approach! When a pydantic model is given, a pydantic model should be returned....

This seems more like it's passing too many requests to the create constructor. Can you try removing temperature and max_tokens and see if it works?

Hi! This is a great idea, I'll look through litellm docs to see if this is supported currently.

Great discussion. I think that using both is ideal EXCEPT for the added latency. We should see if we could parallelize the two reqs and not hurt perf. If so,...

imo SimlarToList or SimilarToValues are better names than previous values (that's not a strong opinion though). When last I used the validator, it seemed unintuitive to pass `prev_values` as a...

closing - been a while, we have these on the hub submission https://hub.guardrailsai.com/validator/guardrails/similar_to_previous_values

Hey Muhammad, In that case, you would wrap the model invocation in a custom callable, following the docs [here](https://www.guardrailsai.com/docs/integrations/llm_api_wrappers#using-a-custom-llm-api). In this case it could be as simple as ``` def...

Imagine we have a guard output structure with 10 fields defined in it and each field has validators. If we make an LLM call and validate that guard, and 9...

reopening, good feature request