NeMo-Guardrails
NeMo-Guardrails copied to clipboard
NVIDIA
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
## Description Adds the ability to select a LLM prompt template for value generations and for flow generations by setting a Jiinja variable `{% set template = "" %}` this...
## Description Add support for is_in event parameter comparison operator for match statements with containers. For instance: ``` match Event(x=is_in([1,2,3,4])) ```
## Description This pull request includes fixes to the PII detection and masking flows of PrivateAI, as well as fixes to the prompt security colang 2 flows. ### PII Detection...
### Did you check docs and existing issues? - [x] I have read all the NeMo-Guardrails docs - [x] I have updated the package to the latest version before submitting...
### Did you check docs and existing issues? - [x] I have read all the NeMo-Guardrails docs - [x] I have updated the package to the latest version before submitting...
### Did you check docs and existing issues? - [x] I have read all the NeMo-Guardrails docs - [x] I have updated the package to the latest version before submitting...
### Did you check docs and existing issues? - [x] I have read all the NeMo-Guardrails docs - [x] I have updated the package to the latest version before submitting...
### Did you check the docs? - [x] I have read all the NeMo-Guardrails docs ### Is your feature request related to a problem? Please describe. Hi, there is no...
### Please also confirm the following - [x] I have searched the [main issue tracker](https://github.com/NVIDIA/NeMo-Guardrails/issues) of NeMo Guardrails repository and believe that this is not a duplicate ### Issue Kind...
How about adding a validate option where we pass in a provider/model so we can check if it's supported by Guardrails? _Originally posted by @tgasser-nv in https://github.com/NVIDIA/NeMo-Guardrails/pull/1088#pullrequestreview-2765491913_