search

NVIDIA / NeMo-Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Other
4.21k stars 400 forks source link

Dynamic loading trouble #734

Closed nhantran0506 closed 1 month ago

nhantran0506 commented 2 months ago

Hi, I wonder how can we load the config in dynamic way. In my case, the colang file and actions.py file stay the same among model, but I can't find a way to load different model as the main model

Pouyanpi commented 1 month ago

Hi @nhantran0506, apologies for the delay. Just to clarify, have you tried passing the llm while instantiating the LLMRails class? You can also use its 'update_llm' method.

nhantran0506 commented 1 month ago

Hi @nhantran0506, apologies for the delay. Just to clarify, have you tried passing the llm while instantiating the LLMRails class? You can also use its 'update_llm' method.

I don't know we can do that, I try to find the document for this but can't be found, could you send me the document linl please ?