Error message has incorrect model engine name of nemo-infer instead of ai-playground

[nathankw]

RetrievalAugmentedGeneration.common.utils.get_llm() reports the incorrect model_engine name in the last line of the function in error string. Says "Supported engines are triton-trt-llm and nemo-infer", but should say "Supported engines are triton-trt-llm and ai-playground".

In the config.yaml file, we must specify llm.model_engine as one of [triton-trt-llm, ai-playground].

[mohammedpithapur]

hii i am new here i have corrected the error msg now i am confused in config.yaml , previously it was model_engine="triton-trt-llm", now should i add both triton-trt-llm, ai-playground in a list or just separate them by comma

[shubhadeepd]

@mohammedpithapur Thanks for fixing the error message! It should be either model_engine: "triton-trt-llm" OR model_engine: "ai-playground"

[mohammedpithapur]

Can you suggest how I can do it, sorry I am new

[shubhadeepd]

@mohammedpithapur we now have a dedicated example to showcase AI playground in latest codebase! No config file changes are needed (this avoids the confusion you faced). Please checkout the example here https://github.com/NVIDIA/GenerativeAIExamples/blob/main/RetrievalAugmentedGeneration/README.md#1-qa-chatbot----nvidia-ai-foundation-inference-endpoint