Razvan Dinu

Currently, there's no built-in mechanism to specify the topic and refuse anything else. A robust solution would be to implement your own custom classifier and train it with enough data...

Hi @koszilard . The conversation you're seeing represents the first two turns from the [sample conversation](https://github.com/NVIDIA/NeMo-Guardrails/blob/develop/docs/user_guides/configuration-guide.md#sample-conversation). You can find the default value [here](https://github.com/NVIDIA/NeMo-Guardrails/blob/develop/nemoguardrails/rails/llm/default_config.yml#L1-L9). You can override it with something more...

Not yet. A contribution here would be welcome if anyone can help.

@Lumpylam: yes, it should be possible. If you try and run into issues, let us know.

@rohitgarud @Komal-99 , the error message is indeed misleading. This exception is thrown when there is no LLM configured in the config. To fix the original example, there are two...

Hi @Isaac-AC! Unfortunately, executing actions by name is not supported. The only work around I can think of is to also define a flow for each tool and call the...

@Pratekh : can you provide more details on the config (e.g., the content of `config.yml`)? This is probably a configuration issue.

@rohitk-cognizant : to debug this, can you try to get a functional code where you initialize the LLM separately, in a "pure LangChain way". ```python model = AzureOpenAI(...) print(model.invoke("test prompt")...

Thanks for the fix @HanchenXiong! We need you to sign the commit before merging: https://github.com/NVIDIA/NeMo-Guardrails/blob/develop/CONTRIBUTING.md#submitting-your-work. Feel free to force-push the branch.

@HanchenXiong : friendly ping regarding signing the commit. Thanks!