Coming from the european union, I want to design chat bots as data security friendly as possible. The following questions arise: 1. Is it possible to opt out of the training of the content when using ChatGPT? I don't want to allow ChatGPT to train its LLM on the bot's conversations. 2. I would like to define a different LLM (other than ChatGPT) for knowledge base answering (RAG). I have read here: https://discord.com/channels/1108396290624213082/1225442621330034688 that LangChain or StackAI can be used for Knowledge base answering. I am interested in guides to incorporate this into Botpress. Thank you

1. knowledge consumed through OpenAI's API is not used to train ChatGPT, nor do we send that over to them 2. we don't currently support native methods of integrating third-party LLMs, but you're welcome to make API calls to external services by executing custom code

For reference for other people: the first sentence of how we use your data https://platform.openai.com/docs/models/how-we-use-your-data states the same. Thanks for pointing that out Robert