I am exploring the possibility of integrating a chatbot into a training program, designed to assist learners who are required to undertake professional development for specific reasons. The idea is to enable these learners to engage in a 15-minute learning session with the chatbot, where their interaction time could be tracked and logged. Furthermore, we are considering the potential of uploading domain-specific knowledge documents into a custom GPT model, enabling the chatbot to access and leverage this specialized information during interactions. Our question revolves around the reliability of the chatbot consistently referring to the uploaded domain knowledge throughout a session. We understand that general world knowledge will also contribute to the chatbot’s responses, but we are interested in whether there is a method to distinctly mark or differentiate the domain-specific information used in the chatbot’s replies. Is such a setup feasible?
What else is there to know about domain knowledge in relation to custom GPTs?