Another day, another question! I've got a pretty cool gradio interface set up with my own index and a QuestionAnswerPrompt against the index.as_query_engine. However, it seems that each question is distinct (e.g., there's no continuity from message to message). Is there a way to begin with the prompt, and then ask follow-up questions in this context? A la ChatGPT?
Yea, llama index is focused on search/retrieval/synthesis. So if you need a chat interface, you can use llama index as a custom tool in some agent, like langchain (or possibly even the new huggingface agents, I need to experiment with those still)
