The community member is trying to use their support chat history, exported to a JSON file, to feed the llama_index. They are wondering how the AI will know the difference between customer questions and chat attendant answers. The community members suggest manually creating Document objects and labeling each one as a "Question:" or "Answer:" to help the AI understand the structure of the data.
Hello, we're trying to use our support chat history (from our database) to feed the llama_index, right now I've exported all the data to a JSON file and put it on the "data" folder (millions of lines). But I was wondering how will the AI know what is the customer question vs what is the chat attendant answer? Is there a way to send like an index for each phrase (QUESTION:, ANSWER:)?
