The post asks if there is a way to create follow-up questions in a chat, where the API could return suggested questions that the user can click on instead of typing. The comments discuss possible solutions, including:
- Asking the language model (LLM) to generate follow-up questions
- Using the Question Generator from the llamaindex library to generate questions based on the queries
- Utilizing structured outputs to have the LLM output both the response to a question and follow-up questions
There is no explicitly marked answer in the comments.
Is there any way to create follow up questions to a chat. For example, the api returns a few suggested questions so that user can just click on them instead of typing it? Attached is a screenshot of this feature.
