The post asks about the arguments the chat method of a chat engine takes and how to make the response faster. The comments suggest that the main requirement for querying is the query itself, and optionally the chat history. Community members also recommend using streaming to get the response faster, without waiting for the entire response to generate. They provide example code for streaming the response. Additionally, community members mention that the response time depends on the hardware if using an open-source language model. They also suggest referring to the documentation for more information on streaming support and accessing custom prompts.
