This repository was archived by the owner on Jul 22, 2025. It is now read-only.
Which format is better for continuing the chat? #183
-
Hi. If I want to ask further questions based on the returned messages, do I need to send the entire [user-assistant] messages array, including the thinking process, or not? Are there any best practices? |
Beta Was this translation helpful? Give feedback.
Answered by
james-pplx
Mar 6, 2025
Replies: 1 comment
-
Currently, that is the only way to do it. However, if you plan on asking consecutive questions it may be preferable to not use a CoT model in order to keep your tokens (and hence, your billing) low. Please feel free to share some code snippets and we can further optimize if needed! |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
james-pplx
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Currently, that is the only way to do it. However, if you plan on asking consecutive questions it may be preferable to not use a CoT model in order to keep your tokens (and hence, your billing) low. Please feel free to share some code snippets and we can further optimize if needed!