This repository has been archived by the owner on Jun 17, 2023. It is now read-only.
Concurrency and exponential backoff. 3.5 turbo 16k #1
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I don't have access to gpt-4 unfortunately, so you may want to change those parameters back. I did switch to the newer 3.5 16k context model. I know your retry method works, but I've been using the backoff lib and switched to that for simplicity sake. I also switched to a steaming context for the main conversation. I left your normal chat function for the KB articles and user profile updating though. They should be updating in the background using a threads. Due to streaming I also added the tiktoken lib to calculate the current token usage of the conversations that stream.