-
Notifications
You must be signed in to change notification settings - Fork 936
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
prompty: improve token count estimation #3821
Conversation
Adds tools definitions and tool calls into the computation
This is needed for AzureOpenAI models where the deployment name is not a valid OpenAI model.
Hi, thank you for your interest in helping to improve the prompt flow experience and for your contribution. We've noticed that there hasn't been recent engagement on this pull request. If this is still an active work stream, please let us know by pushing some changes or leaving a comment. |
Hi, any chance to advance with this? |
Hi, thank you for your interest in helping to improve the prompt flow experience and for your contribution. We've noticed that there hasn't been recent engagement on this pull request. If this is still an active work stream, please let us know by pushing some changes or leaving a comment. |
Hi, thank you for your contribution. Since there has not been recent engagement, we are going to close this out. Feel free to reopen if you'd like to continue working on these changes. Please be sure to remove the |
Description
Current token count estimation is incomplete.
This PR adds tools definitions and tool calls into the computation, and allows to define a valid OpenAI model name to use to determine the tokenizer, which is needed in case of Azure OpenAI when the deployment is not a valid OpenAI model name.
Fixes #3809.
All Promptflow Contribution checklist:
General Guidelines and Best Practices
Testing Guidelines