Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Wrong conversation summary size vs MAX_TOKENS #610

Open
delfer opened this issue Jul 3, 2024 · 1 comment
Open

Wrong conversation summary size vs MAX_TOKENS #610

delfer opened this issue Jul 3, 2024 · 1 comment

Comments

@delfer
Copy link

delfer commented Jul 3, 2024

Config

OPENAI_MODEL=gpt-3.5-turbo-0125
MAX_TOKENS=16385

Output

2024-07-03 14:39:30,037 - root - INFO - Chat history for chat ID 352569383 is too long. Summarising...
2024-07-03 14:39:34,054 - root - ERROR - This endpoint's maximum context length is 16385 tokens. However, you requested about 17537 tokens (39 of text input, 1113 of tool input, 16385 in the output). Please reduce the length of either one.

Problem: when history too long it summarised to MAX_TOKENS. End then sends to model with MAX_TOKENS+input+tool_input tokens whith is more than MAX_TOKENS
@delfer
Copy link
Author

delfer commented Jul 4, 2024

fixed in #614

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@delfer