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

Backend doesn't handle the maximum number of tokens correctly #47

Open
orpiske opened this issue Mar 27, 2024 · 0 comments
Open

Backend doesn't handle the maximum number of tokens correctly #47

orpiske opened this issue Mar 27, 2024 · 0 comments

Comments

@orpiske
Copy link
Contributor

orpiske commented Mar 27, 2024

Even when setting quarkus.langchain4j.openai.*.chat-model.max-tokens = 4096 it appears that the backend doesn't apply that. After consuming large PDF files, the system start to fail because some models only accept a maximum of 2048 or 4096 tokens.
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
@orpiske