You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When I ask something which requires to generate long message, it will be cut off although it hasn't finished yet. I think it because of the hard-coded 1000 max_tokens
<html><body><scriptsrc="https://js.puter.com/v2/"></script><script>(async()=>{constresp=awaitputer.ai.chat([{"role":"user","content":"Can you help me to create a chess game in React ?"}],{model: 'claude-3-5-sonnet',stream: true});forawait(constpartofresp)puter.print(part?.text?.replaceAll('\n','<br>'));})();</script></body></html>
Expected behaviour
No response
Addition Information or Screenshots (if applicable)
No response
Deployment
Production (puter.com)
Development (npm run start)
Docker (via docker run)
Docker (via docker-compose)
Puter version
No response
The text was updated successfully, but these errors were encountered:
Issue Description
When I ask something which requires to generate long message, it will be cut off although it hasn't finished yet. I think it because of the hard-coded 1000 max_tokens
Steps to reproduce
Expected behaviour
No response
Addition Information or Screenshots (if applicable)
No response
Deployment
npm run start
)docker run
)docker-compose
)Puter version
No response
The text was updated successfully, but these errors were encountered: