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.

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

Streaming Callback: awaiting .output() if not providing a format #52

Open
cabljac opened this issue May 7, 2024 · 0 comments
Open

Streaming Callback: awaiting .output() if not providing a format #52

cabljac opened this issue May 7, 2024 · 0 comments
Assignees
Labels
bug Something isn't working feature New feature or request

Comments

@cabljac
Copy link
Contributor

cabljac commented May 7, 2024

I was using the generate method.

As far as I understand, we know that a stream has finished when .output() resolves. However when you don't provide an output parameter (as i just want to use .text() in the streaming callback) it seems like .output() will reject:

>  [ERROR]  bolt-app UnknownError: No JSON object or array found in model output: (....the llm text response here, which is what i wanted)```
@i14h i14h added bug Something isn't working feature New feature or request labels Jul 3, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working feature New feature or request
Projects
Status: No status
Development

No branches or pull requests

3 participants