-
Notifications
You must be signed in to change notification settings - Fork 246
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
Integrating BLIP Image Captioning model with UAgents #144
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice one!
I was able to get this to run, but the first time I got an error:
INFO: [blip_user]: Got error from uagent: error='Error: Model Salesforce/blip-image-captioning-large is currently loading'
It might be useful to add some retry logic, especially if this a common error. For example, you could reduce the interval period and add a storage flag to indicate when the caption is successfully generated so that it does not need to continue to make requests.
Hi @jrriehl , I have taken your suggestions/feedback and resolved the issues accordingly. Please have a look. |
Thank you for pointing towards storage feature, I've learned something new. |
integrations/blip-image-captioning-large/src/agents/blip_agent.py
Outdated
Show resolved
Hide resolved
integrations/blip-image-captioning-large/src/agents/blip_agent.py
Outdated
Show resolved
Hide resolved
integrations/blip-image-captioning-large/src/agents/blip_user.py
Outdated
Show resolved
Hide resolved
integrations/blip-image-captioning-large/src/agents/blip_user.py
Outdated
Show resolved
Hide resolved
…ake protocol details available agentverse
@jrriehl made changes as per your comments, please review! |
This example demonstrates the integration of BLIP image captioning into the UAgent Ecosystem. It also provides insight on how large byte data, like images, are passed using encoding to the agent.