-
Notifications
You must be signed in to change notification settings - Fork 617
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
fix: Add a graph named "voice_assistant_multimodal" in the property.son of default. #589
Conversation
LGTM |
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.
LGTM
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.
you should register nova as a llm module in playground moduleConfig.ts
the concept of playground is using the same connections while developers are able to switch modules. if you believe video feature is needed, it should rather be a option feature flag for llm module.
to conclude,
- add nova to llm registry in moduleConfig.ts
- in moduleConfig.ts for llm module add an option
modalities=["image", "text"]
- change ChatCfgModuleSelect.tsx so that a connection from rtc to llm will be added when a llm module accepts image input
…"image", "text"] change ChatCfgModuleSelect.tsx so that a connection from rtc to llm will be added when a llm module accepts image input
Some developers are confused about debugging the Amazon Nova multimodal model, so we are adding a copy of the demo graph to the default configuration.