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
I wonder if this is currently possible or on the roadmap:
The idea is a ProviderChain per feature (TextGen, ToolCalling, STT, TTS), with three tiers:
Platform Native (Apple Foundation Models, Gemini Nano on Android)
Local (llama.cpp, Whisper ONNX, Piper ONNX)
Remote (cloud API — your backend or third-party)
Each tier can be enabled/disabled, and the SDK resolves the best available provider at runtime. Library developers set sensible defaults; app developers can override at init; end users can override at runtime (if you expose the settings surface).
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
I wonder if this is currently possible or on the roadmap:
The idea is a ProviderChain per feature (TextGen, ToolCalling, STT, TTS), with three tiers:
Each tier can be enabled/disabled, and the SDK resolves the best available provider at runtime. Library developers set sensible defaults; app developers can override at init; end users can override at runtime (if you expose the settings surface).
Beta Was this translation helpful? Give feedback.
All reactions