Back to explore

Jev-demo med on-device-modeller

Desert Ant Labs visar en demo som kombinerar Jev med on-device-modeller: Ear identifierar språket, Voz transkriberar, Redact tar bort PII och Jev fattar cirka 20 beslut i ett anrop utan LLM i loopen.

Jev + on-device models = results in seconds with no LLM in the loop. Quick demo app to show the possibilities. Drop in an audio file: Ear detects the language, Voz transcribes it and Redact removes PII. Then @typesafeai's Jev makes about 20 decisions in one call in

· 3 likesOpen on X