Google Chrome and Microsoft Edge include on-device AI (Gemini Nano via the Prompt API). To enable it for private, offline plagiarism and semantic analysis, follow these 3 steps:
- Enable Prompt API in Browser Flags:
In your address bar, open: chrome://flags/#prompt-api-for-gemini-nano
(or edge://flags for Microsoft Edge)
Set it to Enabled. - Enable On-Device Model Requirement Bypass:
In your address bar, open: chrome://flags/#optimization-guide-on-device-model
Set it to Enabled BypassPerfRequirement. - Relaunch Browser & Check Model Component:
Restart Chrome or Edge, then visit: chrome://components
Find Optimization Guide On Device Model and click "Check for update" to ensure the model is fully downloaded.
Note: When the Prompt API flag is not enabled, RankSmartTools automatically uses the high-precision client-side NLP engine so you can still check documents without any interruption.