google-ai-edge/gallery：README 來源編輯指南

google-ai-edge/gallery 的 README 將專案描述為「A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.」。本文只整理倉庫可直接核對的內容，不把 star、Fork 或宣傳語當成品質證明。README 在「Google AI Edge Gallery ✨」下寫到：Explore, Experience, and Evaluate the Future of On-Device Generative AI with Google AI Edge.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「✨ Core Features」與相關條目，可以先判斷它是否處理你的實際問題：AI Chat with Thinking Mode: Engage in fluid, multi-turn conversations and toggle the new Thinking Mode to peek "under the hood." This feature allows you to see the model's step-by-step reasoning process, which is perfect for understanding。若需求不同，不應只因專案熱度就採用。本文保留原始專案名、命令與元件名，方便回到一手來源核對。 README 另外列出一項可核對的資訊：Agent Skills: Transform your LLM from a conversationalist into a proactive assistant. Use the Agent Skills tile to augment model capabilities with tools like Wikipedia for fact-grounding, interactive maps, and rich visual summary cards.。這類原文條目可用來設計試跑步驟，但不能取代實際環境測試。

README 將運作方式分散在「Google AI Edge Gallery ✨」等段落。可確認的線索包括：The latest version brings official support for the newly released Gemma 4 family. As the centerpiece of this release, Gemma 4 allows you to test the cutting edge of on-device AI.。本文不把未寫出的架構、效能或安全邊界補成結論；真正的執行鏈仍要配合目錄、設定檔與版本標籤檢查。

第一次安裝應從 README 指出的入口開始。目前可核對的命令是： README 没有给出可直接复制的安装命令。 如果倉庫沒有命令，本文不會自行編造步驟，而是建議先閱讀「App Preview」，確認系統依賴、預設埠與首次初始化。

日常使用取決於專案文件。README 的「Google AI Edge Gallery ✨」段落提到：| Install the app today from Google Play | Install the app today from App Store | Download for macOS | | :--- | :--- | :--- | | | | |。設定檔、環境變數、權限與資料目錄只在來源明確時才會記錄；沒有寫出的預設值，應在測試環境驗證並保留回滾副本。 同一部分也提到：Ask Image: Use multimodal power to identify objects, solve visual puzzles, or get detailed descriptions using your device's camera or photo gallery.。