<figure class="table"><table><colgroup><col style="width:33.33%;"><col style="width:33.33%;"><col style="width:33.34%;"></colgroup><tbody><tr><td> </td><td> </td><td> </td></tr><tr><td> </td><td> </td><td> </td></tr><tr><td><h1 class="text-4xl font-semibold" style="--tw-backdrop-blur:;--tw-backdrop-brightness:;--tw-backdrop-contrast:;--tw-backdrop-grayscale:;--tw-backdrop-hue-rotate:;--tw-backdrop-invert:;--tw-backdrop-opacity:;--tw-backdrop-saturate:;--tw-backdrop-sepia:;--tw-blur:;--tw-border-spacing-x:0;--tw-border-spacing-y:0;--tw-brightness:;--tw-contrast:;--tw-drop-shadow:;--tw-grayscale:;--tw-hue-rotate:;--tw-invert:;--tw-numeric-figure:;--tw-numeric-fraction:;--tw-numeric-spacing:;--tw-ordinal:;--tw-pan-x:;--tw-pan-y:;--tw-pinch-zoom:;--tw-ring-color:rgb(59 130 246 / .5);--tw-ring-inset:;--tw-ring-offset-color:#fff;--tw-ring-offset-shadow:0 0 #0000;--tw-ring-offset-width:0px;--tw-ring-shadow:0 0 #0000;--tw-rotate:0;--tw-saturate:;--tw-scale-x:1;--tw-scale-y:1;--tw-scroll-snap-strictness:proximity;--tw-sepia:;--tw-shadow-colored:0 0 #0000;--tw-shadow:0 0 #0000;--tw-skew-x:0;--tw-skew-y:0;--tw-slashed-zero:;--tw-translate-x:0;--tw-translate-y:0;-webkit-text-stroke-width:0px;border:0px solid rgb(229, 231, 235);box-sizing:border-box;color:rgb(0, 0, 0);font-family:;" roboto="" sans="">https://www.bnext.com.tw/article/84876/chatgpt-3-word-rule-7-prompts</h1><h1 class="text-4xl font-semibold" style="--tw-backdrop-blur:;--tw-backdrop-brightness:;--tw-backdrop-contrast:;--tw-backdrop-grayscale:;--tw-backdrop-hue-rotate:;--tw-backdrop-invert:;--tw-backdrop-opacity:;--tw-backdrop-saturate:;--tw-backdrop-sepia:;--tw-blur:;--tw-border-spacing-x:0;--tw-border-spacing-y:0;--tw-brightness:;--tw-contrast:;--tw-drop-shadow:;--tw-grayscale:;--tw-hue-rotate:;--tw-invert:;--tw-numeric-figure:;--tw-numeric-fraction:;--tw-numeric-spacing:;--tw-ordinal:;--tw-pan-x:;--tw-pan-y:;--tw-pinch-zoom:;--tw-ring-color:rgb(59 130 246 / .5);--tw-ring-inset:;--tw-ring-offset-color:#fff;--tw-ring-offset-shadow:0 0 #0000;--tw-ring-offset-width:0px;--tw-ring-shadow:0 0 #0000;--tw-rotate:0;--tw-saturate:;--tw-scale-x:1;--tw-scale-y:1;--tw-scroll-snap-strictness:proximity;--tw-sepia:;--tw-shadow-colored:0 0 #0000;--tw-shadow:0 0 #0000;--tw-skew-x:0;--tw-skew-y:0;--tw-slashed-zero:;--tw-translate-x:0;--tw-translate-y:0;-webkit-text-stroke-width:0px;border:0px solid rgb(229, 231, 235);box-sizing:border-box;color:rgb(0, 0, 0);font-family:;" roboto="" sans="">善用「3字規則+7組萬用提示詞」</h1><p class="text-4xl font-semibold" style="--tw-backdrop-blur:;--tw-backdrop-brightness:;--tw-backdrop-contrast:;--tw-backdrop-grayscale:;--tw-backdrop-hue-rotate:;--tw-backdrop-invert:;--tw-backdrop-opacity:;--tw-backdrop-saturate:;--tw-backdrop-sepia:;--tw-blur:;--tw-border-spacing-x:0;--tw-border-spacing-y:0;--tw-brightness:;--tw-contrast:;--tw-drop-shadow:;--tw-grayscale:;--tw-hue-rotate:;--tw-invert:;--tw-numeric-figure:;--tw-numeric-fraction:;--tw-numeric-spacing:;--tw-ordinal:;--tw-pan-x:;--tw-pan-y:;--tw-pinch-zoom:;--tw-ring-color:rgb(59 130 246 / .5);--tw-ring-inset:;--tw-ring-offset-color:#fff;--tw-ring-offset-shadow:0 0 #0000;--tw-ring-offset-width:0px;--tw-ring-shadow:0 0 #0000;--tw-rotate:0;--tw-saturate:;--tw-scale-x:1;--tw-scale-y:1;--tw-scroll-snap-strictness:proximity;--tw-sepia:;--tw-shadow-colored:0 0 #0000;--tw-shadow:0 0 #0000;--tw-skew-x:0;--tw-skew-y:0;--tw-slashed-zero:;--tw-translate-x:0;--tw-translate-y:0;-webkit-text-stroke-width:0px;border:0px solid rgb(229, 231, 235);box-sizing:border-box;color:rgb(0, 0, 0);font-family:;" roboto="" sans=""><strong style="--tw-backdrop-blur:;--tw-backdrop-brightness:;--tw-backdrop-contrast:;--tw-backdrop-grayscale:;--tw-backdrop-hue-rotate:;--tw-backdrop-invert:;--tw-backdrop-opacity:;--tw-backdrop-saturate:;--tw-backdrop-sepia:;--tw-blur:;--tw-border-spacing-x:0;--tw-border-spacing-y:0;--tw-brightness:;--tw-contrast:;--tw-drop-shadow:;--tw-grayscale:;--tw-hue-rotate:;--tw-invert:;--tw-numeric-figure:;--tw-numeric-fraction:;--tw-numeric-spacing:;--tw-ordinal:;--tw-pan-x:;--tw-pan-y:;--tw-pinch-zoom:;--tw-ring-color:rgb(59 130 246 / .5);--tw-ring-inset:;--tw-ring-offset-color:#fff;--tw-ring-offset-shadow:0 0 #0000;--tw-ring-offset-width:0px;--tw-ring-shadow:0 0 #0000;--tw-rotate:0;--tw-saturate:;--tw-scale-x:1;--tw-scale-y:1;--tw-scroll-snap-strictness:proximity;--tw-sepia:;--tw-shadow-colored:0 0 #0000;--tw-shadow:0 0 #0000;--tw-skew-x:0;--tw-skew-y:0;--tw-slashed-zero:;--tw-translate-x:0;--tw-translate-y:0;-webkit-text-stroke-width:0px;border:0px solid rgb(229, 231, 235);box-sizing:border-box;color:rgba(0, 0, 0, 0.8);font-family:;" roboto="" sans="">一個極為簡單的「3字規則」（3-word rule）：在你的提問句尾，加上「like a role」（像個某某角色一樣），能有效地指導 AI 聊天機器人調整語氣、內容深度與格式，提供更具思考性、相關性和專業水準的回覆<span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans=""> 。<p class="text-4xl font-semibold" style="--tw-backdrop-blur:;--tw-backdrop-brightness:;--tw-backdrop-contrast:;--tw-backdrop-grayscale:;--tw-backdrop-hue-rotate:;--tw-backdrop-invert:;--tw-backdrop-opacity:;--tw-backdrop-saturate:;--tw-backdrop-sepia:;--tw-blur:;--tw-border-spacing-x:0;--tw-border-spacing-y:0;--tw-brightness:;--tw-contrast:;--tw-drop-shadow:;--tw-grayscale:;--tw-hue-rotate:;--tw-invert:;--tw-numeric-figure:;--tw-numeric-fraction:;--tw-numeric-spacing:;--tw-ordinal:;--tw-pan-x:;--tw-pan-y:;--tw-pinch-zoom:;--tw-ring-color:rgb(59 130 246 / .5);--tw-ring-inset:;--tw-ring-offset-color:#fff;--tw-ring-offset-shadow:0 0 #0000;--tw-ring-offset-width:0px;--tw-ring-shadow:0 0 #0000;--tw-rotate:0;--tw-saturate:;--tw-scale-x:1;--tw-scale-y:1;--tw-scroll-snap-strictness:proximity;--tw-sepia:;--tw-shadow-colored:0 0 #0000;--tw-shadow:0 0 #0000;--tw-skew-x:0;--tw-skew-y:0;--tw-slashed-zero:;--tw-translate-x:0;--tw-translate-y:0;-webkit-text-stroke-width:0px;border:0px solid rgb(229, 231, 235);box-sizing:border-box;color:rgb(0, 0, 0);font-family:;" roboto="" sans=""><span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans="">原本提示：「Summarize this article」（摘要這篇文章） <span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans="">調整後提示：「Summarize this article like a journalist」（像個記者一樣幫我摘要這篇文章）<p class="text-4xl font-semibold" style="--tw-backdrop-blur:;--tw-backdrop-brightness:;--tw-backdrop-contrast:;--tw-backdrop-grayscale:;--tw-backdrop-hue-rotate:;--tw-backdrop-invert:;--tw-backdrop-opacity:;--tw-backdrop-saturate:;--tw-backdrop-sepia:;--tw-blur:;--tw-border-spacing-x:0;--tw-border-spacing-y:0;--tw-brightness:;--tw-contrast:;--tw-drop-shadow:;--tw-grayscale:;--tw-hue-rotate:;--tw-invert:;--tw-numeric-figure:;--tw-numeric-fraction:;--tw-numeric-spacing:;--tw-ordinal:;--tw-pan-x:;--tw-pan-y:;--tw-pinch-zoom:;--tw-ring-color:rgb(59 130 246 / .5);--tw-ring-inset:;--tw-ring-offset-color:#fff;--tw-ring-offset-shadow:0 0 #0000;--tw-ring-offset-width:0px;--tw-ring-shadow:0 0 #0000;--tw-rotate:0;--tw-saturate:;--tw-scale-x:1;--tw-scale-y:1;--tw-scroll-snap-strictness:proximity;--tw-sepia:;--tw-shadow-colored:0 0 #0000;--tw-shadow:0 0 #0000;--tw-skew-x:0;--tw-skew-y:0;--tw-slashed-zero:;--tw-translate-x:0;--tw-translate-y:0;-webkit-text-stroke-width:0px;border:0px solid rgb(229, 231, 235);box-sizing:border-box;color:rgb(0, 0, 0);font-family:;" roboto="" sans=""><span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans="">原本提示：「Give me feedback on my resume」（給我履歷建議） <span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans="">調整後提示：「Give me feedback on my resume like a hiring manager」（像個人資主管一樣給我履歷建議）<p class="text-4xl font-semibold" style="--tw-backdrop-blur:;--tw-backdrop-brightness:;--tw-backdrop-contrast:;--tw-backdrop-grayscale:;--tw-backdrop-hue-rotate:;--tw-backdrop-invert:;--tw-backdrop-opacity:;--tw-backdrop-saturate:;--tw-backdrop-sepia:;--tw-blur:;--tw-border-spacing-x:0;--tw-border-spacing-y:0;--tw-brightness:;--tw-contrast:;--tw-drop-shadow:;--tw-grayscale:;--tw-hue-rotate:;--tw-invert:;--tw-numeric-figure:;--tw-numeric-fraction:;--tw-numeric-spacing:;--tw-ordinal:;--tw-pan-x:;--tw-pan-y:;--tw-pinch-zoom:;--tw-ring-color:rgb(59 130 246 / .5);--tw-ring-inset:;--tw-ring-offset-color:#fff;--tw-ring-offset-shadow:0 0 #0000;--tw-ring-offset-width:0px;--tw-ring-shadow:0 0 #0000;--tw-rotate:0;--tw-saturate:;--tw-scale-x:1;--tw-scale-y:1;--tw-scroll-snap-strictness:proximity;--tw-sepia:;--tw-shadow-colored:0 0 #0000;--tw-shadow:0 0 #0000;--tw-skew-x:0;--tw-skew-y:0;--tw-slashed-zero:;--tw-translate-x:0;--tw-translate-y:0;-webkit-text-stroke-width:0px;border:0px solid rgb(229, 231, 235);box-sizing:border-box;color:rgb(0, 0, 0);font-family:;" roboto="" sans=""><span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans="">Like a teacher：用於將複雜主題拆解成簡單、循序漸進的課程。 <span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans="">Like a therapist：用於以冷靜、富同理心的方式處理情緒或棘手對話的策略。 <span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans="">Like a coach：用於設定目標、制定每週計畫，或提供激勵人心的建議。 <span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans="">Like a nutritionist：用於提供專注於營養均衡、價格實惠且準備簡單的每週食譜。 <span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:1px;orphans:2;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" roboto="" sans="">Like a project manager：用於以清晰好懂的優先順序、截止日期來組織任務清單。</td><td>5 個 prompt 做決策、盯專案、回顧會議重點 1. 提前預知會議重點：讓 AI 幫你搞懂對方在想什麼 Prompt：「根據我與［/person］先前的互動，列出對方在我們下次會議中最可能關注的 5 件事。」（Based on my prior interactions with [/person], give me 5 things likely top of mind for our next meeting.）2. 一鍵生成專案報告：告別繁瑣的彙整工作 Prompt：「根據郵件、聊天紀錄和［/series］中的所有會議，撰寫一份專案更新報告：包括 KPI 與目標的差距、成敗分析、風險點、競爭對手動態，以及可能被問到的尖銳問題與建議回答。」（Draft a project update based on emails, chats, and all meetings in [/series]: KPIs vs. targets, wins/losses, risks, competitive moves, plus likely tough questions and answers.）  3. 專案進度量化分析：用數據看清成功機率 Prompt：「我們是否準備好在 11 月推出［Product］？請檢查工程進度、試點計畫成果和潛在風險，並提供一個成功機率。」（Are we on track for the [Product] launch in November? Check eng progress, pilot program results, risks. Give me a probability.）  4. 時間分析：搞懂自己的時間都花去哪了 Prompt：「請分析我過去一個月的行事曆與電子郵件，整理出 5 到 7 類我花最多時間處理的專案，列出各自的時間占比與簡短說明。」（Review my calendar and email from the last month and create 5 to 7 buckets for projects I spend most time on, with % of time spent and short descriptions.）  5. 會議準備神器：自動回顧討論脈絡 Prompt：「請根據我選取的電子郵件內容，以及過去主管與團隊的討論，幫我準備接下來的［/series］會議。」（Review [/select email] + prep me for the next meeting in [/series], based on past manager and team discussions.）</td><td><span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;letter-spacing:normal;orphans:2;text-align:center;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" microsoft="">如何讓ChatGPT成為「影子寫手」，寫出專屬於你的「味道」<h3 style="-webkit-text-stroke-width:0px;background-color:rgb(255, 255, 255);border-width:0px;box-sizing:border-box;color:rgb(77, 77, 77);font-family:;" microsoft="">深津式泛用Prompt</h3><b style="border-width:0px;box-sizing:border-box;font-family:inherit;font-feature-settings:inherit;font-kerning:inherit;font-optical-sizing:inherit;font-size:inherit;font-stretch:inherit;font-style:inherit;font-variant:inherit;font-variation-settings:inherit;line-height:inherit;margin:0px;padding:0px;vertical-align:baseline;">#Instructions（你想要它扮演的角色）你是專業的編輯。根據以下規範和輸入的句子來輸出最佳摘要。<b style="border-width:0px;box-sizing:border-box;font-family:inherit;font-feature-settings:inherit;font-kerning:inherit;font-optical-sizing:inherit;font-size:inherit;font-stretch:inherit;font-style:inherit;font-variant:inherit;font-variation-settings:inherit;line-height:inherit;margin:0px;padding:0px;vertical-align:baseline;">#Constraints（你想要的文章樣貌）字符數約為300個字符。小學生也能輕鬆理解。保持句子簡潔。指令：文章內容必須包含：A、B、C。這裡的ABC除了可以填入你想要文章包含的元素以外，也可以填入一些你想要ChatGPT了解的背景資料，讓它能根據這些資料撰寫，而不是隨口亂編。如果你想要讓這篇文章的架構更縝密，你可以先大致分配文章的段落和各個段落的重點，並將指令改為：請將文章分成五段，這五段的內容分別為 A、B、C、D、E，並照順序寫作。<b style="border-width:0px;box-sizing:border-box;font-family:inherit;font-feature-settings:inherit;font-kerning:inherit;font-optical-sizing:inherit;font-size:inherit;font-stretch:inherit;font-style:inherit;font-variant:inherit;font-variation-settings:inherit;line-height:inherit;margin:0px;padding:0px;vertical-align:baseline;">#Input（你想要修改 / 摘錄的文字）（填入想要摘錄的文本）<b style="border-width:0px;box-sizing:border-box;font-family:inherit;font-feature-settings:inherit;font-kerning:inherit;font-optical-sizing:inherit;font-size:inherit;font-stretch:inherit;font-style:inherit;font-variant:inherit;font-variation-settings:inherit;line-height:inherit;margin:0px;padding:0px;vertical-align:baseline;">#output<p style="-webkit-text-stroke-width:0px;background-color:rgb(247, 247, 247);color:rgb(51, 51, 51);font-family:微軟正黑體, sans-serif;font-size:14pt;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:normal;line-height:2em;margin:0px 0px 1.5em;orphans:2;text-align:start;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;">Line採用了名為CO-STAR的提示詞撰寫架構，來切分提示任務。這幾個字母分別代表不同要素，比如C是指情境（Context），也就是在提示中描述任務概況、賦予LLM角色；O則指目標（Objective），即在提示中告知LLM想實現的目標，像是「給出案件類別，並總結案件始末」。<p style="-webkit-text-stroke-width:0px;background-color:rgb(247, 247, 247);color:rgb(51, 51, 51);font-family:微軟正黑體, sans-serif;font-size:14pt;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:normal;line-height:2em;margin:0px 0px 1.5em;orphans:2;text-align:start;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;">再來是S，也就是回覆風格（Style），比如告訴LLM，要以客服身分回答問題。T則是語調（Tone），可以在提示中，要求LLM以溫柔的語調回覆。A則指受眾（Audience）目標，R是輸出的格式（Response），比如「將標籤和案件解釋區分開來」這類描述。 </td></tr><tr><td>建議增加WFH的作法以及管理等，包含數位工具的搭配應用等等NO CODE AI的瞭解和體驗</td><td><meta charset="utf-8">透過評鑑分析了解本身的職能現況以及人格特質，而針對有待加強的地方，則可經由培訓過程學習到的系統性方法，制訂可操作的改善計畫，搭配相關指標的驗證，持續練習以成為更好的領導人，從而如期如質完成單位交付的工作。</td><td>以下為示範：<div style="-webkit-text-stroke-width:0px;background-color:rgb(229, 244, 255);border-width:0px;box-sizing:border-box;color:rgb(77, 77, 77);font-family:;" microsoft=""><p style="border-width:0px;box-sizing:border-box;font-family:inherit;font-feature-settings:inherit;font-kerning:inherit;font-optical-sizing:inherit;font-size:inherit;font-stretch:inherit;font-style:inherit;font-variant:inherit;font-variation-settings:inherit;font-weight:inherit;line-height:28px;margin:0px;padding:0.825em 0px;vertical-align:baseline;">#Instructions：你是一名作家，請根據constraints的規範寫一篇文章<p style="border-width:0px;box-sizing:border-box;font-family:inherit;font-feature-settings:inherit;font-kerning:inherit;font-optical-sizing:inherit;font-size:inherit;font-stretch:inherit;font-style:inherit;font-variant:inherit;font-variation-settings:inherit;font-weight:inherit;line-height:28px;margin:0px;padding:0.825em 0px;vertical-align:baseline;">#Constraints：字符數約為800個字符。小學生也能輕鬆理解。保持句子簡潔。本篇文章的主題為：信仰對於我的意義，內容請聚焦在我成為基督徒後的心態轉變。內容必須包含：我小學五年級的受洗經驗、曾經討厭每周日的無聊聚會、大學時遇到課業壓力和人際壓力、某次禮拜時牧師和晤談後不在迷惘、感受到神的恩典。文章中請加入以下的字詞：曾經、我以為、最後、或許、就在這時。文章中請加入這句名言佳句：藐視鄰舍的，毫無智慧，明哲人卻靜默不言。<p style="border-width:0px;box-sizing:border-box;font-family:inherit;font-feature-settings:inherit;font-kerning:inherit;font-optical-sizing:inherit;font-size:inherit;font-stretch:inherit;font-style:inherit;font-variant:inherit;font-variation-settings:inherit;font-weight:inherit;line-height:28px;margin:0px;padding:0.825em 0px;vertical-align:baseline;">#output：</div></td></tr><tr><td>時代趨勢:少子化，老齡化技術趨勢:低碳化(循環化)，AI化終身學習;獨立思考</td><td>project to go:LLM RAG on document of cycle chemistry00flask_yolo3 as generic platform of object detection</td><td> </td></tr><tr><td><h1 class="pw-post-title fm fn fo be fp fq fr fs ft fu fv fw fx fy fz ga gb gc gd ge gf gg gh gi gj gk bj" style="-webkit-text-stroke-width:0px;background-color:rgb(255, 255, 255);box-sizing:inherit;color:rgb(36, 36, 36);font-family:sohne,;" helvetica="" id="23ed" data-testid="storyTitle" data-selectable-paragraph="">https://analyticsindiamag.com/top-5-llm-benchmarks/</h1><h1 class="pw-post-title fm fn fo be fp fq fr fs ft fu fv fw fx fy fz ga gb gc gd ge gf gg gh gi gj gk bj" style="-webkit-text-stroke-width:0px;background-color:rgb(255, 255, 255);box-sizing:inherit;color:rgb(36, 36, 36);font-family:sohne,;" helvetica="" id="23ed" data-testid="storyTitle" data-selectable-paragraph="">You don’t need hosted LLMs, do you?</h1><a href="https://betterprogramming.pub/you-dont-need-hosted-llms-do-you-1160b2520526">https://betterprogramming.pub/you-dont-need-hosted-llms-do-you-1160b2520526</a>https://www.vellum.ai/blog/should-i-use-prompting-rag-or-fine-tuning<a class="af ag ah ai aj ak al am an ao ap aq ar jf" style="-webkit-tap-highlight-color:transparent;-webkit-text-stroke-width:0px;background-color:rgb(255, 255, 255);border-color:inherit;box-sizing:inherit;color:inherit;cursor:pointer;fill:inherit;font-family:sohne,;" href="https://afaqueumer.medium.com/?source=post_page-----a1736252b172--------------------------------" helvetica="" rel="noopener follow">Afaque Umer</a><a href="https://ai.plainenglish.io/%EF%B8%8F-langchain-streamlit-llama-bringing-conversational-ai-to-your-local-machine-a1736252b172">https://ai.plainenglish.io/%EF%B8%8F-langchain-streamlit-llama-bringing-conversational-ai-to-your-local-machine-a1736252b172</a><a href="https://github.com/afaqueumer/DocQA">https://github.com/afaqueumer/DocQA</a><a href="https://huggingface.co/TheBloke/LLaMa-7B-GGML">https://huggingface.co/TheBloke/LLaMa-7B-GGML</a>1.Visual Studio with C++2.https://github.com/abetlen/llama-cpp-python <div class="ab q" style="-webkit-text-stroke-width:0px;align-items:center;background-color:rgb(255, 255, 255);box-sizing:inherit;color:rgb(36, 36, 36);display:flex;font-family:sohne,;" helvetica=""><div style="box-sizing:inherit;"><div class="bl" style="box-sizing:inherit;display:inline-block;" aria-hidden="false" aria-describedby="5" aria-labelledby="5"><a class="af ag ah ai aj ak al am an ao ap aq ar ig" style="-webkit-tap-highlight-color:transparent;border-color:inherit;box-sizing:inherit;color:inherit;cursor:pointer;fill:inherit;font-family:inherit;font-size:inherit;font-weight:inherit;letter-spacing:inherit;margin:0px;padding:0px;text-decoration:none;" href="https://medium.com/@fabio.matricardi?source=post_page-----2f75b8d639ae--------------------------------" rel="noopener follow">Fabio Matricardi</a></div></div></div><a href="https://artificialcorner.com/answering-question-about-your-documents-using-langchain-and-not-openai-2f75b8d639ae">https://artificialcorner.com/answering-question-about-your-documents-using-langchain-and-not-openai-2f75b8d639ae</a><a href="https://artificialcorner.com/lamini-is-here-a-little-giant-llm-on-your-cpu-8af30ff5a7c2">https://artificialcorner.com/lamini-is-here-a-little-giant-llm-on-your-cpu-8af30ff5a7c2</a>https://towardsdatascience.com/distributed-llama-2-on-cpus-via-llama-cpp-pyspark-65736e9f466dhttps://simonwillison.net/2023/Aug/3/weird-world-of-llms/<a href="https://huggingface.co/TheBloke/airoboros-l2-7b-gpt4-1.4.1-GGML/tree/main">https://huggingface.co/TheBloke/airoboros-l2-7b-gpt4-1.4.1-GGML/tree/main</a><nav class="Box-sc-g0xbh4-0 kzRgrI" style="-webkit-text-stroke-width:0px;background-color:rgb(255, 255, 255);box-sizing:border-box;color:rgb(31, 35, 40);display:block;font-family:-apple-system, BlinkMacSystemFont,;" segoe="" color="" ui="" data-testid="breadcrumbs" aria-labelledby="breadcrumb-heading" id="breadcrumb"><a class="Link__StyledLink-sc-14289xe-0 eVjWum" style="background-color:transparent;box-sizing:border-box;color:rgb(9, 105, 218);text-decoration:none;" href="https://github.com/R3gm/InsightSolver-Colab/tree/main" sx="[object Object]" data-testid="breadcrumbs-repo-link">InsightSolver-Colab</a>/<h1 class="Heading__StyledHeading-sc-1c1dgg0-0 diwsLq" style="box-sizing:border-box;display:inline-block;font-size:16px;margin:0px;max-width:100%;" tabindex="-1" id="file-name-id">LLM_Inference_with_llama_cpp_python__Llama_2_13b_chat.ipynb</h1>    </nav></td><td>人工智慧大語言模型相關技術用於環化業務的可行性研究先進人工智慧技術應用於電業水處理程序的可行性探討usage:tech review, coding assissting, process alert, report QA, ViT, DETRAI, LLM, Transformer, Attention, Llama cpp python langchainAbby Morgan<a href="https://www.comet.com/site/blog/explainable-ai-for-transformers/">https://www.comet.com/site/blog/explainable-ai-for-transformers/</a>langchain說明:<a href="https://python.langchain.com/docs/integrations/llms/llamacpp">https://python.langchain.com/docs/integrations/llms/llamacpp</a>https://ai.plainenglish.io/from-idea-to-reality-creating-llm-powered-apps-with-langchain-a0317a23590dLLM排行榜:<a href="https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard">https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard</a> <h1 class="col-12" style="-webkit-text-stroke-width:0px;background-color:rgb(242, 242, 242);border-left:3px solid rgb(245, 87, 83);box-sizing:border-box;color:rgb(51, 51, 51);flex:0 0 100%;font-family:;" microsoft="">微軟導入ChatGPT和機器人互動 我們離賈維斯不遠了！</h1><a href="https://www.cool3c.com/article/197069">https://www.cool3c.com/article/197069</a> <a href="https://agi-sphere.com/llama-2/">https://agi-sphere.com/llama-2/</a><a href="https://onpassive.com/blog/top-5-benefits-of-robotic-process-automation/">https://onpassive.com/blog/top-5-benefits-of-robotic-process-automation/</a>https://bdtechtalks.com/2023/08/14/llm-api-server-nocode/<o:p></o:p></td><td>1.https://replicate.com/blog/how-to-prompt-llama2.https://huggingface.co/blog/stackllama(<span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;letter-spacing:normal;orphans:2;text-align:start;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;">StackLLaMA: A hands-on guide to train LLaMA with RLHF)3.https://medium.com/@mikeyoung_97230/harnessing-the-power-of-llama-v2-for-chat-applications-9b0c7597a9fa4.https://notes.aimodels.fyi/building-a-customer-support-chatbot-with-langchain-and-deepinfra-a-step-by-step-guide/llama cpp=ggmlinference time:7b=60 sec;13b=120 sec;chat2model1.Nous-Hermes-13b-Chinese.ggmlv3.q4_0.bin2.llama-cpp-python          0.1.783.langchain                 0.0.27chat2data1.airoboros-l2-7b-2.2.Q4_0.ggufdir1 = "./model_llm/" llm = LlamaCpp(model_path=dir1 + "airoboros-l2-7b-2.2.Q4_0.gguf", n_ctx=1024)#, n_gqa=8)2.#embeddings = LlamaCppEmbeddings(model_path=dir1 + "airoboros-l2-13b-gpt4-1.4.1.ggmlv3.q4_0.bin")#, n_gqa=8) embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2") # Equivalent to SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")shibing624/text2vec-base-chinese3.llama-cpp-python          0.2.64.langchain                 0.0.300可以中文問，可能英文答!(中文embedding/英文llm)pip install chromadb要記得重啟kernel!!!</td></tr><tr><td><a href="https://lexica.art/">https://lexica.art/</a>老共的問題1.房價不准下跌，一開始是怕地方政府的擔保品就是房子的資產會縮水2.貨幣政策，人民幣匯率和資本的自由流通三者不可並得，為了控制人民幣匯率不至於降得太快，會用掉儲存的美元外匯，所以其終局就是外匯會用完，人民幣則是災難式的貶值</td><td>Pythonhttps://www.freecodecamp.org/news/object-oriented-programming-python/</td><td>智慧化系統水鐵分析軟硬體整合應用實作研發1.影像收集2.模型訓練3.硬體選用4.程式撰寫5.軟硬體整合cycle water, analysis, edge computing, training, deploying</td></tr><tr><td>QA:<a href="https://towardsdatascience.com/4-ways-of-question-answering-in-langchain-188c6707cc5a">https://towardsdatascience.com/4-ways-of-question-answering-in-langchain-188c6707cc5a</a> summarization: <h2 class="pa ms gj be mt pb pc pd mw pe pf pg mz nw ph pi pj oa pk pl pm oe pn po pp pq bj" style="-webkit-text-stroke-width:0px;background-color:rgb(255, 255, 255);box-sizing:inherit;color:rgb(36, 36, 36);font-family:sohne,;" helvetica="" id="81df" data-selectable-paragraph="">Named Entities</h2><a href="https://cobusgreyling.medium.com/using-a-large-language-model-for-entity-extraction-6fffb988eb15">https://cobusgreyling.medium.com/using-a-large-language-model-for-entity-extraction-6fffb988eb15</a>Agent<a href="https://gathnex.medium.com/how-to-create-your-own-llm-agent-from-scratch-a-step-by-step-guide-14b763e5b3b8">https://gathnex.medium.com/how-to-create-your-own-llm-agent-from-scratch-a-step-by-step-guide-14b763e5b3b8</a><span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:-0.06px;orphans:2;text-align:start;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" times="" new="">LLM agents are are programs that use large language models to decide how and when to use tools to complete tasks.<span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:-0.06px;orphans:2;text-align:start;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:normal;widows:2;word-spacing:0px;" times="" new="">https://towardsdev.com/llamaindex-yet-another-powerful-framework-to-build-efficient-knowledge-bots-06065f60605fASR, speech to text<a href="https://deepgram.com/learn/benchmarking-top-open-source-speech-models">https://deepgram.com/learn/benchmarking-top-open-source-speech-models</a><a href="https://github.com/malceore/voice-assistant-client">https://github.com/malceore/voice-assistant-client</a><a href="https://www.assemblyai.com/blog/deepspeech-for-dummies-a-tutorial-and-overview-part-1/">https://www.assemblyai.com/blog/deepspeech-for-dummies-a-tutorial-and-overview-part-1/</a><a href="https://www.assemblyai.com/blog/the-state-of-python-speech-recognition-in-2021/">https://www.assemblyai.com/blog/the-state-of-python-speech-recognition-in-2021/</a>https://github.com/mozilla/DeepSpeech-examples/blob/r0.9/mic_vad_streaming/README.rst</td><td> whisper<a href="https://github.com/tobiashuttinger/openai-whisper-realtime/blob/main/openai-whisper-realtime.py">https://github.com/tobiashuttinger/openai-whisper-realtime/blob/main/openai-whisper-realtime.py</a><a href="https://medium.com/@dominique.heer/controlling-your-computer-with-voice-commands-by-using-openai-whisper">https://medium.com/@dominique.heer/controlling-your-computer-with-voice-commands-by-using-openai-whisper</a><span style="-webkit-text-stroke-width:0px;display:inline !important;float:none;font-style:normal;font-variant-caps:normal;font-variant-ligatures:normal;font-weight:400;letter-spacing:-0.308px;orphans:2;text-align:start;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;white-space:pre;widows:2;word-spacing:0px;" courier="">pip install SpeechRecognition[whisper-local] pyaudio setuptools<a href="https://github.com/Uberi/speech_recognition/blob/master/examples/threaded_workers.py">https://github.com/Uberi/speech_recognition/blob/master/examples/threaded_workers.py</a><a href="https://fahizkp.medium.com/building-a-robust-real-time-transcription-system-with-openais-whisper-6a0b40c4b997">https://fahizkp.medium.com/building-a-robust-real-time-transcription-system-with-openais-whisper-6a0b40c4b997</a><a href="https://pypi.org/project/RealtimeSTT/">https://pypi.org/project/RealtimeSTT/</a>https://github.com/SYSTRAN/faster-whisperwhisper.cpp<a href="https://github.com/ggerganov/whisper.cpp">https://github.com/ggerganov/whisper.cpp</a><a href="https://github.com/ggerganov/whisper.cpp/tree/master/models">https://github.com/ggerganov/whisper.cpp/tree/master/models</a><a href="https://huggingface.co/ggerganov/whisper.cpp/tree/main">https://huggingface.co/ggerganov/whisper.cpp/tree/main</a>https://huggingface.co/learn/audio-course/chapter7/voice-assistant#speech-transcription</td><td>藻類養殖自動化技術研發1.技術文獻研讀2.網路架構和基本監視系統3.藻類生長狀況自動判別技術建立4.繼代操作自動化技術研發5.藻類放大養殖自動化技術6.口語化操作指令可行性network, CNN;robot arm(motoman python control), python, whisper prompt<a href="https://tinyml.substack.com/p/your-go-to-guide-to-master-prompt">https://tinyml.substack.com/p/your-go-to-guide-to-master-prompt</a><a href="https://blog.hubspot.com/marketing/write-ai-prompts">https://blog.hubspot.com/marketing/write-ai-prompts</a>https://realpython.com/practical-prompt-engineering/#improve-your-output-with-the-power-of-conversation<a href="https://www.pinecone.io/learn/series/langchain/langchain-prompt-templates/">https://www.pinecone.io/learn/series/langchain/langchain-prompt-templates/</a>https://www.pinecone.io/learn/series/langchain/langchain-retrieval-augmentation/<a href="https://www.youtube.com/watch?v=efIzlP4JT6g">https://www.youtube.com/watch?v=efIzlP4JT6g</a><a href="https://github.blog/2023-07-17-prompt-engineering-guide-generative-ai-llms/">https://github.blog/2023-07-17-prompt-engineering-guide-generative-ai-llms/</a><a href="https://axk51013.medium.com/%E5%B0%88%E6%AC%84-%E5%A6%82%E4%BD%95%E7%94%A8chatgpt%E6%89%93%E9%80%A0%E4%B8%80%E5%80%8Bai%E7%94%A2%E5%93%81-part2-%E5%9F%BA%E7%A4%8Eprompt-engineering%E5%85%A5%E9%96%80-11d6cc3161ac">https://axk51013.medium.com/%E5%B0%88%E6%AC%84-%E5%A6%82%E4%BD%95%E7%94%A8chatgpt%E6%89%93%E9%80%A0%E4%B8%80%E5%80%8Bai%E7%94%A2%E5%93%81-part2-%E5%9F%BA%E7%A4%8Eprompt-engineering%E5%85%A5%E9%96%80-11d6cc3161ac</a>pyttsx3<pre class="lang-sh s-code-block" style="--_cb-line-numbers-bg:var(--black-150);--theme-background-attachment:auto;--theme-background-color:var(--white);--theme-background-position:top left;--theme-background-repeat:repeat;--theme-background-size:auto;--theme-base-primary-color-h:12.87958115;--theme-base-primary-color-l:48.82352941%;--theme-base-primary-color-s:76.70682731%;--theme-body-font-color:var(--black-600);--theme-body-font-family:var(--ff-sans);--theme-button-active-background-color:var(--theme-primary-200);--theme-button-color:var(--theme-primary);--theme-button-hover-background-color:var(--theme-primary-100);--theme-button-hover-color:var(--theme-primary-400);--theme-button-outlined-border-color:var(--theme-primary-400);--theme-button-outlined-selected-border-color:var(--theme-primary-500);--theme-button-primary-active-background-color:var(--theme-primary-600);--theme-button-primary-active-color:var(--white);--theme-button-primary-background-color:var(--theme-primary-400);--theme-button-primary-color:var(--white);--theme-button-primary-hover-background-color:var(--theme-primary-500);--theme-button-primary-hover-color:var(--white);--theme-button-primary-selected-background-color:var(--theme-primary-600);--theme-button-primary-selected-color:var(--white);--theme-button-selected-background-color:var(--theme-primary-300);--theme-button-selected-color:var(--theme-primary-600);--theme-content-background-color:var(--white);--theme-content-border-color:var(--black-225);--theme-footer-background-border-top:0;--theme-footer-background-color:#393939;--theme-footer-background-position:top left;--theme-footer-background-repeat:no-repeat;--theme-footer-background-size:auto;--theme-footer-divider-color:hsl(210,8%,25%);--theme-footer-link-color-hover:hsl(0,0%,100%);--theme-footer-link-color:hsl(0,0%,100%);--theme-footer-padding-bottom:0;--theme-footer-padding-top:0;--theme-footer-text-color:hsl(0,0%,100%);--theme-footer-title-color:hsl(0,0%,100%);--theme-header-background-border-bottom:0;--theme-header-background-color:#DC461D;--theme-header-background-position:center left;--theme-header-background-repeat:repeat;--theme-header-background-size:auto;--theme-header-foreground-color:transparent;--theme-header-foreground-position:bottom right;--theme-header-foreground-repeat:no-repeat;--theme-header-foreground-size:auto;--theme-header-link-color:var(--theme-primary);--theme-header-sponsored-color:hsla(0,0%,100%,0.6);--theme-link-color-hover:#ec8d73;--theme-link-color-visited:rgba(220,70,29,0.7);--theme-link-color:#DC461D;--theme-post-body-font-family:var(--ff-sans);--theme-post-owner-background-color:var(--theme-primary-100);--theme-post-owner-new-background-color:var(--theme-primary-200);--theme-post-title-color-hover:hsla(210,8%,5%,0.8);--theme-post-title-color-visited:hsl(210,8%,35%);--theme-post-title-color:hsl(210,8%,5%);--theme-post-title-font-family:var(--ff-sans);--theme-primary-custom-100:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + ((100% - var(--theme-base-primary-color-l)) * .9)));--theme-primary-custom-200:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + ((100% - var(--theme-base-primary-color-l)) * .75)));--theme-primary-custom-300:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + ((100% - var(--theme-base-primary-color-l)) * .5)));--theme-primary-custom-400:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), var(--theme-base-primary-color-l));--theme-primary-custom-500:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + (var(--theme-base-primary-color-l) * -.3)));--theme-primary-custom-600:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + (var(--theme-base-primary-color-l) * -.6)));--theme-primary-custom:var(--theme-primary-custom-400);--theme-topbar-bottom-border:none;-webkit-text-stroke-width:0px;background-color:var(--highlight-bg);border-radius:var(--br-md);border-width:0px;box-sizing:inherit;color:rgb(12, 13, 14);font-family:var(--ff-mono);font-feature-settings:inherit;font-kerning:inherit;font-optical-sizing:inherit;font-size:var(--fs-body1);font-stretch:inherit;font-style:normal;font-variant-alternates:inherit;font-variant-caps:normal;font-variant-east-asian:inherit;font-variant-ligatures:normal;font-variant-numeric:inherit;font-variant-position:inherit;font-variation-settings:inherit;font-weight:400;letter-spacing:normal;line-height:var(--lh-md);margin:0px 0px calc(1.5em);max-height:600px;orphans:2;overflow-wrap:normal;overflow:auto;padding:var(--su12);scrollbar-color:var(--scrollbar) transparent;text-align:left;text-decoration-color:initial;text-decoration-style:initial;text-decoration-thickness:initial;text-indent:0px;text-transform:none;vertical-align:baseline;widows:2;width:auto;word-spacing:0px;"><code class="language-plaintext hljs language-bash" style="--theme-background-attachment:auto;--theme-background-color:var(--white);--theme-background-position:top left;--theme-background-repeat:repeat;--theme-background-size:auto;--theme-base-primary-color-h:12.87958115;--theme-base-primary-color-l:48.82352941%;--theme-base-primary-color-s:76.70682731%;--theme-body-font-color:var(--black-600);--theme-body-font-family:var(--ff-sans);--theme-button-active-background-color:var(--theme-primary-200);--theme-button-color:var(--theme-primary);--theme-button-hover-background-color:var(--theme-primary-100);--theme-button-hover-color:var(--theme-primary-400);--theme-button-outlined-border-color:var(--theme-primary-400);--theme-button-outlined-selected-border-color:var(--theme-primary-500);--theme-button-primary-active-background-color:var(--theme-primary-600);--theme-button-primary-active-color:var(--white);--theme-button-primary-background-color:var(--theme-primary-400);--theme-button-primary-color:var(--white);--theme-button-primary-hover-background-color:var(--theme-primary-500);--theme-button-primary-hover-color:var(--white);--theme-button-primary-selected-background-color:var(--theme-primary-600);--theme-button-primary-selected-color:var(--white);--theme-button-selected-background-color:var(--theme-primary-300);--theme-button-selected-color:var(--theme-primary-600);--theme-content-background-color:var(--white);--theme-content-border-color:var(--black-225);--theme-footer-background-border-top:0;--theme-footer-background-color:#393939;--theme-footer-background-position:top left;--theme-footer-background-repeat:no-repeat;--theme-footer-background-size:auto;--theme-footer-divider-color:hsl(210,8%,25%);--theme-footer-link-color-hover:hsl(0,0%,100%);--theme-footer-link-color:hsl(0,0%,100%);--theme-footer-padding-bottom:0;--theme-footer-padding-top:0;--theme-footer-text-color:hsl(0,0%,100%);--theme-footer-title-color:hsl(0,0%,100%);--theme-header-background-border-bottom:0;--theme-header-background-color:#DC461D;--theme-header-background-position:center left;--theme-header-background-repeat:repeat;--theme-header-background-size:auto;--theme-header-foreground-color:transparent;--theme-header-foreground-position:bottom right;--theme-header-foreground-repeat:no-repeat;--theme-header-foreground-size:auto;--theme-header-link-color:var(--theme-primary);--theme-header-sponsored-color:hsla(0,0%,100%,0.6);--theme-link-color-hover:#ec8d73;--theme-link-color-visited:rgba(220,70,29,0.7);--theme-link-color:#DC461D;--theme-post-body-font-family:var(--ff-sans);--theme-post-owner-background-color:var(--theme-primary-100);--theme-post-owner-new-background-color:var(--theme-primary-200);--theme-post-title-color-hover:hsla(210,8%,5%,0.8);--theme-post-title-color-visited:hsl(210,8%,35%);--theme-post-title-color:hsl(210,8%,5%);--theme-post-title-font-family:var(--ff-sans);--theme-primary-custom-100:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + ((100% - var(--theme-base-primary-color-l)) * .9)));--theme-primary-custom-200:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + ((100% - var(--theme-base-primary-color-l)) * .75)));--theme-primary-custom-300:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + ((100% - var(--theme-base-primary-color-l)) * .5)));--theme-primary-custom-400:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), var(--theme-base-primary-color-l));--theme-primary-custom-500:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + (var(--theme-base-primary-color-l) * -.3)));--theme-primary-custom-600:hsl(var(--theme-base-primary-color-h), var(--theme-base-primary-color-s), calc(var(--theme-base-primary-color-l) + (var(--theme-base-primary-color-l) * -.6)));--theme-primary-custom:var(--theme-primary-custom-400);--theme-topbar-bottom-border:none;background-color:transparent;border-width:0px;box-sizing:inherit;font-family:inherit;font-feature-settings:inherit;font-kerning:inherit;font-optical-sizing:inherit;font-size:var(--_pr-code-fs);font-stretch:inherit;font-style:inherit;font-variant:inherit;font-variation-settings:inherit;font-weight:inherit;line-height:inherit;margin:0px;padding:0px;vertical-align:baseline;white-space:inherit;">sudo apt install libttspico-utils</code></pre></td></tr><tr><td>   <pre style="-webkit-text-stroke-width:0px;background-color:rgb(246, 248, 250);border-radius:6px;box-sizing:border-box;color:rgb(31, 35, 40);font-family:ui-monospace, SFMono-Regular,;" sf=""># Run with default arguments and small model
./command -m ./models/ggml-small.en.bin -t 8

# On Raspberry Pi, use tiny or base models + "-ac 768" for better performance
./command -m ./models/ggml-tiny.en.bin -ac 768 -t 3 -c 0</pre>whisper on rpi4(python≥3.8) </td><td>生成式 AI 將影響的前 5 大領域為產品設計、軟體開發、客戶互動、行銷公關與供應鏈管理。ffmpeg on rpi4sudo apt update && sudo apt upgrade -ysudo apt install ffmpeg -yffmpeg -i <source_video audio_file="">.format <output_filename>.format</output_filename></source_video>ex=ffmpeg -i test.mp4 out.mkvffmpeg -i <source_video_file>-vn<output_audio_file></output_audio_file></source_video_file>ex=ffmpeg -i test.mp4 -vn out.mp3mp3 play with rpi4pip install python-vlc===code below===import vlc from time import sleepp = vlc.MediaPlayer('./five_hundred_miles.mp3') p.play() sleep(20) p.pause() sleep(2) p.play() sleep(20) p.stop()pyttsx3 on rpi4pip install pyttsx3sudo apt-get update && apt-get upgrade -y && sudo apt-get install espeak### speech recognition on rpi ###sudo apt install portaudio19-dev python3-pyaudio flac espeakpip install speechrecognition sounddevice pyaudio  </td><td>mistral with fine-tuning<a href="https://www.analyticsvidhya.com/blog/2023/11/from-gpt-to-mistral-7b-the-exciting-leap-forward-in-ai-conversations/">https://www.analyticsvidhya.com/blog/2023/11/from-gpt-to-mistral-7b-the-exciting-leap-forward-in-ai-conversations/</a> knowledge graph(KG)<a href="https://towardsdatascience.com/how-to-convert-any-text-into-a-graph-of-concepts-110844f22a1a">https://towardsdatascience.com/how-to-convert-any-text-into-a-graph-of-concepts-110844f22a1a</a><a href="https://github.com/rahulnyk/knowledge_graph/blob/main/extract_graph.ipynb">https://github.com/rahulnyk/knowledge_graph/blob/main/extract_graph.ipynb</a><a href="https://towardsdatascience.com/text-to-knowledge-graph-made-easy-with-graph-maker-f3f890c0dbe8">https://towardsdatascience.com/text-to-knowledge-graph-made-easy-with-graph-maker-f3f890c0dbe8</a>YOLO11https://learnopencv.com/yolo11/</td></tr><tr><td>數位轉型:<a href="https://www.cathayholdings.com/holdings/brand/fintech/ctc/trends/digital_transformation">https://www.cathayholdings.com/holdings/brand/fintech/ctc/trends/digital_transformation</a><a href="https://turingcerts.com/zh/digital-transformation/">https://turingcerts.com/zh/digital-transformation/</a><a href="https://alteia.com/resources/blog/artificial-intelligence-in-digital-transformation/">https://alteia.com/resources/blog/artificial-intelligence-in-digital-transformation/</a> </td><td>###OCRhttps://neuralnet.solutions/ultralytics-yolo-11-and-ollama-a-very-accurate-ocr</td><td>###google langextract <a href="https://www.datacamp.com/tutorial/langextract">https://www.datacamp.com/tutorial/langextract</a> ###vvv transforming unstructured text into interactive Knowledge Graph<a href="https://robert-mcdermott.medium.com/from-unstructured-text-to-interactive-knowledge-graphs-using-llms-dd02a1f71cd6">https://robert-mcdermott.medium.com/from-unstructured-text-to-interactive-knowledge-graphs-using-llms-dd02a1f71cd6</a><a href="https://memgraph.com/blog/vector-search-memgraph-knowledge-graph-demo">https://memgraph.com/blog/vector-search-memgraph-knowledge-graph-demo</a><a href="https://github.com/FareedKhan-dev/KG-Pipeline">https://github.com/FareedKhan-dev/KG-Pipeline</a>  </td></tr></tbody></table></figure>