已比較的版本

索引鍵

  • 此行已新增。
  • 此行已移除。
  • 格式已變更。

你可以依照類別找到相關的 FAQ

...

關於 GAISF
錨點
About-GAISF-CN
About-GAISF-CN

展開
title什麼是聯發科技生成式 AI 服務框架 (GAI Service Framework, GAISF)?

聯發科技生成式 AI 服務框架 (GAISF) 是企業的中央人工智慧大腦,透過 API 在企業內提供生成式 AI 服務,同時遵守用戶資料隱私規範,不斷改進和擴展以採用更多生成型 AI 服務。

Image Added

關於 MediaTek DaVinci (達哥)
錨點
About-DaVinci-CN
About-DaVinci-CN

展開
title什麼是 MediaTek DaVinci (達哥) 聊天機器人?

MediaTek DaVinci (達哥) 聊天機器人是一款基於生成式 AI 服務框架 (GAISF),類似於 ChatGPT 的應用服務。MediaTek DaVinci 被設計為你的個人助理,以提你的日常工作的效率。除此之外,MediaTek DaVinci 同時也是一個開放平台,開發人員可在此建立插件與現有的系統及服務進行整合。

Image Added
展開
titleMediaTek DaVinci 相較於其他平台 (例如: ChatGPT) 的優勢是什麼?

MediaTek DaVinci 是一個開方式平台,我們相容所有市面上的語言模型,不論從閉源的 Azure OpenAI GPT-4, Claude3, 到開源 (llama2, mistral) 或是自行微調的模型 (breeze-7b, breexe 8x7B 由 MediaTek Research 微調的繁體中文大模型)。因此在服務體驗 (模型成功達成任務的穩定性)、資料機敏性 (可提供地端部署模型,讓所有資料都鎖在企業內部)、成本控管角度 (任務有難易之分,難的可請 GPT-4,簡易的可請Claude3 或甚至開源模型,以達到更有性價比的使用生成式 AI 服務) 等都能夠打造符合企業要求的版本。

展開
title在 MediaTek DaVinci

...

PIM

...

Others

上開發 plugin 與在 OpenAI 上開發的差異是什麼?

MediaTek DaVinci 提供兩種開發 plugin 的方式,1) 以 OpenAPI 方式 2) 以 python 寫程式方式開發。因此,以支援 OpenAPI 的方式來說確實相容 OpenAI 的 plugin;然而,若有更多客製化的開發需求,MediaTek DaVinci 提供 python 寫程式的方式開發,可達到更多樣化的方式開發。

展開
title在 MediaTek DaVinci Store 上提供的重要元件「Plugin」、「Prompt Template」、「DVCx」、「Assistant」分別是什麼? 又該如何開發與上架呢?

重要元件的介紹、使用方是、上架方式請看這裡

開發方式請看這裡這裡

關於用戶隱私
錨點
About-User-Data-Privacy-CN
About-User-Data-Privacy-CN

展開
title生成式 AI 服務提供商 (MSFT) 會重複使用我的 Prompt 或數據來訓練他們的 AI 模型嗎?

答案是 "不會"。生成式 AI 服務提供商 (MSFT) 不能也不會重複使用你的 Prompt、結果或任何客戶數據來重新訓練其自己的模型。

展開
title生成式 AI 服務提供商 (MSFT) 會有我的對話紀錄嗎?他們能訪問我在 MediaTek DaVinci 中上傳的對話數據或檔案嗎?

答案是"不會"。我們已申請 "選擇不進行日誌記錄和人工審核程序",並已獲得微軟的批准。這意味著你的 Prompt 和結果不會記錄在 Azure 雲端服務中。簡而言之,你在使用 Azure OpenAI 服務時不會在雲端留下任何痕跡。

展開
titleMediaTek DaVinci (達哥) 是否使用 OpenAI 的 ChatGPT 服務?

答案是"否"。我們使用的是微軟 Azure OpenAI 服務,而不是 OpenAI ChatGPT 服務。

Image Added

其他
錨點
Others-CN
Others-CN

展開
titleDaVinci 支援哪些瀏覽器?
  • Chrome 版本需要 Chrome 102 或者更新

  • Edge 需要使用 Chromium core

展開
title什麼是 Tokens?如何計算我問題和回答中的 Tokens 數量?
  1. Tokens 是 Azure OpenAI GPT 模型(包括 GPT3.5/4)用來計算文本長度的基本單位。它們是字符的組合,有時候與單詞數相同,但並不總是如此。具體來說,它取決於字符數量並包括標點符號或表情符號。這就是為什麼 Tokens 數量通常與單詞數量不同。

  2. 為了準確知道你的文本中花費了多少個 Tokens,你需要將你的文本進行 Tokens 化,意味著運行一個 Tokens 化算法來計數所有的 Tokens。聽起來困難?實際上只需複製粘貼而已,十分簡單。
    你可以使用 https://www.gptcalculator.xyz/ 來計算。

  3. 想知更多關於 Token 的資訊

展開
title如何提升我的 Prompt 提示技巧?是否有任何資源可以與我分享?

我們強烈建議從下列資源學習:

  1. 外部資源:大量的影片可以協助你提升 Prompt 提示技巧

  2. 以下是一些極佳的 Prompt 提示技巧範本,供你參考:https://github.com/f/awesome-chatgpt-prompts

...

About GAISF
錨點
About-GAISF
About-GAISF

展開
titleWhat is Generative AI Service Framework (GAISF)?

The GAI Service Framework (GAISF) is the central AI brain that delivers generative AI services via API services across the enterprise, in compliance with PIM policiesuser data privacy, and is continuously improved and extensible to adopt new GAI services.

Image Added

About MediaTek DaVinci
錨點
About-DaVinci
About-DaVinci

展開
titleWhat is MediaTek DaVinci chatbot?

MediaTek DaVinci chatbot is a web-based, ChatGPT-like application based on the GAI Service Framework (GAISF). MediaTek DaVinci is designed to be a personal assistant to increase your productivity in daily work.  More than this, MediaTek DaVinci is also an open platform for developers to create plugins to integrate with existing system & services.

Image Added
展開
titleWhat are the advantages of MediaTek DaVinci compared to other platforms (e.g., ChatGPT)?

MediaTek DaVinci is an open platform that is compatible with all language models available on the market, ranging from proprietary models like Azure OpenAI GPT-4 and Claude3, to open-source models (llama2, mistral), and even custom-tuned models (breeze-7b, breeze 8x7B by MediaTek Research tailored for Traditional Chinese). This compatibility allows for a service experience (model success stability), data sensitivity (offering on-premise deployment to keep all data within the company), and cost control (tasks vary in difficulty, with complex ones possibly requiring GPT-4, simpler ones could use Claude3 or even open-source models, achieving a more cost-effective generative AI service) that can meet enterprise requirements.

...

展開
titleWhat is the difference between developing plugins on MediaTek DaVinci and on OpenAI?

MediaTek DaVinci offers two ways to develop plugins: 1) Using the OpenAPI specification 2) Programming in Python. Thus, in terms of supporting OpenAPI, it is indeed compatible with OpenAI plugins; however, for more customized development needs, MediaTek DaVinci allows for programming in Python, enabling a more diverse development approach.

展開
titleWhat are the key components offered on the MediaTek DaVinci Store: "Plugin", "Prompt Template", "DVCx", "Assistant", and how can they be developed and listed?

For an introduction to the key components, their uses, and listing methods, please refer to link.

For development methods, please see here and here.

About User Data Privacy
錨點
About-

...

User-Data-Privacy
About-

...

User-Data-Privacy

展開
titleWill GAI service providers (MSFT) reuse my prompt or data to train their AI models?

The Answer is "No".  GAI service provider (MSFT) cannot and will not reuse MediaTek your prompt, result or any customer data to retrain its own model. 

展開
titleDoes the GAI service provider (MSFT) have any record of our my conversations? Can they access to our my conversation data or files that we uploaded in DaVinci?

The Answer is "No".  MediaTek We has applied "opted out of the logging and human review process " and has been approved by Microsoft. This means that MediaTek users' your prompts and results are not logged in the Azure cloud services. In short, no footprint in the cloud while you use Azure OpenAI Service. 

展開
titleIs MediaTek DaVinci using OpenAI's ChatGPT service?

The Answer is "No".  We use Microsoft Azure OpenAI Service, instead of OpenAI ChatGPT service. 

Image Added

Others
錨點
Others
Others

展開
titleWhat browsers does DaVinci support?
  • The Chrome version required must be Chrome 102 or above.

  • Edge needs to use the Chromium core.

展開
titleWhat are Tokens? How to count tokens in my prompt & Answeranswer?
  1. Tokens are the basic unit that Azure OpenAI GPT models (including GPT3.5/4) use to compute the length of a text. They are groups of characters, which sometimes align with words, but not always. In particular, it depends on the number of characters and includes punctuation signs or emojis. This is why the tokens count is usually different from the word count.

  2. In order to know exactly how many tokens spent in your text, you need to tokenize your text, which means running a tokenizer algorithm that will count all the tokens. Sounds difficult? It’s actually as easy as copy/pasting. You can use https://www.gptcalculator.xyz/  

  3. For more information about Token

...