From 54ca303efcf82b5b2bca428528f0142223ff6171 Mon Sep 17 00:00:00 2001 From: John Aziz Date: Wed, 7 Aug 2024 11:29:32 +0000 Subject: [PATCH 1/4] fix broken paths --- .../python/aoai-assignment.ipynb | 8 ++------ 07-building-chat-applications/python/oai-assignment.ipynb | 4 +--- .../python/aoai-solution.ipynb | 2 +- 08-building-search-applications/python/oai-solution.ipynb | 2 +- .../python/aoai-assignment.ipynb | 2 +- 11-integrating-with-function-calling/README.md | 2 +- .../translations/tw/README.md | 2 +- 15-rag-and-vector-databases/translations/cn/README.md | 2 +- 8 files changed, 9 insertions(+), 15 deletions(-) diff --git a/07-building-chat-applications/python/aoai-assignment.ipynb b/07-building-chat-applications/python/aoai-assignment.ipynb index 4f8d997ff..ea8a7b7a6 100644 --- a/07-building-chat-applications/python/aoai-assignment.ipynb +++ b/07-building-chat-applications/python/aoai-assignment.ipynb @@ -92,9 +92,7 @@ }, "source": [ "### Build your first prompt \n", - "This short exercise will provide a basic introduction for submitting prompts to an OpenAI model for a simple task \"summarization\". \n", - "\n", - "![](images/generative-AI-models-reduced.jpg) \n", + "This short exercise will provide a basic introduction for submitting prompts to an OpenAI model for a simple task \"summarization\".\n", "\n", "\n", "**Steps**: \n", @@ -209,8 +207,7 @@ "### 3. Finding the right model \n", "The GPT-3.5-turbo or GPT-4 models can understand and generate natural language. The service offers four model capabilities, each with different levels of power and speed suitable for different tasks. \n", "\n", - "[Azure OpenAI models](https://learn.microsoft.com/azure/cognitive-services/openai/concepts/models?WT.mc_id=academic-105485-koreyst) \n", - "![](images/a-b-c-d-models-reduced.jpg) \n" + "[Azure OpenAI models](https://learn.microsoft.com/azure/cognitive-services/openai/concepts/models?WT.mc_id=academic-105485-koreyst)\n" ] }, { @@ -296,7 +293,6 @@ } }, "source": [ - "![](images/prompt_design.jpg)\n", "image is creating your first text prompt!" ] }, diff --git a/07-building-chat-applications/python/oai-assignment.ipynb b/07-building-chat-applications/python/oai-assignment.ipynb index 9f61a486a..2238ce72f 100644 --- a/07-building-chat-applications/python/oai-assignment.ipynb +++ b/07-building-chat-applications/python/oai-assignment.ipynb @@ -74,9 +74,7 @@ }, "source": [ "### Build your first prompt \n", - "This short exercise will provide a basic introduction for submitting prompts to an OpenAI model for a simple task \"summarization\". \n", - "\n", - "![](images/generative-AI-models-reduced.jpg) \n", + "This short exercise will provide a basic introduction for submitting prompts to an OpenAI model for a simple task \"summarization\".\n", "\n", "\n", "**Steps**: \n", diff --git a/08-building-search-applications/python/aoai-solution.ipynb b/08-building-search-applications/python/aoai-solution.ipynb index ea9b5da82..e68d2167f 100644 --- a/08-building-search-applications/python/aoai-solution.ipynb +++ b/08-building-search-applications/python/aoai-solution.ipynb @@ -142,7 +142,7 @@ "4. Finally, the `display_results` function is called to display the results to the user.\n", "5. The user is then prompted to enter another query. This process continues until the user enters `exit`.\n", "\n", - "![](media/notebook_search.png)\n", + "![](../images/notebook-search.png)\n", "\n", "You will be prompted to enter a query. Enter a query and press enter. The application will return a list of videos that are relevant to the query. The application will also return a link to the place in the video where the answer to the question is located.\n", "\n", diff --git a/08-building-search-applications/python/oai-solution.ipynb b/08-building-search-applications/python/oai-solution.ipynb index 38b9853d2..b67322844 100644 --- a/08-building-search-applications/python/oai-solution.ipynb +++ b/08-building-search-applications/python/oai-solution.ipynb @@ -140,7 +140,7 @@ "4. Finally, the `display_results` function is called to display the results to the user.\n", "5. The user is then prompted to enter another query. This process continues until the user enters `exit`.\n", "\n", - "![](media/notebook_search.png)\n", + "![](../images/notebook-search.png)\n", "\n", "You will be prompted to enter a query. Enter a query and press enter. The application will return a list of videos that are relevant to the query. The application will also return a link to the place in the video where the answer to the question is located.\n", "\n", diff --git a/09-building-image-applications/python/aoai-assignment.ipynb b/09-building-image-applications/python/aoai-assignment.ipynb index 52714f289..d9d7d91d4 100644 --- a/09-building-image-applications/python/aoai-assignment.ipynb +++ b/09-building-image-applications/python/aoai-assignment.ipynb @@ -299,7 +299,7 @@ " The base image would only contain the rabbit but the final image would have the hat on the rabbit.\n", " \n", "- **Create variations**. \n", - " Look at our [OpenAI notebook for more information](/09-building-image-applications/openai/notebook-openai.ipynb)." + " Look at our [OpenAI notebook for more information](./oai-assignment.ipynb)." ] } ], diff --git a/11-integrating-with-function-calling/README.md b/11-integrating-with-function-calling/README.md index 31a2ca3b6..a5bdeb1d9 100644 --- a/11-integrating-with-function-calling/README.md +++ b/11-integrating-with-function-calling/README.md @@ -45,7 +45,7 @@ Function Calling is a feature of the Azure OpenAI Service to overcome to the fol ## Illustrating the problem through a scenario -> We recommend you to use the [included notebook](/11-integrating-with-function-calling/python/aoai-assignment.ipynb) if you want to run the below scenario. You can also just read along as we're trying to illustrate a problem where functions can help to address the problem. +> We recommend you to use the [included notebook](./python/aoai-assignment.ipynb) if you want to run the below scenario. You can also just read along as we're trying to illustrate a problem where functions can help to address the problem. Let's look at the example that illustrates the response format problem: diff --git a/11-integrating-with-function-calling/translations/tw/README.md b/11-integrating-with-function-calling/translations/tw/README.md index 5a7b11601..b312ee1ae 100644 --- a/11-integrating-with-function-calling/translations/tw/README.md +++ b/11-integrating-with-function-calling/translations/tw/README.md @@ -45,7 +45,7 @@ ## 通過情境說明問題 -> 我們建議你使用[內建筆記本](/11-integrating-with-function-calling/Lesson11-FunctionCalling.ipynb)如果你想要執行以下場景。你也可以只是閱讀，因為我們正在嘗試說明一個函式可以幫助解決的問題。 +> 我們建議你使用[內建筆記本](../../python/aoai-assignment.ipynb)如果你想要執行以下場景。你也可以只是閱讀，因為我們正在嘗試說明一個函式可以幫助解決的問題。 讓我們看看說明回應格式問題的範例: diff --git a/15-rag-and-vector-databases/translations/cn/README.md b/15-rag-and-vector-databases/translations/cn/README.md index 3877d8c19..a0ad1cf65 100644 --- a/15-rag-and-vector-databases/translations/cn/README.md +++ b/15-rag-and-vector-databases/translations/cn/README.md @@ -92,7 +92,7 @@ def split_text(text, max_length, min_length): ``` 一旦完成分块，我们就可以使用不同的嵌入模型来嵌入我们的文本。您可以使用的一些模型包括word2vec、OpenAI的ada-002、Azure Computer Vision等。选择使用哪个模型将取决于您使用的语言、编码的内容类型（文本/图像/音频）、它可以编码的输入大小以及嵌入输出的长度。 -使用OpenAI的`text-embedding-ada-002`模型嵌入文本的示例是：![嵌入单词cat的示例](images/cat.png?WT.mc_id=academic-105485-koreyst) +使用OpenAI的`text-embedding-ada-002`模型嵌入文本的示例是：![嵌入单词cat的示例](../../images/cat.png?WT.mc_id=academic-105485-koreyst) ## 检索和向量搜索 From cedede7a846a0b48371a7c3fa6e3b4b7cbd65514 Mon Sep 17 00:00:00 2001 From: John Aziz Date: Wed, 7 Aug 2024 11:32:54 +0000 Subject: [PATCH 2/4] fix paths tracking --- 08-building-search-applications/python/aoai-solution.ipynb | 2 +- 08-building-search-applications/python/oai-solution.ipynb | 2 +- 09-building-image-applications/python/aoai-assignment.ipynb | 2 +- 11-integrating-with-function-calling/README.md | 2 +- 11-integrating-with-function-calling/translations/tw/README.md | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/08-building-search-applications/python/aoai-solution.ipynb b/08-building-search-applications/python/aoai-solution.ipynb index e68d2167f..7bb4e2907 100644 --- a/08-building-search-applications/python/aoai-solution.ipynb +++ b/08-building-search-applications/python/aoai-solution.ipynb @@ -142,7 +142,7 @@ "4. Finally, the `display_results` function is called to display the results to the user.\n", "5. The user is then prompted to enter another query. This process continues until the user enters `exit`.\n", "\n", - "![](../images/notebook-search.png)\n", + "![](../images/notebook-search.png?WT.mc_id=academic-105485-koreyst)\n", "\n", "You will be prompted to enter a query. Enter a query and press enter. The application will return a list of videos that are relevant to the query. The application will also return a link to the place in the video where the answer to the question is located.\n", "\n", diff --git a/08-building-search-applications/python/oai-solution.ipynb b/08-building-search-applications/python/oai-solution.ipynb index b67322844..fd572aa75 100644 --- a/08-building-search-applications/python/oai-solution.ipynb +++ b/08-building-search-applications/python/oai-solution.ipynb @@ -140,7 +140,7 @@ "4. Finally, the `display_results` function is called to display the results to the user.\n", "5. The user is then prompted to enter another query. This process continues until the user enters `exit`.\n", "\n", - "![](../images/notebook-search.png)\n", + "![](../images/notebook-search.png?WT.mc_id=academic-105485-koreyst)\n", "\n", "You will be prompted to enter a query. Enter a query and press enter. The application will return a list of videos that are relevant to the query. The application will also return a link to the place in the video where the answer to the question is located.\n", "\n", diff --git a/09-building-image-applications/python/aoai-assignment.ipynb b/09-building-image-applications/python/aoai-assignment.ipynb index d9d7d91d4..28a9a4a43 100644 --- a/09-building-image-applications/python/aoai-assignment.ipynb +++ b/09-building-image-applications/python/aoai-assignment.ipynb @@ -299,7 +299,7 @@ " The base image would only contain the rabbit but the final image would have the hat on the rabbit.\n", " \n", "- **Create variations**. \n", - " Look at our [OpenAI notebook for more information](./oai-assignment.ipynb)." + " Look at our [OpenAI notebook for more information](./oai-assignment.ipynb?WT.mc_id=academic-105485-koreyst)." ] } ], diff --git a/11-integrating-with-function-calling/README.md b/11-integrating-with-function-calling/README.md index a5bdeb1d9..5c5ff6b51 100644 --- a/11-integrating-with-function-calling/README.md +++ b/11-integrating-with-function-calling/README.md @@ -45,7 +45,7 @@ Function Calling is a feature of the Azure OpenAI Service to overcome to the fol ## Illustrating the problem through a scenario -> We recommend you to use the [included notebook](./python/aoai-assignment.ipynb) if you want to run the below scenario. You can also just read along as we're trying to illustrate a problem where functions can help to address the problem. +> We recommend you to use the [included notebook](./python/aoai-assignment.ipynb?WT.mc_id=academic-105485-koreyst) if you want to run the below scenario. You can also just read along as we're trying to illustrate a problem where functions can help to address the problem. Let's look at the example that illustrates the response format problem: diff --git a/11-integrating-with-function-calling/translations/tw/README.md b/11-integrating-with-function-calling/translations/tw/README.md index b312ee1ae..2aa194b1f 100644 --- a/11-integrating-with-function-calling/translations/tw/README.md +++ b/11-integrating-with-function-calling/translations/tw/README.md @@ -45,7 +45,7 @@ ## 通過情境說明問題 -> 我們建議你使用[內建筆記本](../../python/aoai-assignment.ipynb)如果你想要執行以下場景。你也可以只是閱讀，因為我們正在嘗試說明一個函式可以幫助解決的問題。 +> 我們建議你使用[內建筆記本](../../python/aoai-assignment.ipynb?WT.mc_id=academic-105485-koreyst)如果你想要執行以下場景。你也可以只是閱讀，因為我們正在嘗試說明一個函式可以幫助解決的問題。 讓我們看看說明回應格式問題的範例: From d9adbbd522009216a4c73d236c878b4537b5e0a5 Mon Sep 17 00:00:00 2001 From: John Aziz Date: Wed, 7 Aug 2024 11:58:19 +0000 Subject: [PATCH 3/4] fix broken urls --- 02-exploring-and-comparing-different-llms/README.md | 2 +- .../translations/cn/README.md | 2 +- .../translations/ja-jp/README.md | 2 +- .../translations/ko/README.md | 2 +- .../translations/pt-br/README.md | 2 +- .../translations/tw/README.md | 2 +- 08-building-search-applications/README.md | 2 +- 08-building-search-applications/translations/cn/README.md | 4 ++-- 08-building-search-applications/translations/ko/README.md | 4 ++-- 08-building-search-applications/translations/pt-br/README.md | 4 ++-- 08-building-search-applications/translations/tw/README.md | 4 ++-- 10-building-low-code-ai-applications/README.md | 2 +- .../translations/cn/README.md | 2 +- .../translations/ja-jp/README.md | 2 +- .../translations/ko/README.md | 2 +- .../translations/pt-br/README.md | 2 +- .../translations/tw/README.md | 2 +- 17 files changed, 21 insertions(+), 21 deletions(-) diff --git a/02-exploring-and-comparing-different-llms/README.md b/02-exploring-and-comparing-different-llms/README.md index 9876f01cd..7cbd94a7a 100644 --- a/02-exploring-and-comparing-different-llms/README.md +++ b/02-exploring-and-comparing-different-llms/README.md @@ -65,7 +65,7 @@ Image source: [2108.07258.pdf (arxiv.org)](https://arxiv.org/pdf/2108.07258.pdf? Another way to categorize LLMs is whether they are open source or proprietary. -Open-source models are models that are made available to the public and can be used by anyone. They are often made available by the company that created them, or by the research community. These models are allowed to be inspected, modified, and customized for the various use cases in LLMs. However, they are not always optimized for production use, and may not be as performant as proprietary models. Plus, funding for open-source models can be limited, and they may not be maintained long term or may not be updated with the latest research. Examples of popular open source models include [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-koreyst), [Bloom](https://sapling.ai/llm/bloom?WT.mc_id=academic-105485-koreyst) and [LLaMA](https://sapling.ai/llm/llama?WT.mc_id=academic-105485-koreyst). +Open-source models are models that are made available to the public and can be used by anyone. They are often made available by the company that created them, or by the research community. These models are allowed to be inspected, modified, and customized for the various use cases in LLMs. However, they are not always optimized for production use, and may not be as performant as proprietary models. Plus, funding for open-source models can be limited, and they may not be maintained long term or may not be updated with the latest research. Examples of popular open source models include [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-koreyst), [Bloom](https://huggingface.co/bigscience/bloom) and [LLaMA](https://llama.meta.com). Proprietary models are models that are owned by a company and are not made available to the public. These models are often optimized for production use. However, they are not allowed to be inspected, modified, or customized for different use cases. Plus, they are not always available for free, and may require a subscription or payment to use. Also, users do not have control over the data that is used to train the model, which means they should entrust the model owner with ensuring commitment to data privacy and responsible use of AI. Examples of popular proprietary models include [OpenAI models](https://platform.openai.com/docs/models/overview?WT.mc_id=academic-105485-koreyst), [Google Bard](https://sapling.ai/llm/bard?WT.mc_id=academic-105485-koreyst) or [Claude 2](https://www.anthropic.com/index/claude-2?WT.mc_id=academic-105485-koreyst). diff --git a/02-exploring-and-comparing-different-llms/translations/cn/README.md b/02-exploring-and-comparing-different-llms/translations/cn/README.md index 045c9c156..9e24b8bca 100644 --- a/02-exploring-and-comparing-different-llms/translations/cn/README.md +++ b/02-exploring-and-comparing-different-llms/translations/cn/README.md @@ -62,7 +62,7 @@ LLM 模型有许多不同类型，您选择的模型取决于您的用途、您 对 LLM 进行分类的另一种方法是它们是开源的还是专有的。 -开源模型是向公众开放并且任何人都可以使用的模型。 它们通常由创建它们的公司或研究团体提供。 这些模型可以针对 LLMs 的各种用例进行检查、修改和定制。 然而，它们并不总是针对生产用途进行优化，并且可能不如专有模型具备高性能。 此外，开源模型的资金可能有限，并且它们可能无法长期维护或可能无法根据最新研究进行更新。 流行的开源模型的例子包括 [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html)、[Bloom](https://sapling.ai/llm/bloom) 和 [ LLaMA](https://sapling.ai/llm/llama?WT.mc_id=academic-105485-koreyst)。 +开源模型是向公众开放并且任何人都可以使用的模型。 它们通常由创建它们的公司或研究团体提供。 这些模型可以针对 LLMs 的各种用例进行检查、修改和定制。 然而，它们并不总是针对生产用途进行优化，并且可能不如专有模型具备高性能。 此外，开源模型的资金可能有限，并且它们可能无法长期维护或可能无法根据最新研究进行更新。 流行的开源模型的例子包括 [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html)、[Bloom](https://huggingface.co/bigscience/bloom) 和 [ LLaMA](https://llama.meta.com)。 专有模型是公司拥有的模型，不向公众提供。 这些模型通常针对生产用途进行了优化。 但是，不允许针对特定的使用场景进行检查、修改或定制它们。 另外，它们并不总是免费提供，可能需要订阅或付费才能使用。 此外，用户无法控制用于训练模型的数据，这意味着他们应该委托模型所有者确保对数据隐私和负责任地使用人工智能的承诺。 流行的专有模型的例子包括 [OpenAI 模型](https://platform.openai.com/docs/models/overview)、[Google Bard](https://sapling.ai/llm/bard?WT.mc_id=academic-105485-koreyst) 或 [Claude 2](https://www.anthropic.com/index/claude-2)。 diff --git a/02-exploring-and-comparing-different-llms/translations/ja-jp/README.md b/02-exploring-and-comparing-different-llms/translations/ja-jp/README.md index 67bab8956..9d55e2770 100644 --- a/02-exploring-and-comparing-different-llms/translations/ja-jp/README.md +++ b/02-exploring-and-comparing-different-llms/translations/ja-jp/README.md @@ -62,7 +62,7 @@ LLM モデルには、さまざまな種類があり、どのモデルを選択 大規模言語モデル（LLM）を分類する別の方法として、それがオープンソースなのか、もしくはプロプライエタリな物なのか、という観点もあります。 -オープンソース・モデルは、一般に公開され、誰でも利用できるモデルです。これらは多くの場合、そのモデルを開発した企業や研究コミュニティによって提供されます。これらのモデルは、LLM の様々な用途に合わせて検証、変更、カスタマイズの許可がされています。しかし、常に本番環境での利用に最適化されているわけではなく、プロプライエタリモデルほど高いパフォーマンスを発揮しない場合もあります。さらに、オープンソース・モデルの資金調達は限られており、長期的に継続できない可能性や、最新の研究に基づいて更新されていない可能性もあります。[Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-yoterada)、[Bloom](https://sapling.ai/llm/bloom?WT.mc_id=academic-105485-yoterada)、[LLaMA](https://sapling.ai/llm/llama?WT.mc_id=academic-105485-yoterada) などが人気のオープンソース・モデルの例です。 +オープンソース・モデルは、一般に公開され、誰でも利用できるモデルです。これらは多くの場合、そのモデルを開発した企業や研究コミュニティによって提供されます。これらのモデルは、LLM の様々な用途に合わせて検証、変更、カスタマイズの許可がされています。しかし、常に本番環境での利用に最適化されているわけではなく、プロプライエタリモデルほど高いパフォーマンスを発揮しない場合もあります。さらに、オープンソース・モデルの資金調達は限られており、長期的に継続できない可能性や、最新の研究に基づいて更新されていない可能性もあります。[Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-yoterada)、[Bloom](https://huggingface.co/bigscience/bloom)、[LLaMA](https://llama.meta.com) などが人気のオープンソース・モデルの例です。 プロプライエタリ・モデルは、企業が所有し一般には公開されていないモデルです。これらのモデルは、通常本番環境での利用に最適化されています。しかし異なるユースケースに対して、検証、変更、カスタマイズは許可されていません。また、常に無料で利用できるわけではなく、利用するためには、サブスクリプション等による支払いが必要な場合もあります。さらに、利用者はモデルをトレーニングする際に使用するデータをコントロールできず、データのプライバシーや、責任ある AI の原則に基づく使用をモデル・プロバイダが保証しているのを信用しなければなりません。[OpenAI のモデル](https://platform.openai.com/docs/models/overview?WT.mc_id=academic-105485-yoterada)、[Google Bard](https://sapling.ai/llm/bard?WT.mc_id=academic-105485-yoterada)、[Claude 2](https://www.anthropic.com/index/claude-2?WT.mc_id=academic-105485-yoterada) などが人気のプロプライエタリ・モデルです。 diff --git a/02-exploring-and-comparing-different-llms/translations/ko/README.md b/02-exploring-and-comparing-different-llms/translations/ko/README.md index 054f9b1ba..8b5b5fa05 100644 --- a/02-exploring-and-comparing-different-llms/translations/ko/README.md +++ b/02-exploring-and-comparing-different-llms/translations/ko/README.md @@ -61,7 +61,7 @@ Foundation Model이라는 용어는 [스탠포드 연구원들에 의해 만들 LLM을 분류하는 또 다른 방법은 오픈 소스인지 독점 모델인지에 따라 나눌 수 있습니다. -오픈 소스 모델은 일반에 공개되어 누구나 사용할 수 있는 모델입니다. 이러한 모델은 일반적으로 해당 모델을 개발한 회사나 연구 커뮤니티에 의해 제공됩니다. 이러한 모델은 검토, 수정 및 사용 사례에 맞게 사용자 정의할 수 있습니다. 그러나 이러한 모델은 항상 프로덕션 환경에 최적화되지 않을 수 있으며, 독점 모델만큼 성능이 우수하지 않을 수도 있습니다. 또한, 오픈 소스 모델의 자금 지원은 제한적일 수 있으며, 장기적으로 유지되지 않거나 최신 연구로 업데이트되지 않을 수도 있습니다. 대표적인 오픈 소스 모델로는 [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-koreyst), [Bloom](https://sapling.ai/llm/bloom?WT.mc_id=academic-105485-koreyst) 및 [LLaMA](https://sapling.ai/llm/llama?WT.mc_id=academic-105485-koreyst)이 있습니다. +오픈 소스 모델은 일반에 공개되어 누구나 사용할 수 있는 모델입니다. 이러한 모델은 일반적으로 해당 모델을 개발한 회사나 연구 커뮤니티에 의해 제공됩니다. 이러한 모델은 검토, 수정 및 사용 사례에 맞게 사용자 정의할 수 있습니다. 그러나 이러한 모델은 항상 프로덕션 환경에 최적화되지 않을 수 있으며, 독점 모델만큼 성능이 우수하지 않을 수도 있습니다. 또한, 오픈 소스 모델의 자금 지원은 제한적일 수 있으며, 장기적으로 유지되지 않거나 최신 연구로 업데이트되지 않을 수도 있습니다. 대표적인 오픈 소스 모델로는 [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-koreyst), [Bloom](https://huggingface.co/bigscience/bloom) 및 [LLaMA](https://llama.meta.com)이 있습니다. 독점 모델 (Proprietary models)은 회사에 소유되어 일반에 공개되지 않는 모델입니다. 이러한 모델은 일반적으로 프로덕션 환경에 최적화되어 있습니다. 그러나 이러한 모델은 사용자가 검토, 수정 또는 사용 사례에 맞게 사용자 정의할 수 없습니다. 또한, 이러한 모델은 항상 무료로 제공되지 않을 수 있으며, 사용을 위해 구독 또는 결제가 필요할 수 있습니다. 또한, 사용자는 모델을 훈련하는 데 사용되는 데이터를 제어할 수 없으므로 데이터 프라이버시와 AI의 책임있는 사용을 보장하기 위해 모델 소유자에게 의존해야 합니다. 대표적인 독점 모델로는 [OpenAI 모델](https://platform.openai.com/docs/models/overview?WT.mc_id=academic-105485-koreyst), [Google Bard](https://sapling.ai/llm/bard?WT.mc_id=academic-105485-koreyst) 및 [Claude 2](https://www.anthropic.com/index/claude-2?WT.mc_id=academic-105485-koreyst)가 있습니다. diff --git a/02-exploring-and-comparing-different-llms/translations/pt-br/README.md b/02-exploring-and-comparing-different-llms/translations/pt-br/README.md index b470939ed..a3f617ffe 100644 --- a/02-exploring-and-comparing-different-llms/translations/pt-br/README.md +++ b/02-exploring-and-comparing-different-llms/translations/pt-br/README.md @@ -65,7 +65,7 @@ Fonte da imagem: [2108.07258.pdf (arxiv.org)](https://arxiv.org/pdf/2108.07258.p Outra maneira de categorizar os Modelos de Linguagem de Grande Escala (LLMs) é se eles são de código aberto ou proprietários. -Os modelos de código aberto são modelos que são disponibilizados ao público e podem ser usados por qualquer pessoa. Eles são frequentemente disponibilizados pela empresa que os criou ou pela comunidade de pesquisa. Esses modelos podem ser inspecionados, modificados e personalizados para diversos casos de uso em LLMs. No entanto, nem sempre são otimizados para uso em produção e podem não ser tão eficientes quanto os modelos proprietários. Além disso, o financiamento para modelos de código aberto pode ser limitado, e eles podem não ser mantidos a longo prazo ou não ser atualizados com as pesquisas mais recentes. Exemplos de modelos de código aberto populares incluem [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-koreyst), [Bloom](https://sapling.ai/llm/bloom?WT.mc_id=academic-105485-koreyst) e [LLaMA](https://sapling.ai/llm/llama?WT.mc_id=academic-105485-koreyst). +Os modelos de código aberto são modelos que são disponibilizados ao público e podem ser usados por qualquer pessoa. Eles são frequentemente disponibilizados pela empresa que os criou ou pela comunidade de pesquisa. Esses modelos podem ser inspecionados, modificados e personalizados para diversos casos de uso em LLMs. No entanto, nem sempre são otimizados para uso em produção e podem não ser tão eficientes quanto os modelos proprietários. Além disso, o financiamento para modelos de código aberto pode ser limitado, e eles podem não ser mantidos a longo prazo ou não ser atualizados com as pesquisas mais recentes. Exemplos de modelos de código aberto populares incluem [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-koreyst), [Bloom](https://huggingface.co/bigscience/bloom) e [LLaMA](https://llama.meta.com). Os modelos proprietários são modelos de propriedade de uma empresa e não são disponibilizados ao público. Esses modelos são frequentemente otimizados para uso em produção. No entanto, não podem ser inspecionados, modificados ou personalizados para diferentes casos de uso. Além disso, nem sempre estão disponíveis gratuitamente e podem exigir uma assinatura ou pagamento para uso. Além disso, os usuários não têm controle sobre os dados usados para treinar o modelo, o que significa que devem confiar ao proprietário do modelo o compromisso com a privacidade dos dados e o uso responsável da IA. Exemplos de modelos proprietários populares incluem [modelos da OpenAI](https://platform.openai.com/docs/models/overview?WT.mc_id=academic-105485-koreyst), [Google Bard](https://sapling.ai/llm/bard?WT.mc_id=academic-105485-koreyst) ou [Claude 2](https://www.anthropic.com/index/claude-2?WT.mc_id=academic-105485-koreyst). diff --git a/02-exploring-and-comparing-different-llms/translations/tw/README.md b/02-exploring-and-comparing-different-llms/translations/tw/README.md index 11006bbd8..695e824a7 100644 --- a/02-exploring-and-comparing-different-llms/translations/tw/README.md +++ b/02-exploring-and-comparing-different-llms/translations/tw/README.md @@ -64,7 +64,7 @@ LLMs 可以根據其架構、訓練數據和使用案例進行多種分類。了 另一種分類 LLMs 的方式是它們是開放原始碼還是專有的。 -開放原始碼模型是公開提供給大眾使用的模型，任何人都可以使用。這些模型通常由創建它們的公司或研究社群提供。這些模型允許被檢查、修改和自訂，以適應LLM的各種使用案例。然而，它們並不總是針對生產使用進行最佳化，性能可能不如專有模型。此外，開放原始碼模型的資金可能有限，可能不會長期維護或更新最新的研究。受歡迎的開放原始碼模型範例包括[Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-koreyst)、[Bloom](https://sapling.ai/llm/bloom?WT.mc_id=academic-105485-koreyst)和[LLaMA](https://sapling.ai/llm/llama?WT.mc_id=academic-105485-koreyst)。 +開放原始碼模型是公開提供給大眾使用的模型，任何人都可以使用。這些模型通常由創建它們的公司或研究社群提供。這些模型允許被檢查、修改和自訂，以適應LLM的各種使用案例。然而，它們並不總是針對生產使用進行最佳化，性能可能不如專有模型。此外，開放原始碼模型的資金可能有限，可能不會長期維護或更新最新的研究。受歡迎的開放原始碼模型範例包括[Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html?WT.mc_id=academic-105485-koreyst)、[Bloom](https://huggingface.co/bigscience/bloom)和[LLaMA](https://llama.meta.com)。 專有模型是由公司擁有且不對公眾開放的模型。這些模型通常針對生產用途進行最佳化。然而，它們不允許被檢查、修改或針對不同的使用案例進行自訂。此外，它們並不總是免費提供，可能需要訂閱或支付費用才能使用。而且，使用者無法控制用於訓練模型的數據，這意味著他們應該信任模型擁有者來確保對數據隱私和負責任使用 AI 的承諾。流行的專有模型範例包括[OpenAI models](https://platform.openai.com/docs/models/overview?WT.mc_id=academic-105485-koreyst)、[Google Bard](https://sapling.ai/llm/bard?WT.mc_id=academic-105485-koreyst)或[Claude 2](https://www.anthropic.com/index/claude-2?WT.mc_id=academic-105485-koreyst)。 diff --git a/08-building-search-applications/README.md b/08-building-search-applications/README.md index 40514a013..b9ad736ba 100644 --- a/08-building-search-applications/README.md +++ b/08-building-search-applications/README.md @@ -65,7 +65,7 @@ The Embedding index for this lesson was created with a series of Python scripts. The scripts perform the following operations: -1. The transcript for each YouTube video in the [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-koreyst) playlist is downloaded. +1. The transcript for each YouTube video in the [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) playlist is downloaded. 2. Using [OpenAI Functions](https://learn.microsoft.com/azure/ai-services/openai/how-to/function-calling?WT.mc_id=academic-105485-koreyst), an attempt is made to extract the speaker name from the first 3 minutes of the YouTube transcript. The speaker name for each video is stored in the Embedding Index named `embedding_index_3m.json`. 3. The transcript text is then chunked into **3 minute text segments**. The segment includes about 20 words overlapping from the next segment to ensure that the Embedding for the segment is not cut off and to provide better search context. 4. Each text segment is then passed to the OpenAI Chat API to summarize the text into 60 words. The summary is also stored in the Embedding Index `embedding_index_3m.json`. diff --git a/08-building-search-applications/translations/cn/README.md b/08-building-search-applications/translations/cn/README.md index 9be6c8846..bd8feb89b 100644 --- a/08-building-search-applications/translations/cn/README.md +++ b/08-building-search-applications/translations/cn/README.md @@ -29,7 +29,7 @@ LLMs 应用场景不仅仅是聊天机器人和文本生成。 还可以使用 创建搜索应用将帮助您了解如何使用嵌入来搜索数据。 您还将学习如何构建可供学生快速查找信息的搜索应用程序。 -本课程包括 Microsoft [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-koreyst) YouTube 频道的 YouTube 记录的嵌入索引。 AI Show 是一个 YouTube 频道，向您介绍人工智能和机器学习。 嵌入索引包含截至 2023 年 10 月每个 YouTube 记录的嵌入。您将使用嵌入索引为“Our Startup”构建搜索应用程序。 搜索应用程序返回视频中问题答案所在位置的链接。 这是学生快速找到所需信息的好方法。 +本课程包括 Microsoft [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) YouTube 频道的 YouTube 记录的嵌入索引。 AI Show 是一个 YouTube 频道，向您介绍人工智能和机器学习。 嵌入索引包含截至 2023 年 10 月每个 YouTube 记录的嵌入。您将使用嵌入索引为“Our Startup”构建搜索应用程序。 搜索应用程序返回视频中问题答案所在位置的链接。 这是学生快速找到所需信息的好方法。 以下是问题“can you use rstudio with azure ml?”的语义查询示例。 查看 YouTube 网址，您会看到该网址包含一个时间戳，可将您带到视频中问题答案所在的位置。 @@ -63,7 +63,7 @@ Today we are going to learn about Azure Machine Learning. 这些脚本执行以下操作： -1. 下载 [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-koreyst) 播放列表中每个 YouTube 视频的文字记录。 +1. 下载 [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) 播放列表中每个 YouTube 视频的文字记录。 2. 使用[OpenAI Functions](https://learn.microsoft.com/azure/ai-services/openai/how-to/function-calling?WT.mc_id=academic-105485-koreyst)，尝试 从 YouTube 记录的前 3 分钟中提取演讲者姓名。 每个视频的演讲者姓名存储在名为 `embedding_index_3m.json` 的嵌入索引中。 3. 然后将转录文本分成 **3 分钟的文本片段**。 该片段包含大约 20 个与下一个片段重叠的单词，以确保该片段的嵌入不会被切断并提供更好的搜索上下文。 4. 然后，每个文本片段都会传递到 OpenAI Chat API，将文本总结为 60 个单词。 摘要也存储在嵌入索引 `embedding_index_3m.json` 中。 diff --git a/08-building-search-applications/translations/ko/README.md b/08-building-search-applications/translations/ko/README.md index a189dd277..39f0e88d8 100644 --- a/08-building-search-applications/translations/ko/README.md +++ b/08-building-search-applications/translations/ko/README.md @@ -29,7 +29,7 @@ LLM(대형 언어 모델)은 챗봇과 텍스트 생성 이상의 기능을 가 검색 애플리케이션을 만드는 것은 Embedding을 사용하여 데이터를 검색하는 방법을 이해하는 데 도움이 됩니다. 또한 학생들이 정보를 빠르게 찾을 수 있는 검색 애플리케이션을 만드는 방법을 배우게 될 것입니다. -이 레슨에는 Microsoft [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-koreyst) YouTube 채널의 YouTube 비디오 트랜스크립트의 Embedding 인덱스가 포함되어 있습니다. AI Show는 AI와 머신러닝에 대해 가르치는 YouTube 채널입니다. Embedding 인덱스에는 2023년 10월까지의 각 YouTube 트랜스크립트에 대한 Embedding이 포함되어 있습니다. 우리 스타트업을 위해 Embedding 인덱스를 사용하여 검색 애플리케이션을 만들 것입니다. 검색 애플리케이션은 질문의 답변이 있는 비디오의 위치로 이동할 수 있는 링크를 반환합니다. 이는 학생들이 필요한 정보를 빠르게 찾는 좋은 방법입니다. +이 레슨에는 Microsoft [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) YouTube 채널의 YouTube 비디오 트랜스크립트의 Embedding 인덱스가 포함되어 있습니다. AI Show는 AI와 머신러닝에 대해 가르치는 YouTube 채널입니다. Embedding 인덱스에는 2023년 10월까지의 각 YouTube 트랜스크립트에 대한 Embedding이 포함되어 있습니다. 우리 스타트업을 위해 Embedding 인덱스를 사용하여 검색 애플리케이션을 만들 것입니다. 검색 애플리케이션은 질문의 답변이 있는 비디오의 위치로 이동할 수 있는 링크를 반환합니다. 이는 학생들이 필요한 정보를 빠르게 찾는 좋은 방법입니다. 다음은 질문 'Azure ML에서 rstudio를 사용할 수 있나요?'에 대한 의미 기반 쿼리의 예입니다. YouTube URL을 확인해보면, 질문의 답변이 있는 비디오의 위치로 이동하는 타임스탬프가 URL에 포함되어 있습니다. @@ -63,7 +63,7 @@ LLM(대형 언어 모델)은 챗봇과 텍스트 생성 이상의 기능을 가 이 스크립트는 다음과 같은 작업을 수행합니다: -1. [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-koreyst) 재생목록의 각 YouTube 비디오의 트랜스크립트를 다운로드합니다. +1. [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) 재생목록의 각 YouTube 비디오의 트랜스크립트를 다운로드합니다. 2. [OpenAI Functions](https://learn.microsoft.com/azure/ai-services/openai/how-to/function-calling?WT.mc_id=academic-105485-koreyst)를 사용하여 YouTube 트랜스크립트의 처음 3분에서 스피커 이름을 추출하려고 시도합니다. 각 비디오의 스피커 이름은 `embedding_index_3m.json`이라는 임베딩 인덱스에 저장됩니다. 3. 그런 다음 트랜스크립트 텍스트를 **3분 텍스트 세그먼트**로 분할합니다. 세그먼트에는 임베딩이 잘리지 않도록 하고 더 나은 검색 문맥을 제공하기 위해 다음 세그먼트에서 약 20개의 단어가 겹치도록 설계되었습니다. 4. 각 텍스트 세그먼트는 OpenAI Chat API에 전달되어 텍스트를 60단어로 요약합니다. 이 요약은 임베딩 인덱스 `embedding_index_3m.json`에도 저장됩니다. diff --git a/08-building-search-applications/translations/pt-br/README.md b/08-building-search-applications/translations/pt-br/README.md index dbb8773d9..39d96e3a0 100644 --- a/08-building-search-applications/translations/pt-br/README.md +++ b/08-building-search-applications/translations/pt-br/README.md @@ -29,7 +29,7 @@ Após completar esta lição, você será capaz de: Criar uma aplicação de busca ajudará você a entender como usar Embeddings para buscar dados. Você também aprenderá como construir uma aplicação de busca que pode ser usada por estudantes para encontrar informações rapidamente. -A lição inclui um Índice de Embeddings dos transcritos do YouTube para o canal [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-koreyst) da Microsoft no YouTube. O AI Show é um canal do YouTube que ensina sobre IA e aprendizado de máquina. O Índice de Embeddings contém os Embeddings para cada um dos transcritos do YouTube até outubro de 2023. Você usará o Índice de Embeddings para construir uma aplicação de busca para nossa startup. A aplicação de busca retorna um link para o local no vídeo onde está localizada a resposta para a pergunta. Esta é uma ótima maneira para os estudantes encontrarem rapidamente as informações de que precisam. +A lição inclui um Índice de Embeddings dos transcritos do YouTube para o canal [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) da Microsoft no YouTube. O AI Show é um canal do YouTube que ensina sobre IA e aprendizado de máquina. O Índice de Embeddings contém os Embeddings para cada um dos transcritos do YouTube até outubro de 2023. Você usará o Índice de Embeddings para construir uma aplicação de busca para nossa startup. A aplicação de busca retorna um link para o local no vídeo onde está localizada a resposta para a pergunta. Esta é uma ótima maneira para os estudantes encontrarem rapidamente as informações de que precisam. Abaixo nós temos um exemplo de uma consulta semântica para a pergunta: 'É possível usar o RStudio com o Azure ML?'. Confira a URL do YouTube, você verá que a URL contém um carimbo de data/hora que o leva para o local no vídeo onde está localizada @@ -63,7 +63,7 @@ O Índice de Embeddings para esta lição foi criado com uma série de scripts P Os scripts executam as seguintes operações: -1. A transcrição de cada vídeo do YouTube na lista de reprodução [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-koreyst) é baixada. +1. A transcrição de cada vídeo do YouTube na lista de reprodução [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) é baixada. 2. Usando [OpenAI Functions](https://learn.microsoft.com/azure/ai-services/openai/how-to/function-calling?WT.mc_id=academic-105485-koreyst), uma tentativa é feita para extrair o nome do orador dos primeiros 3 minutos do transcrição do YouTube. O nome do orador para cada vídeo é armazenado no Índice de Embeddings chamado `embedding_index_3m.json`. diff --git a/08-building-search-applications/translations/tw/README.md b/08-building-search-applications/translations/tw/README.md index 7cddda6ac..525ffe050 100644 --- a/08-building-search-applications/translations/tw/README.md +++ b/08-building-search-applications/translations/tw/README.md @@ -31,7 +31,7 @@ 建立搜尋應用程式將幫助你了解如何使用嵌入來搜尋資料。你還將學習如何建構一個學生可以用來快速找到資訊的搜尋應用程式。 -這課程包括 Microsoft [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-koreyst) YouTube 頻道的 YouTube 文字記錄的嵌入索引。AI Show 是一個教你關於 AI 和機器學習的 YouTube 頻道。嵌入索引包含截至 2023 年 10 月的每個 YouTube 文字記錄的嵌入。你將使用嵌入索引為我們的初創公司建構一個搜尋應用程式。搜尋應用程式會返回一個連結，指向影片中回答問題的位置。這是一個讓學生快速找到所需資訊的好方法。 +這課程包括 Microsoft [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) YouTube 頻道的 YouTube 文字記錄的嵌入索引。AI Show 是一個教你關於 AI 和機器學習的 YouTube 頻道。嵌入索引包含截至 2023 年 10 月的每個 YouTube 文字記錄的嵌入。你將使用嵌入索引為我們的初創公司建構一個搜尋應用程式。搜尋應用程式會返回一個連結，指向影片中回答問題的位置。這是一個讓學生快速找到所需資訊的好方法。 以下是一個針對問題「你可以將 rstudio 與 azure ml 一起使用嗎？」的語義查詢範例。查看 YouTube 連結, 你會看到連結包含一個時間戳記, 它會帶你到影片中回答問題的位置。 @@ -65,7 +65,7 @@ 腳本執行以下操作: -1. 每個 YouTube 影片在 [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-koreyst) 播放清單中的逐字稿會被下載。 +1. 每個 YouTube 影片在 [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) 播放清單中的逐字稿會被下載。 2. 使用 [OpenAI 函式](https://learn.microsoft.com/azure/ai-services/openai/how-to/function-calling?WT.mc_id=academic-105485-koreyst)，嘗試從 YouTube 逐字稿的前 3 分鐘中提取講者姓名。每個影片的講者姓名會儲存在名為 `embedding_index_3m.json` 的嵌入索引中。 3. 然後將逐字稿文本分塊成 **3 分鐘文本片段**。每個片段包括大約 20 個與下一個片段重疊的單詞，以確保片段的嵌入不會被切斷，並提供更好的搜索上下文。 4. 然後將每個文本片段傳遞給 OpenAI 聊天 API，將文本摘要為 60 個單詞。摘要也會儲存在嵌入索引 `embedding_index_3m.json` 中。 diff --git a/10-building-low-code-ai-applications/README.md b/10-building-low-code-ai-applications/README.md index 7f7e17ac9..997f71144 100644 --- a/10-building-low-code-ai-applications/README.md +++ b/10-building-low-code-ai-applications/README.md @@ -71,7 +71,7 @@ The copilot AI assistant feature in Power Automate enables you to describe what Our startup provides online courses to students. The startup has grown rapidly and is now struggling to keep up with the demand for its courses. The startup has hired you as a Power Platform developer to help them build a low code solution to help them manage their student assignments and invoices. Their solution should be able to help them track and manage student assignments through an app and automate the invoice processing process through a workflow. You have been asked to use Generative AI to develop the solution. -When you are getting started with using Copilot, you can use the [Power Platform Copilot Prompt Library](https://pnp.github.io/powerplatform-prompts/?WT.mc_id=academic-109639-somelezediko) to get started with the prompts. This library contains a list of prompts that you can use to build apps and flows with Copilot. You can also use the prompts in the library to get an idea of how to describe your requirements to Copilot. +When you are getting started with using Copilot, you can use the [Power Platform Copilot Prompt Library](https://github.com/pnp/powerplatform-prompts?WT.mc_id=academic-109639-somelezediko) to get started with the prompts. This library contains a list of prompts that you can use to build apps and flows with Copilot. You can also use the prompts in the library to get an idea of how to describe your requirements to Copilot. ### Build a Student Assignment Tracker App for Our Startup diff --git a/10-building-low-code-ai-applications/translations/cn/README.md b/10-building-low-code-ai-applications/translations/cn/README.md index 01e821f68..b41cc86c6 100644 --- a/10-building-low-code-ai-applications/translations/cn/README.md +++ b/10-building-low-code-ai-applications/translations/cn/README.md @@ -71,7 +71,7 @@ Power Automate 中的 Copilot AI 助手功能使您能够描述您需要哪种 “Our Startup” 为学生提供在线课程。 这家初创公司发展迅速，目前正在努力满足其课程的需求。 该初创公司聘请您作为 Power Platform 开发人员，帮助他们构建低代码解决方案，以帮助他们管理学生作业和发票。 他们的解决方案应该能够帮助他们通过应用程序跟踪和管理学生作业，并通过工作流程自动化发票处理过程。 您被要求使用生成式人工智能来开发解决方案。 -当您开始使用 Copilot 时，可以使用 [Power Platform Copilot Prompt 库](https://pnp.github.io/powerplatform-prompts/?WT.mc_id=academic-109639-somelezediko) 作为提示词。 该库包含一系列提示，您可以使用这些提示与 Copilot 一起构建应用程序和流程。 您还可以使用库中的提示来了解如何向 Copilot 描述您的需求。 +当您开始使用 Copilot 时，可以使用 [Power Platform Copilot Prompt 库](https://github.com/pnp/powerplatform-prompts?WT.mc_id=academic-109639-somelezediko) 作为提示词。 该库包含一系列提示，您可以使用这些提示与 Copilot 一起构建应用程序和流程。 您还可以使用库中的提示来了解如何向 Copilot 描述您的需求。 ### 为 “Our Startup” 构建学生作业跟踪应用程序 diff --git a/10-building-low-code-ai-applications/translations/ja-jp/README.md b/10-building-low-code-ai-applications/translations/ja-jp/README.md index d8d5329fe..4ab3ef8b7 100644 --- a/10-building-low-code-ai-applications/translations/ja-jp/README.md +++ b/10-building-low-code-ai-applications/translations/ja-jp/README.md @@ -71,7 +71,7 @@ Power Automate における Copilot AI アシスタント機能を利用する スタートアップは、学生にオンラインコースを提供しています。スタートアップは急速に成長し、そのコースの需要に対応するのが難しくなっています。スタートアップはあなたを Power Platform 開発者として新たに採用し、学生の課題と請求書を管理するためのローコードソリューションを構築するように依頼しました。そのソリューションは、アプリを通じて学生の課題の追跡と管理を行い、ワークフローを通じて請求処理のプロセスを自動化するのに役立ちます。あなたは、ソリューションを開発するために生成 AI を使用するように指示されています。 -Copilot を使い始める際には、[Power Platform Copilot Prompt Library](https://pnp.github.io/powerplatform-prompts/?WT.mc_id=academic-109639yoterada) を使用して、プロンプトを使い始めます。このライブラリには Copilot と共に、アプリやフローを作成するためのプロンプトのリストが含まれています。また、ライブラリ内のプロンプトを使用して、Copilot に対して要件をどのように説明できるのかといったアイデアを得られます。 +Copilot を使い始める際には、[Power Platform Copilot Prompt Library](https://github.com/pnp/powerplatform-prompts?WT.mc_id=academic-109639yoterada) を使用して、プロンプトを使い始めます。このライブラリには Copilot と共に、アプリやフローを作成するためのプロンプトのリストが含まれています。また、ライブラリ内のプロンプトを使用して、Copilot に対して要件をどのように説明できるのかといったアイデアを得られます。 ### スタートアップによる学生課題追跡アプリの構築 diff --git a/10-building-low-code-ai-applications/translations/ko/README.md b/10-building-low-code-ai-applications/translations/ko/README.md index 6ec3342d9..dd0a1b63b 100644 --- a/10-building-low-code-ai-applications/translations/ko/README.md +++ b/10-building-low-code-ai-applications/translations/ko/README.md @@ -71,7 +71,7 @@ Power Automate의 Copilot AI 어시스턴트 기능을 사용하면 필요한 우리 스타트업은 학생들에게 온라인 강좌를 제공합니다. 스타트업은 빠르게 성장하여 강좌 수요를 따라가기 어려워졌습니다. 스타트업은 학생 과제와 송장 처리 프로세스를 관리하기 위해 low code 솔루션을 구축하는 데 도움을 받기 위해 Power Platform 개발자로서 여러분을 고용했습니다. 솔루션은 앱을 통해 학생 과제를 추적하고 관리하며, 워크플로우를 통해 송장 처리 프로세스를 자동화해야 합니다. 여러분은 생성형 AI를 사용하여 솔루션을 개발하도록 요청받았습니다. -Copilot 사용을 시작할 때는 [Power Platform Copilot Prompt Library](https://pnp.github.io/powerplatform-prompts/?WT.mc_id=academic-109639-somelezediko)를 사용하여 프롬프트로 시작할 수 있습니다. 이 라이브러리에는 Copilot을 사용하여 앱과 플로우를 구축하는 데 사용할 수 있는 프롬프트 목록이 포함되어 있습니다. 또한 라이브러리의 프롬프트를 사용하여 Copilot에게 요구 사항을 설명하는 방법에 대한 아이디어를 얻을 수 있습니다. +Copilot 사용을 시작할 때는 [Power Platform Copilot Prompt Library](https://github.com/pnp/powerplatform-prompts?WT.mc_id=academic-109639-somelezediko)를 사용하여 프롬프트로 시작할 수 있습니다. 이 라이브러리에는 Copilot을 사용하여 앱과 플로우를 구축하는 데 사용할 수 있는 프롬프트 목록이 포함되어 있습니다. 또한 라이브러리의 프롬프트를 사용하여 Copilot에게 요구 사항을 설명하는 방법에 대한 아이디어를 얻을 수 있습니다. ### 학생 과제 추적 앱 구축하기 diff --git a/10-building-low-code-ai-applications/translations/pt-br/README.md b/10-building-low-code-ai-applications/translations/pt-br/README.md index f6e3923c3..968c0f7b1 100644 --- a/10-building-low-code-ai-applications/translations/pt-br/README.md +++ b/10-building-low-code-ai-applications/translations/pt-br/README.md @@ -58,7 +58,7 @@ O recurso de assistente de IA Copilot no Power Automate permite que você descre Nossa startup fornece cursos online para estudantes. A startup cresceu rapidamente e está enfrentando dificuldades para acompanhar a demanda por seus cursos. A startup contratou você como desenvolvedor da Power Platform para ajudá-los a criar uma solução de baixo código para ajudá-los a gerenciar suas atribuições de estudantes e faturas. Sua solução deve ser capaz de ajudá-los a rastrear e gerenciar as atribuições de estudantes por meio de um aplicativo e automatizar o processo de processamento de faturas por meio de um fluxo. Foi solicitado a você que use a IA generativa para desenvolver a solução. -Quando estiver começando a usar o Copilot, você pode usar a [Biblioteca de Prompts do Power Platform Copilot](https://pnp.github.io/powerplatform-prompts/?WT.mc_id=academic-109639-somelezediko) para começar com os prompts. Esta biblioteca contém uma lista de prompts que você pode usar para criar aplicativos e fluxos com Copilot. Você também pode usar os prompts na biblioteca para ter uma ideia de como descrever seus requisitos para o Copilot. +Quando estiver começando a usar o Copilot, você pode usar a [Biblioteca de Prompts do Power Platform Copilot](https://github.com/pnp/powerplatform-prompts?WT.mc_id=academic-109639-somelezediko) para começar com os prompts. Esta biblioteca contém uma lista de prompts que você pode usar para criar aplicativos e fluxos com Copilot. Você também pode usar os prompts na biblioteca para ter uma ideia de como descrever seus requisitos para o Copilot. ### Criando um Aplicativo de Rastreamento de Atribuições de Estudantes para Nossa Startup diff --git a/10-building-low-code-ai-applications/translations/tw/README.md b/10-building-low-code-ai-applications/translations/tw/README.md index 07e2279bc..111b01cdf 100644 --- a/10-building-low-code-ai-applications/translations/tw/README.md +++ b/10-building-low-code-ai-applications/translations/tw/README.md @@ -71,7 +71,7 @@ Power Automate 中的副駕駛 AI 助手功能使您能夠描述您需要的流 我們的初創公司為學生提供線上課程。該初創公司發展迅速，現在難以應對課程的需求。該初創公司聘請了你作為 Power Platform 開發人員，幫助他們建構一個低程式碼解決方案，以幫助他們管理學生作業和發票。他們的解決方案應能通過應用程式幫助他們追蹤和管理學生作業，並通過工作流程自動化發票處理過程。你被要求使用生成式 AI 開發該解決方案。 -當你開始使用 Copilot 時，你可以使用 [Power Platform Copilot Prompt Library](https://pnp.github.io/powerplatform-prompts/?WT.mc_id=academic-109639-somelezediko) 來開始使用提示。此函式庫包含一系列提示，你可以用來與 Copilot 一起建構應用程式和流程。你也可以使用函式庫中的提示來了解如何向 Copilot 描述你的需求。 +當你開始使用 Copilot 時，你可以使用 [Power Platform Copilot Prompt Library](https://github.com/pnp/powerplatform-prompts?WT.mc_id=academic-109639-somelezediko) 來開始使用提示。此函式庫包含一系列提示，你可以用來與 Copilot 一起建構應用程式和流程。你也可以使用函式庫中的提示來了解如何向 Copilot 描述你的需求。 ### 建構我們新創公司的學生作業追蹤應用程式 From 3e4b224f74b7d6811d081c25ccd5f224e3fd6803 Mon Sep 17 00:00:00 2001 From: John Aziz Date: Wed, 7 Aug 2024 12:02:49 +0000 Subject: [PATCH 4/4] fix broken url --- 08-building-search-applications/translations/ja-jp/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/08-building-search-applications/translations/ja-jp/README.md b/08-building-search-applications/translations/ja-jp/README.md index b62461ddc..3e572573b 100644 --- a/08-building-search-applications/translations/ja-jp/README.md +++ b/08-building-search-applications/translations/ja-jp/README.md @@ -29,7 +29,7 @@ LLM は、チャットボットやテキスト生成だけでなく、Embeddings 実際に検索アプリケーションを作成すると、Embeddings を使用したデータの検索技術を習得できます。また、学生が情報を素早く見つけるための検索アプリケーションの作り方も学べます。 -このレッスンでは、Microsoft の [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-yoterada) という YouTube チャンネルから、YouTube の字幕を抜き出し、それを Embedding 検索用のインデックスとして利用する方法について紹介します。AI Show は、AI と機械学習について学べる YouTube チャンネルです。Embedding 用のインデックスは、2023 年 10 月までの各 YouTube にアップロードされた動画の字幕を含めています。この Embedding インデックスを使用して、スタートアップ用の検索アプリケーションを作ります。この検索アプリケーションは、質問の答えが動画のどの部分にあるかを示すリンクも返します。これは、学生が必要な情報を素早く見つけるのに非常に役立ちます。 +このレッスンでは、Microsoft の [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) という YouTube チャンネルから、YouTube の字幕を抜き出し、それを Embedding 検索用のインデックスとして利用する方法について紹介します。AI Show は、AI と機械学習について学べる YouTube チャンネルです。Embedding 用のインデックスは、2023 年 10 月までの各 YouTube にアップロードされた動画の字幕を含めています。この Embedding インデックスを使用して、スタートアップ用の検索アプリケーションを作ります。この検索アプリケーションは、質問の答えが動画のどの部分にあるかを示すリンクも返します。これは、学生が必要な情報を素早く見つけるのに非常に役立ちます。 下記は、「Azure ML で rstudio を使えますか？」という質問に対するセマンティック・クエリの例です。YouTube の URL を見てみると、URL には質問の答えがどの動画のどの部分にあるかを示すタイムスタンプが含まれています。 @@ -70,7 +70,7 @@ LLM は、チャットボットやテキスト生成だけでなく、Embeddings スクリプト内部では下記の操作を行っています： -1. [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1?WT.mc_id=academic-105485-yoterada) プレイリスト中の各 YouTube 動画の字幕をダウンロードします。 +1. [AI Show](https://www.youtube.com/playlist?list=PLlrxD0HtieHi0mwteKBOfEeOYf0LJU4O1) プレイリスト中の各 YouTube 動画の字幕をダウンロードします。 2. [OpenAI の Function Calling](https://learn.microsoft.com/azure/ai-services/openai/how-to/function-calling?WT.mc_id=academic-105485-yoterada) を使用して、YouTube 字幕の最初から 3 分で発表者の名前を抽出します。各動画の発表者の名前は、`embedding_index_3m.json` という名前の埋め込みインデックスに保存します。 3. その後、字幕テキストは「**3 分間のテキストブロック**」に分割します。各ブロックには、次のブロックから約 20 語を重複して含め、各ブロックの埋め込みが途切れないように、より良い検索コンテキストを提供します。 4. 各テキストブロックを OpenAI の Chat API に渡し、テキストを 60 語に要約します。この要約結果も `embedding_index_3m.json` という埋め込みインデックスに保存します。