From deep learning to LLMs to generative AI, we live in a world where AI has the power to transform just about everything, whether it's handling customer support or generating code.

從深度學習到 LLM，再到生成式人工智能，我們生活在一個人工智能能夠改變一切的世界，無論是處理客戶支持還是生成代碼。

AI wasn't always so pervasive, though.

不過，人工智能並不總是如此普及。

The first AI tools had significant limitations.

最初的人工智能工具有很大的侷限性。

They couldn't understand context or learn and improve on their own.

他們無法理解上下文，也無法自主學習和提高。

The first chatbots, for example, were rule-based, meaning they were developed based on predefined rules or scripts.

例如，最早的哈拉機器人是基於規則的，這意味著它們是根據預定義的規則或腳本開發的。

This severely restricted their capacity to just what was fed into them, the same way any computing software can only perform the tasks that it was programmed to perform.

這嚴重限制了它們的能力，使其只能執行輸入的內容，就像任何計算機軟件只能執行編程規定的任務一樣。

AI-based chatbots have come a long way since then.

從那時起，基於人工智能的哈拉機器人已經取得了長足的進步。

They're leveraging advancements in machine learning and deep learning capabilities to improve the understanding of natural language.

他們正在利用先進的機器學習和深度學習能力來提高對自然語言的理解。

Now with the adoption of LLMs, we're seeing a new evolution.

現在，隨著法律碩士的採用，我們看到了新的發展。

Large language models use massive amounts of data and a combination of deep learning algorithms, neural networks, and natural language processing techniques to generate human-like responses to queries.

大型語言模型使用海量數據，結合深度學習算法、神經網絡和自然語言處理技術，生成類似人類的查詢回覆。

Let's show what we're talking about with Watson X Assistant, a conversational AI platform designed to build and deploy AI-powered chatbots.

讓我們用 Watson X Assistant 展示一下我們在說什麼，這是一個對話式人工智能平臺，旨在構建和部署人工智能驅動的哈拉機器人。

With the emergence of generative AI, Watson X Assistant is working to transform user experiences and deliver more intelligent human-like responses.

隨著生成式人工智能的出現，Watson X Assistant 正在努力改變用戶體驗，並提供更多類似人類的智能響應。

Today we'll show you how to leverage Neuralseq, which is a search and natural language generation system that we'll integrate with Watson X Assistant.

今天，我們將向你展示如何利用 Neuralseq，這是一個搜索和自然語言生成系統，我們將把它與 Watson X Assistant 集成在一起。

First, we need to set up Watson X Discovery, which is where our data will be stored.

首先，我們需要設置 Watson X Discovery，也就是存儲數據的地方。

Let's use Robotic Vacuum Manuals as our example and go into Improve and Customize to test it.

讓我們以《機器人真空吸塵器手冊》為例，進入 "改進 "和 "自定義 "進行測試。

Let's ask, how do I change the filter?

請問，如何更換過濾器？

The answer we get isn't great, so let's try asking it another question, how often should I change the mopping pad?

我們得到的答案並不理想，所以我們試著問另一個問題：我應該多久更換一次拖布墊？

This time it doesn't answer the question we were asking at all.

這一次，它根本沒有回答我們提出的問題。

To improve our answers, let's set up Neuralseq to work with Discovery and Assistant.

為了改進我們的答案，讓我們設置 Neuralseq 與 Discovery 和 Assistant 協同工作。

Now let's go into the initial setup page to further fine-tune our extension.

現在，讓我們進入初始設置頁面，進一步微調我們的擴展。

We've already pre-filled the initial information here, like what we're talking about, and we've also connected with Watson Discovery.

我們已經預先在這裡填寫了初始資訊，比如我們正在談論的內容，我們還連接了沃森探索系統。

Then in the About section, it came up with this paragraph on its own.

然後，在 "關於 "部分，它自己出現了這樣一段話。

In tune, we're basically seeing how it should look, as well as whether we should be looking at newer or older documents.

在調整過程中，我們基本上是在看它應該是什麼樣子，以及我們應該看新文件還是舊文件。

And now in Q&A, this actually looks at all of our documents and generates some questions for us to bootstrap our actions in Watson X Assistant.

現在，在問答中，它會查看我們的所有文檔，並生成一些問題，供我們在 Watson X Assistant 中引導操作。

So it's saying that based on this data, we think people are going to be asking these questions.

所以說，根據這些數據，我們認為人們會問這些問題。

Now click on the Integrate tab.

現在點擊 "整合 "選項卡。

From here, make note of your API key and download your custom OpenAPI file.

在這裡，請記下您的 API 密鑰並下載自定義 OpenAPI 文件。

Now open the Integrations page in Watson X Assistant and click Build Custom Extension.

現在打開 Watson X 助手中的集成頁面，點擊 "構建自定義擴展"。

Follow the steps to import your OpenAPI file and click Finish.

按照步驟導入 OpenAPI 文件，然後單擊完成。

Now scroll down and click Add on your Neuralseq tile to add the extension.

現在向下滾動並單擊 Neuralseq 磁貼上的 "添加 "來添加擴展。

Follow the steps to set up the authentication for Neuralseq.

請按照以下步驟為 Neuralseq 設置身份驗證。

For the authentication type, be sure to set it to API Key Auth and paste your Neuralseq API key from earlier in the indicated field.

對於驗證類型，請務必將其設置為 API Key Auth，並在指定資料欄中粘貼之前輸入的 Neuralseq API 密鑰。

Click through to finish.

點擊完成。

Now that we've set up our Neuralseq extension, let's go ahead and add it to our dialog.

既然我們已經設置了 Neuralseq 擴展，那就把它添加到對話框中吧。

First create a new action skill.

首先創建一個新的動作技能。

Next we're going to create an action and quick start with a template before adding our Neuralseq starter kit, which we just generated.

接下來，我們將創建一個動作和快速啟動模板，然後添加我們剛剛生成的 Neuralseq 入門套件。

Here you can see we have our Neuralseq search action.

在這裡，你可以看到我們的 Neuralseq 搜索行動。

We need to configure it.

我們需要對其進行配置。

So you can see that it's generated all this information for us.

是以，你可以看到它為我們生成了所有這些資訊。

We need to edit our extension, select the extension we just created, and for the operation we would like to seek an answer from Neuralseq.

我們需要編輯我們的擴展，選擇我們剛剛創建的擴展，並選擇我們希望從 Neuralseq 尋求答案的操作。

For parameters, we'll set question equal to query underscore text.

對於參數，我們將問題設置為查詢下劃線文本。

Click Apply and then save the action.

單擊 "應用"，然後保存操作。

Now we want to go to no action matches, which means that if we can't match any of the phrases to anything we've set up in Watson X Assistant, it's going to go out to Neuralseq and get that answer for us from Discovery.

現在，我們要選擇 "無動作匹配"，這意味著如果我們無法將任何短語與 Watson X Assistant 中設置的任何內容相匹配，它就會轉到 Neuralseq，從 Discovery 中為我們獲取答案。

Let's remove the pre-filled text.

讓我們刪除預填文字。

So this is basically like the anything else node.

是以，這基本上就像其他節點一樣。

Now let's go to a sub action and go to Neuralseq search before hitting apply, then save, then preview.

現在，讓我們轉到子操作，在點擊應用、保存、預覽之前轉到神經序列搜索。

Let's ask Watson X Assistant, how do I change the filter?

讓我們問問 Watson X 助手，如何更換過濾器？

It's going out to Neuralseq and here you can see the response that it's generated.

它將被髮送到 Neuralseq，在這裡你可以看到它產生的響應。

To change the filter, open the filter door, remove the filter by grasping the tab, shake off debris, reinsert the filter, and close the filter door.

要更換過濾器，請打開過濾器門，抓住卡扣取下過濾器，抖掉碎屑，重新插入過濾器，然後關上過濾器門。

Replace the filter every two months.

每兩個月更換一次過濾器。

This is a really good and accurate response.

這是一個非常好、非常準確的答覆。

Now let's ask our other question.

現在我們來問另一個問題。

How often should I change the mopping pad?

拖布墊多久更換一次？

It's going back to Neuralseq again and gives us the correct response.

它會再次回到 Neuralseq，並給出正確的回覆。

As you can see, our Neuralseq extension can help your chatbots carry out conversations just as well as any human could, and that's due to its generative AI capabilities.

正如您所看到的，我們的 Neuralseq 擴展可以幫助您的哈拉機器人像人類一樣進行對話，這得益於它的生成式人工智能功能。

To learn more about how you can leverage generative AI with Watson X Assistant, please visit the Watson X Assistant page on ibm.com.

要進一步瞭解如何利用 Watson X Assistant 生成人工智能，請訪問 ibm.com 上的 Watson X Assistant 頁面。

Thank you.

謝謝。

If you have questions, please drop us a line below.

如果您有任何問題，請在下方給我們留言。

If you want to see more videos like this in the future, please like and subscribe.

如果您希望今後看到更多類似視頻，請點贊和訂閱。