Sinch Community

When using a Knowledge base AI, it might be useful to tell your bot which content to scrape. For example, if a customer asks for something on topic X, it's better if your bot only looks for the content on topic X at that point in your conversation. You can define different categories of topic by using tags.   Add tags to your content Adding tags to your pieces of content is an optional step when creating your knowledge base.   To add tags to your content: Add a piece of content. When the window pops up, you have the option to add a tag under Tag this source. You can either: create a tag from this field or select a tag that you've already created   Edit tags Once all your sources are added to the knowledge base, you can still edit your tags. To edit tags: Click the three dots at the end of the line where your content is listed. Click the Edit option. In the window that pops up, you can remove existing tags or add new tags.   Use tags in your knowledge base flow Tags become useful when you add them to your knowledge base flow so that they limit where your chatbot will look for an answer.   To use tags in your knowledge base flow: Build your flow. Open your Knowledge base AI block that retrieves the answer. Under Limit your content, choose the tags of the sources that you would like your bot to visit. Only the pieces of content that have the tag that is specified in the Knowledge base AI action will be used to generate the answer. Save your changes.     Example use case An example use case would be a bot that has a lot of content uploaded to it from different sources, but needs to give a specific answers when it comes to questions about security.   The "security" intent catches all questions related to security. When that intent is triggered, the bot answers through the Knowledge base AI content that is tagged with "security". Afterwards, the bot will provide a link where more security information can be found:       See also: Knowledge base AI introduction Create a FAQ flow with a generative knowledge base Non-generative knowledge base   ... View more

If for some reason you don't want your bot to use generative AI, but still want it to be able to easily retrieve FAQ answers, we've got you covered.   Setting up a non-generative knowledge base AI means that: your bot will be able to understand multiple sentences from your users (i.e. natural language understanding from the AI engine is taking place) but your bot will answer only the sentence that you defined as an answer (i.e. the bot answers are not generated) Note that with a non-generative knowledge base, you'll only be able to upload questions and answers only in the form of a .csv file.   Set up your non-generative knowledge base   To set up your non-generative knowledge base: Decline the Generative AI terms and conditions when opening your Knowledge Base AI tab for the first time Click on Add content: you should only be able to add .csv files from there. Click on Download .csv template file. Open this file and add your questions and answers like below:   5. Save your changes. 6. Come back to your bot, click on Choose files to upload your file to your knowledge base. 7. Click on Add. 8. When the status turns to green, test your bot, you're good to go! 9. Build your knowledge base flow. 10. Test it out.       See also: Knowledge base AI introduction Create a FAQ flow with a generative knowledge base AI Use tags to limit your content ... View more

In this article, you'll learn how to select then add content to create your generative knowledge base. This happens in 3 steps: Select relevant content Add content Build a flow   Select relevant content In order to get the best possible results from your knowledge base AI, it's important to keep a few guidelines in mind when selecting content: Only include data that is relevant to the questions from users. If you have a PDF with 100 pages, of which only 1 is relevant for customers, extract that page, and upload it separately. In PDFs and URLs, complicated layouts might decrease the quality of the results The knowledge base AI isn't good at understanding data from a table. Don't use knowledge base to upload database files. Currently, knowledge base AI isn't able to process any images, video's or other media types Currently, if your website requires JavaScript to be loaded, it can't be read by the knowledge base If the URL has scraping protection activated, such as Incapsula, the webpage won't be able to be added to your knowledge base AI Now, you know better what content your bot would scrape. Let's see how to add it to your bot.   Add content Now that you selected relevant content, your bot needs to access your content. To do this, you need to add content to your bot which will constitute your knowledge base.   To add content to your bot: Navigate to the Knowledge base AI section inside of your bot.    2. Click the Add content button at the top right corner of the screen. A window pops up from where you can add your content.  There are 2 types of content you can add: Documents, uploaded from your computer. These can be: CSV files: are the only ones supported for non-generative knowledge bases, using a specific format.  PDF files: e.g. product descriptions, FAQ documents, training documentation, etc. URLs from publicly available websites. There are two options when you add URLs: Only this page: only use the exact page that the URL links to. Entire domain: use the page the URL links to and all linked pages. 3. Add your content. 4. Once it's done, the content will show up in the Contents table. This table shows the name of your content, its type, its status, when it was added and when it was last synced.  5. Repeat this until you've added all the content that you would like your bot to know. 6. If you click on the three dots at the end of the row, you can: Open your URL in a new tab (or preview your document if the content fits this type) . Sync our URL (i.e. update it with the latest changes). Delete your content. Now, your knowledge base displays your content and is ready to be used inside conversations. Let's see how to build a flow that displays the answer. Build a knowledge base flow Once your bot has access to all relevant content, it's time to build a flow where your bot will know when to browse this knowledge base to provide an answer to your customer's question.   If you want to create a new chatbot, please watch the video:     Making a knowledge base flow will happen in 2 steps: Retrieve the answer Display the answer   Retrieve the answer The flow step to retrieve a response based on the knowledge base will happen inside an Action bot block.   To retrieve an answer from the knowledge base: There are 2 ways that you might want to use your knowledge base. Either: In your Not Understood block, as a fallback option. To do this, go to your Not Understood block, change its block type to Action, and continue by following from step 2. Anywhere in your flow. To do so, drop an Action block in your canvas. For this example, we will name this block "Generate answer".   Click on Knowledge base AI.         Fill in the fields accordingly. You can configure: Variable: the answer from the knowledge base will be stored as a variable. In the first field, you can choose the name of that variable. No results: if the question that the user asks cannot be answered by the knowledge base AI, a block will be triggered. You can select which block in this dropdown. Failure: if there is a problem with the knowledge base AI, and it returns an error, you can select a block which the user will be led to. By default, users will be routed to the Error Occurred block.     4. Save your changes   You bot can now scrape the knowledge base and retrieve an answer based on it. But it cannot yet display that answer. Let's see how to change that.   Display the answer To display the answer from the knowledge base: Open the Action block that generates your knowledge base answer. At the bottom of the block, add a Go To that goes to a block that you can create from within the dropdown. In this example, we will call this block "KB result". Save your changes Open the newly created KB result block Add a text message that contains the variable you chose to save the knowledge base AI answer into. By default, this is {knowledgebase.answer}. Save your changes All done! Your knowledge base AI bot is now ready to be used 👏     How to link to the URL of your source in the bot answer When your bot retrieves an answer from your knowledge base, this answer exists within a variable that also contains a link to the source of this answer. This source is either a PDF name or link to an URL. In the case of an URL source, this URL link can typically be used as a button within the bot conversation.   Please remember that non-generative knowledge bases can only use .csv files.       Find your knowledge base session data To find your knowledge base session data:  Create your knowledge base using a URL as content.  Build your knowledge base AI flow as explained above. Test your bot by asking something for which the bot can retrieve a result.  In the Test your bot window, click on the Debugger button.  Scroll down the Debugger tab until you find the session data called knowledgebase.     The knowledgebase object contains a few fields: answer: the answer that can be used in a text message in your bot retrieved: an array of all the content that was used to formulate the answer. For each array item, the following data is stored: type: type of the source: "URL" or "DOC" name: filename of the document or link of the URL content: snippet of the content that was used to generate the answer.     Display the knowledge base content URL in a button You can use the URL of a knowledge base answer in a button, so that the user can learn more about a specific answer.    To use the knowledge base URL within an answer: Create your text message. Add a button that displays the following variable: knowledgebase.retrieved[0].name. In this variable, name means that we're capturing the URL, [0] means that we're doing this for the first item of the retrieved array. Your bot message should look similar to this one:       Your final result should be similar to this:         See also: Introduction to Knowledge base AI Non-generative knowledge base AI Use tags to limit your content ... View more

Engage Knowledge base AI, allows your bot to generate concise answers after scraping your content. Adding an FAQ flow to your bot was never easier!   How does it work? First, you add the content that your bot will scrape to retrieve the answer to the customer's question. Second, you design a flow to display that answer.   Generative vs non-generative Knowledge base AI We offer 2 ways of using the knowledge base:   Generative knowledge base: the bot will generate, or make up a new sentence to answer your customer's questions after scraping your content. There, you can use: PDF files, URLs of a page or a whole domain and CSV files. Non-generative knowledge base:  the bot will answer what you tell it to answer after you fed it with a list of questions and answers. There, you can use only CSV files in a specific format.   To choose if your knowledge base should be generative: Open your Knowledge Base AI tab for the first time. A popup with the Generative AI terms and conditions opens. If you click on Accept, your bot will be generative. If you click on Cancel, your bot will be non-generative.   Test it on a template You have your Knowledge base feature enabled and would like to test it right away? You can do it by playing with our template "Knowledge Base AI".   Build a powerful, hybrid bot Bots can become really powerful if you use a mix of intents (answers designed by your team) and knowledge base AI. In this sense, your bot will be hybrid because it uses answers generated both by humans and machine.   If you connect your Knowledge base AI Action block to your Not Understood block and add no other content to your bot, all questions from users will be answered directly by your knowledge base AI.   If you have other intents in your bot, the intents will be triggered whenever there is a match with the expression from a user. Only when something is said by the user that isn't a match with any intent, the Not Understood block and thus knowledge base AI will be triggered.   Limit your content using tags For some use cases, it might be important to only allow specific content to be used in an answer that's created by Knowledge base AI. Different categories of content can be created by using tags. You can read more about how to use tags in this article.     See also: Create your FAQ flow with AI Non-generative knowledge base AI Use tags to limit your content ... View more