Search code examples
asp.net-web-apibotframeworkazure-language-understanding

Is there any possible way to apply luis after capturing user input from Adaptive text block?


Within a bot,we have an adaptive card where the user has a choice to select yes or no. On selecting YES, user is prompted to enter the keywords. After the user gives input in the textblock in adaptive card, the input has to be captured and sent as input parameter to web api. However, after the input is given, we will have to apply luis since there is a possibility of having synonyms for the input text. In the below code, keywords variable refers to the input text given by user and for which LUIS has to be applied.

    private async Task CustomisePPT(IDialogContext context, IAwaitable<object> result)
    {          
        try
        {                
            var replyMessage = context.MakeMessage();
            var newMessage = context.Activity.AsMessageActivity();
            var userMessage = newMessage.Value;
            var take=userMessage.ToString().Substring(userMessage.ToString().IndexOf("GetUserInputKeywords"));
            var split = take.ToString().Substring("GetUserInputKeywords".Length+2);
            string keywords = split.Trim();
            keywords = keywords.Substring(1, keywords.Length - 5);

            using (HttpClient client = new HttpClient())
            {
                // api takes the user message as a query paramater
                string RequestURI = "https://xyz" + ***keywords***;
                HttpResponseMessage responsemMsg = await client.GetAsync(RequestURI);
                // TODO: handle fail case

                if (responsemMsg.IsSuccessStatusCode)
                {
                    var apiResponse = await responsemMsg.Content.ReadAsStringAsync();
                }
            }
        }
        catch (Exception ex)
        {

        }
        //throw new NotImplementedException();
        await Task.CompletedTask;
    }

Solution

  • @Taher's answer will help you integrate LUIS. This one will help you use it with Adaptive Cards.

    Adaptive Cards send their Submit results a little different than regular user text. When a user types in the chat and sends a normal message, it ends up in Context.Activity.Text. When a user fills out an input on an Adaptive Card, it ends up in Context.Activity.Value, which is an object where the key names are the id in your card and the values are the field values in the adaptive card.

    For example, the json:

    {
        "type": "AdaptiveCard",
        "body": [
            {
                "type": "TextBlock",
                "text": "Test Adaptive Card"
            },
            {
                "type": "ColumnSet",
                "columns": [
                    {
                        "type": "Column",
                        "items": [
                            {
                                "type": "TextBlock",
                                "text": "Text:"
                            }
                        ],
                        "width": 20
                    },
                    {
                        "type": "Column",
                        "items": [
                            {
                                "type": "Input.Text",
                                "id": "userText",
                                "placeholder": "Enter Some Text"
                            }
                        ],
                        "width": 80
                    }
                ]
            }
        ],
        "actions": [
            {
                "type": "Action.Submit",
                "title": "Submit"
            }
        ],
        "$schema": "http://adaptivecards.io/schemas/adaptive-card.json",
        "version": "1.0"
    }
    

    .. creates a card that looks like:

    Test Adaptive Card

    If a user enters "Testing Testing 123" in the text box and hits Submit, Context.Activity will look something like:

    { type: 'message',
      value: { userText: 'Testing Testing 123' },
      from: { id: 'xxxxxxxx-05d4-478a-9daa-9b18c79bb66b', name: 'User' },
      locale: '',
      channelData: { postback: true },
      channelId: 'emulator',
      conversation: { id: 'xxxxxxxx-182b-11e9-be61-091ac0e3a4ac|livechat' },
      id: 'xxxxxxxx-182b-11e9-ad8e-63b45e3ebfa7',
      localTimestamp: 2019-01-14T18:39:21.000Z,
      recipient: { id: '1', name: 'Bot', role: 'bot' },
      timestamp: 2019-01-14T18:39:21.773Z,
      serviceUrl: 'http://localhost:58453' }
    

    The user submission can be seen in Context.Activity.Value.userText.

    Note that adaptive card submissions are sent as a postBack, which means that the submission data doesn't appear in the chat window as part of the conversation--it stays on the Adaptive Card.

    Using Adaptive Cards with Waterfall Dialogs

    Your question doesn't quite relate to this, but since you may end up attempting this, I thought it might be important to include in my answer.

    Natively, Adaptive Cards don't work like prompts. With a prompt, the prompt will display and wait for user input before continuing. But with Adaptive Cards (even if it contains an input box and a submit button), there is no code in an Adaptive Card that will cause a Waterfall Dialog to wait for user input before continuing the dialog.

    So, if you're using an Adaptive Card that takes user input, you generally want to handle whatever the user submits outside of the context of a Waterfall Dialog.

    That being said, if you want to use an Adaptive Card as part of a Waterfall Dialog, there is a workaround. Basically, you:

    1. Display the Adaptive Card
    2. Display a Text Prompt
    3. Convert the user's Adaptive Card input into the input of a Text Prompt

    In your Waterfall Dialog class (steps 1 and 2):

    private async Task<DialogTurnResult> DisplayCardAsync(WaterfallStepContext stepContext, CancellationToken cancellationToken)
    {
        // Create the Adaptive Card
        var cardPath = Path.Combine(".", "AdaptiveCard.json");
        var cardJson = File.ReadAllText(cardPath);
        var cardAttachment = new Attachment()
        {
            ContentType = "application/vnd.microsoft.card.adaptive",
            Content = JsonConvert.DeserializeObject(cardJson),
        };
    
        // Create the text prompt
        var opts = new PromptOptions
        {
            Prompt = new Activity
            {
                Attachments = new List<Attachment>() { cardAttachment },
                Type = ActivityTypes.Message,
                Text = "waiting for user input...", // You can comment this out if you don't want to display any text. Still works.
            }
        };
    
        // Display a Text Prompt and wait for input
        return await stepContext.PromptAsync(nameof(TextPrompt), opts);
    }
    
    private async Task<DialogTurnResult> HandleResponseAsync(WaterfallStepContext stepContext, CancellationToken cancellationToken)
    {
        // Do something with step.result
        // Adaptive Card submissions are objects, so you likely need to JObject.Parse(step.result)
        await stepContext.Context.SendActivityAsync($"INPUT: {stepContext.Result}");
        return await stepContext.NextAsync();
    }
    

    In your main bot class (<your-bot>.cs) (step 3):

    var activity = turnContext.Activity;
    
    if (string.IsNullOrWhiteSpace(activity.Text) && activity.Value != null)
    {
        activity.Text = JsonConvert.SerializeObject(activity.Value);
    }
    

    Using this to answer your question

    You can handle integrating this with LUIS in either the HandleResponseAsync() (if you don't really care that the exact user input ends up in Step.Result, or you can handle it in the if (channelData.ContainsKey("postback")) block (if you want to change the user input before sending it to the next step in your dialog.