Questions tagged with AWS Chatbot

Good afternoon dear experts. Help solve the issue. I run the sh file (with rights) through the terminal, I get No such file or directory /.bashrc Google didn't help. I'm beating this wall for the 3rd evening). sh file content: source ~/.bashrc cd ~/data python file.py Contents of the .bashrc file: "# .bashrc" export PATH="~/.pyenv/bin:$PATH" eval "$(pyenv init -)" eval "$(pyenv virtualenv-init -)" # Source global definitions if [ -f /etc/bashrc ]; then . /etc/bashrc fi "# Uncomment the following line if you don't like systemctl's auto-paging feature:" "# export SYSTEMD_PAGER=" "# User specific aliases and functi" "# >>> conda initialize >>>" "# !! Contents within this block are managed by 'conda init' !!" __conda_setup="$('/home/ec2-user/.pyenv/versions/anaconda3-2020.11/bin/conda' 'shell.bash' 'hook' 2> /dev/null)" if [ $? -eq 0 ]; then eval "$__conda_setup" else if [ -f "/home/ec2-user/.pyenv/versions/anaconda3-2020.11/etc/profile.d/conda.sh" ]; then . "/home/ec2-user/.pyenv/versions/anaconda3-2020.11/etc/profile.d/conda.sh" else export PATH="/home/ec2-user/.pyenv/versions/anaconda3-2020.11/bin:$PATH" fi fi unset __conda_setup "# <<< conda initialize <<<"

I am trying to create a custom slot that can recognise time format `10:00:00` for example, so i created a custom slot "extended slot type" and tried using regex like this `[0-9]{1,2}:[0-9]{1,2}:[0-9]{1,2}` it failed with "Check the regular expression and try your request again" error so i tried using the unicode character for "colon" like `[0-9]{1,2}\u003A[0-9]{1,2}\u003A[0-9]{1,2}` even this fails with the same error i tried using other unicode and special characters like `-` which works absolutely fine. so, How can i use a colon special character in regex validation ?

Can we play a notification sound for every new message both at client and agent side in AWS Chatbot. Do we have some inbuilt capability in Amazon CCP

I was making a chatbot for a Japanese company and was using the QnAbot to create it. I imported all the questions and answers on the QnAbot Designer. After trying to test the chatbot using QnAbot Client, I found that even though the question exists on the Designer, it does not seem to give me a response. Some words seem to work, while the majority do not, without any sort of pattern. I am not certain what is causing the issue. For example, These works: アクセス権限マトリクス一覧表 申請方法（スマホ内線） These do not work: 早期退職 通達（スマホ内線） They are similar yet one works, while the other does not. In total, there are around 500 questions and answers. Is it the Japanese characters? I am not certain.

I have created a Hotel Management lex bot that makes a reservation for hotel rooms. I am using slots (Check-in Date and Check-out Date). I am using a built-in slot that is Amazon.Date. **Problem** I want to restrict customers at this stage so that customers can only enter date that matches with the current date or after the current date. Currently, these slots are accepting all dates including previous dates. How I can validate these slots? (Can we solve our problem with RegEx while using Amazon.Alphanumeric type) What are the possible solutions? Should we handle this in Lambda? (If yes, kindly describe how I can get the Elicitation value of a slot in Lambda (Python)). What would you prefer me to resolve or achieve this? Any help would be greatly appreciated and thanks in advance.

Hi Everyone, I’m trying to design a simple voice chatbot which is expected to help me achieve these function: 1. The bot needs to be accessible online (via a web link) 2. upon clicking on the link, the **bot** should **initiate** the conversation by asking “how are you doing” 3. the bot records the user answer 4. the bot ends the conversation by saying “Great thank you!” 5. the bot converses with the user by speaking only 6. the user converses with the bot by speaking only Does anyone here help me out? Many thanks, JD

Hi Team, How to send delay response from lambda function to aws lex bot? using c# Ex: Session timeout notification will be send to user. Please help on this.

**TL;DR:** The "OrderFlowers" blueprint for Lex + Lambda on .NET Core 3.1 doesn't seem to work. Instead of populating the values for `CurrentIntent` and `SlotDetails` as expected, these values are `null` instead. Note: Python and Node.js lambda equivalents seem to work just fine, but work use case requires .NET. --- ## Context - Goal: Setup blueprint "OrderFlowers" chatbot with AWS Lex v2 using .NET Core 3.1 and AWS Lambda. [(Link)](https://docs.aws.amazon.com/lex/latest/dg/gs-bp.html) - This may be an issue with Lex v2 rather than with Lambda, but this may be unlikely as Python and Node.js work fine when interchanged with the .NET lambda used. ## Description - When invoking the OrderFlowers blueprint lambda function via AWS Lex, the `LexEvent` does not populate the expected fields, such as `CurrentIntent` and `SlotDetails`. - Compare this to using the Python or Node.js blueprints which do populate the expected fields. ## Reproduction Steps 1. Create a new .NET project using the "AWS Lambda Project (.NET Core - C#)" template with the "Order Flowers Chatbot" Blueprint. 2. Log the `lexEvent` variable to CloudWatch within the **FunctionHandler** function: `LambdaLogger.Log(JsonSerializer.Serialize(lexEvent));` 3. Publish the solution to AWS Lambda (default settings, arbitrary function name). 4. Create a new Lex v2 Chatbot with the "Order Flowers Chatbot" Example. 5. Configure the new chatbot to use the new lambda function you uploaded under Bot > Alias > Language. 6. Under Intents > OrderFlowers > Fulfillment > Advanced Options, ensure "Use a Lambda function for fulfillment" is checked. 7. Save the intent, build the bot, and test the conversation. 8. An error should appear when attempting to fulfill the intent - when you check CloudWatch, the **LexEvent** body should appear with `null` values for fields such as `CurrentIntent` and `SlotDetails`. ### Logs **Lex** `Invalid Lambda Response: Received error response from Lambda: Unhandled` **CloudWatch** ``` { "CurrentIntent": null, "SlotDetails": null, "Bot": { "Name": "OrderFlowersBot", "Alias": null, "Version": "DRAFT" }, "UserId": null, "InputTranscript": "yes", "InvocationSource": "FulfillmentCodeHook", "OutputDialogMode": null, "MessageVersion": "1.0", "SessionAttributes": null, "RequestAttributes": null, "AlternativeIntents": null, "SentimentResponse": null, "RecentIntentSummaryView": null, "ActiveContexts": null } ``` ### Environment * Build Version: Amazon.Lambda.Core 2.1.0, Amazon.Lambda.LexEvents 3.0.0, Amazon.Lambda.Serialization.SystemText 2.2.0 * OS Info: Windows 10 Enterprise * Build Environment: Visual Studio 2019 * Targeted .NET Platform: .NET Core 3.1 ## Resolution - There may be an issue serializing the incoming request from Lex v2 based on the configuration laid out in the current Order Flowers .NET 3.1 blueprint. To resolve this, effort will need to be made comparing the expected Lex v2 request payload with the actual payload and the serialization may have to be adjusted accordingly.

Hai There, i have a requirement to schedule a lex intent with pinpoint push notification. consider this example everyday morning at 9 AM i would like to send a push notification to some users for a survey which will have some questions to answer which is a lex and lambda integration. currently i am able to work with lex by calling the utterance, but what i want to achieve is connect to lex without user calling the utterance. we can think of it like a bot first kinda conversation. Thanks for the help in advance, charith v.

I am building an iOS app that uses Lex. I can successfully contact Lex V1 bots using the code provided in the https://github.com/awslabs/aws-sdk-ios-samples/tree/main/Lex-Sample/Swift , but I am unable to reach Lex V2 bots. It seems like the Swift SDK can only connect to Lex V1 bots. How do I tell the iOS Swift SDK to connect to a Lex V2 bot?

I am very new to lex. I have a questionnaire workflow setup with lex and lambda, i have slot name answers which set as empty array '[]' on the first time lambda is fired to record the values (my questions state in it). But i see something weird happening with sometimes for the few words for example i have 4 words (like a multiple choice) some words are "recognized" fine but for other they change/override my slots["answers"] value. `{'messageVersion': '1.0', 'invocationSource': 'DialogCodeHook', 'userId': 'XXXXX', 'sessionAttributes': {'assessmentState': '1', 'sessionId': 'XXXXX'}, 'requestAttributes': None, 'bot': {'name': 'XXXXX', 'alias': 'XXXXX', 'version': 'XXXXX'}, 'outputDialogMode': 'Text', 'currentIntent': {'name': 'XXXXX', 'slots': {'answers': '[]'}, 'slotDetails': {'answers': {'resolutions': [{'value': '[]'}], 'originalValue': '[]'}}, 'confirmationStatus': 'None', 'nluIntentConfidenceScore': 0.95}, 'alternativeIntents': [{'name': 'XXXXX1', 'slots': {}, 'slotDetails': {}, 'confirmationStatus': 'None', 'nluIntentConfidenceScore': None}], 'inputTranscript': 'Not at all', 'recentIntentSummaryView': [{'intentName': 'XXXXX', 'checkpointLabel': None, 'slots': {'answers': '[]'}, 'confirmationStatus': 'None', 'dialogActionType': 'ElicitSlot', 'fulfillmentState': None, 'slotToElicit': 'answers'}], 'sentimentResponse': None, 'kendraResponse': None, 'activeContexts': []}` this is my first request (answer to my first question) if you see `currentIntent['slots']['answers']` is an `'[]'` which i set when lambda is invoked first time even before this to render user my first question and for this question i answered 'Not at all' if you see the inputTranscript. which looks all fine but for the next question when i tried to answer with another utterance the event has changed a lot. `{'messageVersion': '1.0', 'invocationSource': 'DialogCodeHook', 'userId': 'XXXXX', 'sessionAttributes': {'assessmentState': '2', 'sessionId': 'XXXXX'}, 'requestAttributes': None, 'bot': {'name': 'XXXXX', 'alias': 'XXXXX', 'version': '23'}, 'outputDialogMode': 'Text', 'currentIntent': {'name': 'XXXXX', 'slots': {'answers': 'Several days'}, 'slotDetails': {'answers': {'resolutions': [], 'originalValue': 'Several days'}}, 'confirmationStatus': 'None', 'nluIntentConfidenceScore': 1.0}, 'alternativeIntents': [{'name': 'XXXXX1', 'slots': {}, 'slotDetails': {}, 'confirmationStatus': 'None', 'nluIntentConfidenceScore': None}, {'name': 'XXXXX2', 'slots': {'foodName': None, 'delayWhen': None, 'confirmation': None, 'barcode': None, 'food': None}, 'slotDetails': {'foodName': None, 'delayWhen': None, 'confirmation': None, 'barcode': None, 'food': None}, 'confirmationStatus': 'None', 'nluIntentConfidenceScore': 0.62}, {'name': 'XXXXX3', 'slots': {'answers': 'Several days'}, 'slotDetails': {'answers': {'resolutions': [], 'originalValue': 'Several days'}}, 'confirmationStatus': 'None', 'nluIntentConfidenceScore': 0.51}, {'name': 'XXXXX5', 'slots': {}, 'slotDetails': {}, 'confirmationStatus': 'None', 'nluIntentConfidenceScore': 0.48}], 'inputTranscript': 'Several days', 'recentIntentSummaryView': [{'intentName': 'XXXXX', 'checkpointLabel': None, 'slots': {'answers': '[{"id": 1, "value": 0}]'}, 'confirmationStatus': 'None', 'dialogActionType': 'ElicitSlot', 'fulfillmentState': None, 'slotToElicit': 'answers'}], 'sentimentResponse': None, 'kendraResponse': None, 'activeContexts': []}` but here if you see `currentIntent['slots']['answers']` it is supposed to have `'[{"id": 1, "value": 0}]'` which i set after my 1st question is answered but here it is 'Several days' and if you see `recentIntentSummaryView` array's element `{'intentName': 'XXXXX', 'checkpointLabel': None, 'slots': {'answers': '[{"id": 1, "value": 0}]'},....` this has the value i set in my previous question. as far as my observation go i think it fails for some words and after a build and publish it starts to work which i dont know sometimes looks like magic and sometimes confuses what did i miss. the slot configuration i used is name: answers, type: AMAZON.streetAddress, prompt: what assessment? I used type as AMAZON.streetAddress because i had same issue on other intent and i found somewhere that AMAZON.alphaNumeric has some issue ... and change to AMAZON.streetAddress and that intent works fine, this intent also has similar config and lambda code as other but i am lost in what to do or whats happening. Please help me out, Thanks in advance.

Hi I am working on an app, and in my use case I'd like to call createBotVersion api of aws-sdk javascript library whenever the bot status changes to READY. Writing a cron job is one solution which will publish all the bots with status READY, but it's a load on server as this call might not be needed on regular basis. Is there any way through which I can listen to the event of bot becoming READY, or maybe I can create a SNS topic or something? Please help Edited by: nikhilhatcher on Apr 17, 2020 2:48 PM

According to <https://docs.aws.amazon.com/lex/latest/dg/howitworks-manage-prompts.html#msg-prompts-resp-card> I cannot receive ResponseCards while using PostContent. I realize when people are using speech to interact with a bot, ResponseCards might not be useful, however for those who would like to display a response card, or even use the data in response cards to enhance their app there exists no way to use the nice Lex PostContent interface. Instead we would need to implement the speech recognition and synthesis ourselves and this feels like a waste when Lex has access already. This is a question/feature request Question: Are there any ways to work around PostContent, other than reimplementing the speech features provided by Lex? Feature Request: Add an option to enable ResponseCards for the PostContent Api.