Code Monkey home page Code Monkey logo

amazon-ai-building-better-bots's Issues

Send multiple response cards

Hi,

Is there any way that we can send multiple response cards in bot response using fulfillment by lambda ?

Regards,
Kanwal

Bot consistently showing that the Intent if fulfilled

I followed the tutorial and made a bot using Amazon Lex. I created an alias and attached the lambda function to it and enabled the code hook option so that it uses that lambda function in the alias. When I test the bot though, it just says that the intent coffeOrderBeverageIntent is fulfilled.

Getting the error An error has occurred: Invalid Lambda Response: Received error response from Lambda: Handled

Hi,

Has anything changed with the response format that is expected by Lex,

I am getting the error message,

An error has occurred: Invalid Lambda Response: Received error response from Lambda: Handled

when i try from Lex. However, the cafeOrderCoffee_test.json is giving the response as

{
"sessionAttributes": {},
"dialogAction": {
"type": "ElicitSlot",
"intentName": "cafeOrderBeverageIntent",
"slots": {
"BeverageType": "mocha",
"BeverageStrength": null,
"Creamer": null,
"BeverageSize": null,
"BeverageTemp": null,
"BeverageExtras": null
},
"slotToElicit": "BeverageSize"
}
}

Thanks,

README is out of date for Lex V2 console

Hello!

While this is a very helpful resource, the documentation is only accurate for users using the Lex V1 console. For new users hoping to follow with Lex V2, some instructions are slightly inaccurate or incorrect altogether (Error Handling specifically). I would like to propose a rewriting of the README to better support users hoping to implement the CoffeeBot with Lex V2.

Some areas I noticed that would need a change are:

  • Step 1: Create the bot:
    • "Output Voice" and "Sentiment Analysis" are no longer necessary parts of the table
    • "IAM Role" value listed in table is no longer correct
  • Step 3: Create slot types:
    • Slot types are now created under the "Language" submenu, and are not accessible from the sidebar while creating an intent.
  • Step 6: Define fulfillment:
    • Return parameters to client is no longer an option under the "Fulfillment" menu
  • Step 7: Define responses:
    • "Responses" are now shown as "Closing response" in Lex V2
    • You can no longer declare a second message after selecting "Wait for user reply" in the "Closing response" menu
  • Step 8: Review the error handling settings:
    • This section is fully outdated as there is no longer an "Error handling" page in the menu for Lex V2
      • From my understanding, the error handling is now managed through the "FallbackIntent." Documentation for this was seemingly sparse in AWS docs, so I think this CoffeeBot would be a great way to show new users how to configure the FallbackIntent. This is the section of the project that I personally had the hardest time following when trying to implement within Lex V2.

Hopefully restructuring this CoffeeBot tutorial to utilize Lex V2 will be taken into consideration, this would be nice to have for new Lex users like myself.

Thanks!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.