aws-lex

问题 I have set up a Lex bot which provides the order status to the user. User invoked the intent with a specific utterance. Then lex bot asked the information as requested in the slot specified. Then confirmation prompt is invoked "Are you sure you want information" and the user said "yes". before replying the user with the information, when the user says yes I want that lex bot should say "Please wait, while we are fetching your information". I have tried with different intents invoke. but

问题 I have set up a Lex bot which provides the order status to the user. User invoked the intent with a specific utterance. Then lex bot asked the information as requested in the slot specified. Then confirmation prompt is invoked "Are you sure you want information" and the user said "yes". before replying the user with the information, when the user says yes I want that lex bot should say "Please wait, while we are fetching your information". I have tried with different intents invoke. but

问题 I've been reading the AWS Lex / Lambda docs and looking at the examples. I don't see a way to return multiple lines. I want to create an intent that when a user types 'Help' It gives me an output like below. Options: Deploy new instance. Undeploy instance. List instances. I've tried this: def lambda_handler(event, context): logger.debug('event.bot.name={}'.format(event['bot']['name'])) a = { "dialogAction": { "type": "Close", "fulfillmentState": "Fulfilled", "message": { "contentType":

问题 We are using Amazon connect which uses the "Get customer input" interact block to use the Amazon Lex which internally connects to Lambda so the flow will be like Amazon Connect -> (using Get Customer Input, It connects to Amazon Lex) Amazon Lex -> (In Amazon Lex, the intent is pointed to Amazon Lambda) Amazon Lambda Amazon connect -> Amazon Lex -> AWS Lambda The flow works for all the intents as expected. but for a particular flow, We need to upload the file from lambda to S3 and return the

问题 For my current project, I am looking for a bot building platform with the following features. Should support the creation/updating of new/existing bot via API. Support for intent detection from streaming audio. Enable the hosting of multiple bot agents in a single project. APIs to modify an existing bot/agent and save it as a new one. So I have thoroughly researched and also developed a simple working prototype using DialogFlow. DialogFlow supports intent detection from streaming audio. But

问题 I have to create an intent with sample utterances "open file 'fileName'" "show 'fileName'" ... Basically, I have to have a slot which accepts file name. User can type "open my file report.pdf " "open file activity1.doc " "open file last year report " It would work perfectly If I could use AMAZON.LITERAL type, but it is deprecated. What slot type I can use? Or how to extract file name (or basically any text with no type) So far I have tested with below slot types and all not perfect: Created