我一直在关注youtube教程:https://www.youtube.com/watch?v=HkMi5xPyz1g&t=1533s
public Object handleRequest(Map<String,Object> input, Context context) {
LexRequest lexRequest= LexRequestFactory.createLexRequest(input);
String orgbotcommand= lexRequest.getCommand()+" "+lexRequest.getOld_variable();
String content = String.format("command recieved by %s is %s",
lexRequest.getBotName(),
orgbotcommand);
Message message = new Message("Plain text",content);
DialogueAction dialogueAction = new DialogueAction("Close", "Fulfilled or Failed", message );
System.out.println(dialogueAction);
return new LexRespond(dialogueAction);
}
以上是我正在使用的java代码。
在使用lambda函数测试事件进行测试时,它给了我想要的输出,但是当我尝试从我的lex bot调用这个lambda函数时,它会抛出以下错误:
An error has occurred: Invalid Lambda Response: Received invalid response
from Lambda: Can not construct instance of IntentResponse, problem: The
validated object is null at [Source: {"dialogueAction":
{"type":"Close","fulfillmentState":"Fulfilled or Failed","message":
{"contentType":"Plain text","content":"command recieved by OrgBot is Delete asd"}}}; line: 1, column: 168]
lambda测试事件中的输出是:
{
"dialogueAction": {
"type": "Close",
"fulfillmentState": "Fulfilled or Failed",
"message": {
"contentType": "Plain text",
"content": "command recieved by OrgBotchatbot is delete asd"
}
}
}
我是Amazan lex和lambda的新手。请告诉我我做错了什么
答案 0 :(得分:1)
可能只是你的回复格式。查看Response Format Docs。
首先,contentType
需要 &#39; PlainText&#39;或者&#39; SSML&#39;。
因此,将'Plain text'
更改为'PlainText'
Message message = new Message("PlainText",content);
其次,fulfillmentState
需要 &#39; Fulfulled&#39;或者&#39;失败&#39;。
因此,请从'or Failed'
行删除DialogueAction
:
DialogueAction dialogueAction = new DialogueAction("Close", "Fulfilled", message );
第三,dialogAction
。 Lex必须是美国人,因为它只接受你拼写“对话”时的回应。作为对话&#39;。因此,在代码中更改所需内容,以便响应返回:
{
"dialogAction": {
"type": "Close",
"fulfillmentState": "Fulfilled",
"message": {
"contentType": "PlainText",
"content": "command recieved by OrgBotchatbot is delete asd"
}
}
};
答案 1 :(得分:0)
输出格式必须遵循特定的最小布局。 我使用以下两个功能使其变得简单。
当您准备告诉Lex时,只需从任何函数调用它们
//SessionAttributes any session variables
//fulfillmentState - 'Fulfilled' or 'Failed' depending on if successful or not
//message - the actual response text you want lex to say/type
function close(sessionAttributes, fulfillmentState, message) {
return {
sessionAttributes,
dialogAction: {
type: 'Close',
fulfillmentState,
message,
},
};
}
function delegate(sessionAttributes, slots) {
return {
sessionAttributes,
dialogAction: {
type: 'Delegate',
slots,
},
};
}
答案 2 :(得分:0)
如果您使用的是 Lex v2,则预期的响应格式与 v1 不同。
见https://docs.aws.amazon.com/lexv2/latest/dg/lambda.html#lambda-response-format
{
"sessionState": {
"activeContexts": [
{
"name": "string",
"contextAttributes": {
"key": "value"
},
"timeToLive": {
"timeToLiveInSeconds": number,
"turnsToLive": number
}
}
],
"sessionAttributes": {
"string": "string"
},
"dialogAction": {
"slotToElicit": "string",
"type": "Close | ConfirmIntent | Delegate | ElicitIntent | ElicitSlot"
},
"intent": {
"confirmationState": "Confirmed | Denied | None",
"name": "string",
"slots": {
"string": {
"value": {
"interpretedValue": "string",
"originalValue": "string",
"resolvedValues": [
"string"
]
}
},
"string": {
"shape": "List",
"value": {
"originalValue": "string",
"interpretedValue": "string",
"resolvedValues": [
"string"
]
},
"values": [
{
"shape": "Scalar",
"value": {
"originalValue": "string",
"interpretedValue": "string",
"resolvedValues": [
"string"
]
}
},
{
"shape": "Scalar",
"value": {
"originalValue": "string",
"interpretedValue": "string",
"resolvedValues": [
"string"
]
}
}
]
}
}
},
"state": "Failed | Fulfilled | InProgress | ReadyForFulfillment"
},
"messages": [
{
"contentType": "CustomPayload | ImageResponseCard | PlainText | SSML",
"content": "string",
"imageResponseCard": {
"title": "string",
"subtitle": "string",
"imageUrl": "string",
"buttons": [
{
"text": "string",
"value": "string"
}
]
}
}
],
"requestAttributes": {
"string": "string"
}
}