我在PowerApps中有一个自定义连接器，它使用语言翻译器API，
下面是我在连接器中发送的请求。
{
"pipelineTasks": [
{
"taskType": "asr",
"config": {
"language": {
"sourceLanguage": "hi"
},
"serviceId": "",
"audioFormat": "flac",
"samplingRate": 8000
}
},
{
"taskType": "translation",
"config": {
"language": {
"sourceLanguage": "hi",
"targetLanguage": "en"
},
"serviceId": ""
}
},
{
"taskType": "tts",
"config": {
"language": {
"sourceLanguage": "en"
},
"serviceId": "",
"gender": "female",
"samplingRate": 8000
}
}
],
"inputData": {
"audio": [
{
"audioContent": //base64 string }
]
}}
这是我在连接器中收到的输出，正如预期的那样。请注意，响应中的输出对象是一个数组。
{
"pipelineResponse": [
{
"taskType": "asr",
"config": {
"serviceId": "",
"language": {
"sourceLanguage": "hi",
"sourceScriptCode": ""
},
"audioFormat": "flac",
"encoding": null,
"samplingRate": 8000,
"postProcessors": null
},
"output": [
{
"source": "मेरा नाम महीर है और मैं भाषा वर्ष यूज़ कर रहा हूँ"
}
],
"audio": null
},
{
"taskType": "translation",
"config": null,
"output": [
{
"source": "मेरा नाम महीर है और मैं भाषा वर्ष यूज़ कर रहा हूँ",
"target": "My name is Maher and I'm using the language Year"
}
],
"audio": null
},
{
"taskType": "tts",
"config": {
"language": {
"sourceLanguage": "en",
"sourceScriptCode": ""
},
"audioFormat": "wav",
"encoding": "base64",
"samplingRate": 8000,
"postProcessors": null
},
"output": null,
"audio": [
{
"audioContent": //base64 ,
"audioUri": null
}
]
}
]
}但是，当我尝试在PowerApps中调用自定义连接器时，我最终会出现错误。
“JSON分析错误，需要'string'，但得到'array'。”请参考下面的图像..
有人能帮帮忙吗？我不知道哪里出了问题。
我还添加了swagger的定义。
swagger: '2.0'
info:
title: ASR_NMT_TTS
description: ''
version: '1.0'
host: xxx.co.in
basePath: /
schemes:
- https
consumes: []
produces: []
paths:
/services/inference/pipeline:
post:
responses:
default:
description: default
schema:
type: object
properties:
pipelineResponse:
type: array
items:
type: object
properties:
taskType:
type: string
description: taskType
config:
type: object
properties:
language:
type: object
properties:
sourceLanguage:
type: string
description: sourceLanguage
sourceScriptCode:
type: string
description: sourceScriptCode
description: language
audioFormat:
type: string
description: audioFormat
encoding:
type: string
description: encoding
samplingRate:
type: integer
format: int32
description: samplingRate
postProcessors:
type: string
description: postProcessors
description: config
output:
type: string
description: output
audio:
type: array
items:
type: object
properties:
audioContent:
type: string
description: audioContent
audioUri:
type: string
description: audioUri
description: audio
description: pipelineResponse
summary: ASR_NMT_TTS
description: ASR_NMT_TTS
operationId: Pipeline
parameters:
- name: Content-Type
in: header
required: false
type: string
- name: body
in: body
required: false
schema:
type: object
properties:
pipelineTasks:
type: array
items:
type: object
properties:
taskType:
type: string
description: taskType
config:
type: object
properties:
language:
type: object
properties:
sourceLanguage:
type: string
description: sourceLanguage
targetLanguage:
type: string
description: targetLanguage
description: language
serviceId:
type: string
description: serviceId
audioFormat:
type: string
description: audioFormat
samplingRate:
type: integer
format: int32
description: samplingRate
gender:
type: string
description: gender
description: config
description: pipelineTasks
inputData:
type: object
properties:
audio:
type: array
items:
type: object
properties:
audioContent:
type: string
description: audioContent
description: audio
description: inputData
definitions: {}
parameters: {}
responses: {}
securityDefinitions:
API Key:
type: apiKey
in: header
name: Authorization
security:
- API Key: []
tags: []
1条答案
按热度按时间inkz8wg91#
您的连接器swagger指定'pipelineResponse'数组的'output'字段的类型为'string'：
但是在你的响应中，你实际上有一个'array'，它有两个属性：
您应该更新swagger以正确地输入输出字段，或者更新连接器的响应以匹配swagger指定的预期。