I'm writing an agent using API.AI I'm observing that my back-end is not called everytime. I can see that in my access logs. Any idea what can cause the issue?
Here is the response of the console:
{
"id": "c1902c75-1550-43f6-9cc8-b0461f1dfac7",
"timestamp": "2016-12-22T19:58:13.49Z",
"result": {
"source": "agent",
"resolvedQuery": "echo test",
"action": "",
"actionIncomplete": false,
"parameters": {
"myInput": "test"
},
"contexts": [],
"metadata": {
"intentId": "062b4383-06a0-40fe-bbeb-9189db49aeb8",
"webhookUsed": false,
"webhookForSlotFillingUsed": "false",
"intentName": "Response"
},
"fulfillment": {
"speech": "",
"messages": [
{
"type": 0,
"speech": ""
}
]
},
"score": 0.75
},
"status": {
"code": 200,
"errorType": "success"
},
"sessionId": "70be8f65-81f0-40be-a271-84a2d4960224"
}
I see there no error which explains why my backend is not called.
Here is a screenshot of my intent:
You have not given any value in the action key of the intent.Give some action name and keep this same name of your function which will accept the parameters from the api.ai
basically the flow is
1)user enters an input.
2)api.ai tries to match the user's input with the intents defined by you, if not found it will got to the fallback intent.
3)once the proper intent is matched then api.ai tries to extract the parameters from the user's sentence.
4)once all the required parameters are found it will call the action which you have defined in the intent.
NOTE: if none of the parameters are required in the intent it directly calls the action .
Related
I'm using postman to make rest requests to the azure API to run a pipeline that is in synapse, in terms of permissions and the token I already get them and it works, the problem is that the pipeline receives 3 parameters but I don't know how to pass them, so I have this request, example:
https://hvdhgsad.dev.azuresynapse.net/pipelines/pipeName/createRun?api-version=2020-12-01
and the parameters I added them in the body:
{
"parameters": {
"p_dir": {
"type": "string",
"defaultValue": "val1"
},
"container": {
"type": "string",
"defaultValue": "val"
},
"p_folder": {
"type": "string",
"defaultValue": "val3"
}
}
}
but when I validate the run that was launched with the request I get this.
{
"id": "xxxxxxxxxxxxxxx",
"runId": "xxxxxxxxxxxxxxxxxxxxx",
"debugRunId": null,
"runGroupId": "xxxxxxxxxxxxxxxxxxxx",
"pipelineName": "xxxxxxxxxxxxxxxxx",
"parameters": {
"p_dir": "",
"p_folder": "",
"container": ""
},
"invokedBy": {
"id": "xxxxxxxxxxxxxxxxx",
"name": "Manual",
"invokedByType": "Manual"
},
"runStart": "2021-07-20T05:56:04.2468861Z",
"runEnd": "2021-07-20T05:59:10.1734654Z",
"durationInMs": 185926,
"status": "Failed",
"message": "Operation on target Data flow1 failed: {\"StatusCode\":\"DF-Executor-SourceInvalidPayload\",\"Message\":\"Job failed due to reason: Data preview, debug, and pipeline data flow execution failed because container does not exist\",\"Details\":\"\"}",
"lastUpdated": "2021-07-20T05:59:10.1734654Z",
"annotations": [],
"runDimension": {},
"isLatest": true
}
the params are empty, so I don't know what's wrong or missing.
what is the correct way to pass them???
ref: https://learn.microsoft.com/en-us/rest/api/synapse/data-plane/pipeline/create-pipeline-run#examples
Just created an account to answer this as i've had the same issue.
I resolved this by just having the name of the variable and its subsequent value in the body JSON.
e.g.
{"variable": "value", "variable": "value"}
Found this by following the documentation you had posted, under request body it passes the name of the variable and the value directly into the JSON body.
{
"OutputBlobNameList": [
"exampleoutput.csv"
]
}
This particular example is a list/array so it confused me by adding the brackets [] if you are passing string parameters this is unneeded.
I am trying to automate the creation of Azure Pipelines for a particular branch using their REST api.
However, I am struggling to use almost all their API's, as their documentation lacks examples.
Things like List and Get are simple enough.
However, when it comes to queuing a build:
https://learn.microsoft.com/en-us/rest/api/azure/devops/build/builds/queue?view=azure-devops-rest-6.0
POST https://dev.azure.com/{organization}/{project}/_apis/build/builds?api-version=6.0
{
"parameters": <parameters>, // how do i send paramters
"definition": {
"id": 1
},
"sourceBranch": "refs/heads/feature/my-pipeline",
"sourceVersion": "d265f01aeb4e677a25725f44f20ceb3ff1d7d767"
}
I am currently struggling to send parameters.
I have tried:
Simple JSON like:
"parameters": {
"appId": "bab",
"platform": "android",
"isDemo": true
}
and stringify version of JSON like:
"parameters": "{\"appId\": \"bab\",\"platform\": \"android\",\"isDemo\": true}"
but none seems to work.
It keeps giving me the error:
{
"$id": "1",
"customProperties": {
"ValidationResults": [
{
"result": "error",
"message": "A value for the 'appId' parameter must be provided."
},
{
"result": "error",
"message": "A value for the 'platform' parameter must be provided."
},
{
"result": "error",
"message": "A value for the 'isDemo' parameter must be provided."
}
]
},
"innerException": null,
"message": "Could not queue the build because there were validation errors or warnings.",
"typeName": "Microsoft.TeamFoundation.Build.WebApi.BuildRequestValidationFailedException, Microsoft.TeamFoundation.Build2.WebApi",
"typeKey": "BuildRequestValidationFailedException",
"errorCode": 0,
"eventId": 3000
}
The docs is very unclear in how to send this data: https://learn.microsoft.com/en-us/rest/api/azure/devops/build/builds/queue?view=azure-devops-rest-6.1#propertiescollection
Thank you very much for you help.
I believe you cannot pass runtime parameters trough the Queue API. Instead, use Runs API
With that, your request body (use Content-type: application/json) should look something similar to this:
{
"resources": {
"repositories": {
"self": {
"refName": "refs/heads/feature/my-pipeline"
}
}
},
"templateParameters": {
"appId": "bab"
"platform": "android"
"isDemo": true
}
}
I just realized that in the api-version=6.0 you can also send templateParameters on the Queue Service:
POST https://dev.azure.com/{organization}/{project}/_apis/build/builds?sourceBuildId={BUILD_BUILDID}&api-version=6.0
{
"templateParameters": { "doReleaseBuild": "True" },
"definition": {
"id": 1
},
"sourceBranch": "refs/heads/feature/my-pipeline",
"sourceVersion": "d265f01aeb4e677a25725f44f20ceb3ff1d7d767"
}
I'm using https://chatbase.com/api/messages Chatbase API to send multiple messages to the Chatbase. The documentation stats that the response would provide error and success for individual messages that are sent in the request.
How I should detect which message is failed out of the 3 messages that I have provided in the request if the response provides error for one message?
JSON Request body for sending multiple messages
{
"messages": [
{
"api_key": "<API KEY>",
"type": "agent",
"user_id": "User_1",
"time_stamp": 1542895834,
"platform": "XXX",
"message": "Test 1",
"not_handled": false,
"version": "1.0",
"session_id": "session-User_1"
},
{
"api_key": "<API KEY>",
"type": "agent",
"user_id": "User_1",
"time_stamp": 1542895834,
"platform": "XXX",
"message": "Test 2",
"not_handled": false,
"version": "1.0",
"session_id": "session-User_1"
},
{
"api_key": "<API KEY>",
"type": "agent",
"user_id": "User_1",
"time_stamp": 1542895834,
"platform": "XXX",
"message": "Test 3",
"not_handled": false,
"version": "1.0",
"session_id": "session-User_1"
}
]
}
JSON Response body
{
"all_succeeded": false,
"responses": [
{
"error": "Error fetching parameter 'type': Invalid conversation type [dfg]",
"status": "error"
},
{
"message_id": 139429278,
"status": "success"
},
{
"error": "Error fetching parameter 'time_stamp': Received a time (1921-02-09 09:49:26) which was too small. Please send a time within the past day for metrics to appear in the dashboards, or omit the time_stamp field for the time to automatically be set to now.",
"status": "error"
}
],
"status": 200
}
The order of the error messages will correspond to the order of the messages you submitted. In this case, it was the first and third messages. I also noticed that you are not using unix milliseconds in your timestamps. The messages will need to be at least one millisecond apart in order to sort them correctly in the Chatbase reports.
Is there a way to get all matching intents, not only one result with the biggest score, for example right now I get
"result": {
"source": "agent",
"resolvedQuery": "my test",
"action": "",
"actionIncomplete": false,
"parameters": {},
"contexts": [],
"metadata": {
"intentId": "",
"webhookUsed": "false",
"webhookForSlotFillingUsed": "false",
"intentName": "intentName"
},
"fulfillment": {
"speech": "test",
"messages": [
{
"type": 0,
"speech": "test"
}
]
},
"score": 0.9200000166893005
},
I want to return all intents when the score is not high to allow users to choose their intent.
It isn't possible to return all matching intents.
Given the use case described in the comments, you can just set your fallback intent to return a set of suggestions to the user. The fallback intent is triggered when none of the intents have a sufficiently high score to match.
I'm currently using Dialogflow in combination with fulfillment/webhooks.
In the documentation of the fulfillments there is an example POST request for webhooks:
POST body:
{
"contexts": [
string
],
"lang": string,
"query": string,
"sessionId": string,
"timezone": string
}
The request that I'm receiving on my end is different from what is defined in the documentation. Has somebody an idea why?
This is what I receive:
{
"id": "GUID",
"timestamp": "2018-01-12T12:25:32.202Z",
"lang": "de",
"result": {
"source": "agent",
"resolvedQuery": "Test",
"speech": "",
"action": "",
"actionIncomplete": false,
"parameters": {
"Nummer": ""
},
"contexts": [],
"metadata": {
"intentId": "XYZ",
"webhookUsed": "true",
"webhookForSlotFillingUsed": "false",
"intentName": "Intent"
},
"fulfillment": {
"speech": "",
"messages": [{
"type": 0,
"speech": ""
}]
},
"score": 0.6700000166893005
},
"status": {
"code": 200,
"errorType": "success",
"webhookTimedOut": false
},
"sessionId": "GUID"
}
I've found that different invocation sources send slightly different data to the web hook.
For example the Google Action simulator will send different information in the context reply than say the test pane in an intent.
Im guessing that the answer may lie in where/how your calling the web hook.