I'm trying to send some parameters to dialogflow (api.ai) such as username, email, etc but I couldn't figure it out. The problem is I cannot get/set any specific data (such as username, email, etc.) with Dialogflow v2 Nodejs SDK. I tried to use queryParams.payload (v1: originalRequest) but It didn't work somehow. Also, I tried to trigger custom event with data but I couldn't get any event data on the response. Does someone know how to send some specific data for session talk on dialogFlow?
EXAMPLE OF PAYLOAD
const projectId = 'test-bot-test-1111';
const sessionId = user.uuid;
const languageCode = 'en-GB';
const sessionClient = new dialogFlow.SessionsClient();
const sessionPath = sessionClient.sessionPath(projectId, sessionId);
const request = {
session: sessionPath,
queryInput: {
text: {
text: query,
languageCode
}
},
queryParams: {
payload: {
data: {
username: 'bob',
email: '[email protected]'
}
}
}
};
let resultReq;
console.log('request :: ', request, '\n\n');
try {
resultReq = await sessionClient.detectIntent(request);
} catch (err) {
// eslint-disable-next-line no-console
return console.error('ERROR:', err);
}
EXAMPLE OF EVENT
const projectId = 'test-bot-test-1111';
const sessionId = user.uuid;
const languageCode = 'en-GB';
const sessionClient = new dialogFlow.SessionsClient();
const sessionPath = sessionClient.sessionPath(projectId, sessionId);
const request = {
session: sessionPath,
queryInput: {
event: {
name: 'custom_event',
languageCode,
parameters: {
name: 'sam',
user_name: 'sam',
a: 'saaaa'
}
}
},
queryParams: {
payload: {
data: user
}
}
};
let resultReq;
console.log('request :: ', request, '\n\n');
try {
resultReq = await sessionClient.detectIntent(request);
} catch (err) {
// eslint-disable-next-line no-console
return console.error('ERROR:', err);
}
Webhooks are services that host your business logic. During a session, webhooks allow you to use the data extracted by Dialogflow's natural language processing to generate dynamic responses, validate collected data, or trigger actions on the backend.
Dialogflow sends an API interaction response for each step of slot filling. For each of these slot filling responses, the intent and action will be the same, and the parameters collected so far will be provided. When building an agent, you provide prompts that the agent will use to get parameter data from the end-user.
June 13, 2022. The Dialogflow ES Google Assistant integration will be removed on June 13, 2023. This is due to the Google Assistant Conversational Actions planned sunsetting.
Dialogflow's v2 API uses gRPC and has a few quirks, one of which you've run into. If you look at the samples for the Node.js library you can see how to workaround this. You'll need to impliment a jsonToStructProto
method to convert your JavaScript object to a proto struct or just copy the structjson.js
file in the sample in this gist. Below is a fully working example using the structjson.js
file:
// Imports the Dialogflow library
const dialogflow = require('dialogflow');
// Import the JSON to gRPC struct converter
const structjson = require('./structjson.js');
// Instantiates a sessison client
const sessionClient = new dialogflow.SessionsClient();
// The path to identify the agent that owns the created intent.
const sessionPath = sessionClient.sessionPath(projectId, sessionId);
// The text query request.
const request = {
session: sessionPath,
queryInput: {
event: {
name: eventName,
parameters: structjson.jsonToStructProto({foo: 'bar'}),
languageCode: languageCode,
},
},
};
sessionClient
.detectIntent(request)
.then(responses => {
console.log('Detected intent');
logQueryResult(sessionClient, responses[0].queryResult);
})
.catch(err => {
console.error('ERROR:', err);
});
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With