with Google Dialogflow and Azure OpenAI?
Create completions for chat messages with the GPT-35-Turbo and GPT-4 models. See the documentation
Batch create entities, See REST docs and client API docs
Classify items into specific categories. See the documentation
Creates an Entity Type, See REST docs and client API docs
Google Dialogflow API empowers you to create conversational interfaces for websites, apps, and messaging platforms. Think chatbots that can engage in human-like dialogue, provide customer support, guide through sales processes, or control smart home devices with voice commands. With Pipedream's integration capabilities, you can create automated workflows that trigger actions in other apps based on Dialogflow's processed input, enabling seamless interaction across a plethora of services.
module.exports = defineComponent({
props: {
google_dialogflow: {
type: "app",
app: "google_dialogflow",
}
},
async run({steps, $}) {
// Example code from the Dialogflow Node.js library:
// https://github.com/googleapis/nodejs-dialogflow
const dialogflow = require('dialogflow')
const uuid = require('uuid')
// A unique identifier for the given session
const sessionId = uuid.v4()
const key = JSON.parse(this.google_dialogflow.$auth.key_json)
// Creates a session client from a Google service account key.
const sessionClient = new dialogflow.SessionsClient({
projectId: key.project_id,
credentials: {
client_email: key.client_email,
private_key: key.private_key,
}
})
const sessionPath = sessionClient.sessionPath(key.project_id, sessionId)
// The text query request.
const request = {
session: sessionPath,
queryInput: {
text: {
// The query to send to the dialogflow agent
text: 'hello',
// The language used by the client (en-US)
languageCode: 'en-US',
},
},
}
// Send request and log result
const responses = await sessionClient.detectIntent(request)
console.log('Detected intent')
const result = responses[0].queryResult
console.log(`Query: ${result.queryText}`)
console.log(`Response: ${result.fulfillmentText}`)
if (result.intent) {
console.log(`Intent: ${result.intent.displayName}`)
} else {
console.log(`No intent matched.`)
}
},
})
The Azure OpenAI Service API provides access to powerful AI models that can understand and generate human-like text. With Pipedream, you can harness this capability to create a variety of serverless workflows, automating tasks like content creation, code generation, and language translation. By integrating the API with other apps on Pipedream, you can streamline processes, analyze sentiment, and even automate customer support.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
azure_openai_service: {
type: "app",
app: "azure_openai_service",
}
},
async run({steps, $}) {
const data = {
"messages": [{ role: 'user', content: "Hello, world!" }],
}
return await axios($, {
method: "post",
url: `https://${this.azure_openai_service.$auth.resource_name}.openai.azure.com/openai/deployments/${this.azure_openai_service.$auth.deployment_name}/chat/completions?api-version=2023-05-15`,
headers: {
"Content-Type": `application/json`,
"api-key": `${this.azure_openai_service.$auth.api_key}`,
},
data,
})
},
})