Classify Items Into Categories with Azure OpenAI Service API on New Submission from Typeform API

Pipedream makes it easy to connect APIs for Azure OpenAI Service, Typeform and 2,200+ other apps remarkably fast.

Trigger workflow on

New Submission from the Typeform API

Next, do this

Classify Items Into Categories with the Azure OpenAI Service API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a Typeform trigger and Azure OpenAI Service action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Submission trigger
1. Connect your Typeform account
2. Select a Form
Configure the Classify Items Into Categories action
1. Connect your Azure OpenAI Service account
2. Configure Items
3. Configure Categories
4. Optional- Configure Temperature
5. Optional- Configure N
6. Optional- Configure Stream
7. Optional- Configure Stop
8. Optional- Configure Max Tokens
9. Optional- Configure Presence Penalty
10. Optional- Configure Frequency Penalty
11. Optional- Configure User
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

New Submission on Typeform

Description:Emit new submission

Version:0.0.8

Key:typeform-new-submission

View on GitHub

Typeform Overview#

The Typeform API furnishes you with the means to create dynamic forms and collect user responses in real-time. By leveraging this API within Pipedream's serverless platform, you can automate workflows to process this data, integrate seamlessly with other services, and react to form submissions instantaneously. This empowers you to craft tailored responses, synchronize with databases, trigger email campaigns, or even manage event registrations without manual intervention.

Trigger Code#

import { createHmac } from "crypto";
import sampleEmit from "./test-event.mjs";
import { uuid } from "uuidv4";
import common from "../common/common.mjs";
import constants from "../../constants.mjs";
import utils from "../common/utils.mjs";

const { typeform } = common.props;
const { parseIsoDate } = utils;

export default {
  ...common,
  key: "typeform-new-submission",
  name: "New Submission",
  version: "0.0.8",
  type: "source",
  description: "Emit new submission",
  props: {
    ...common.props,
    http: {
      type: "$.interface.http",
      customResponse: true,
    },
    db: "$.service.db",
    formId: {
      propDefinition: [
        typeform,
        "formId",
      ],
    },
  },
  methods: {
    ...common.methods,
    generateSecret() {
      return "" + Math.random();
    },
  },
  hooks: {
    ...common.hooks,
    async activate() {
      const secret = this.generateSecret();
      this._setSecret(secret);

      let tag = this._getTag();
      if (!tag) {
        tag = uuid();
        this._setTag(tag);
      }

      return await this.typeform.createHook({
        endpoint: this.http.endpoint,
        formId: this.formId,
        tag,
        secret,
      });
    },
    async deactivate() {
      const tag = this._getTag();

      return await this.typeform.deleteHook({
        formId: this.formId,
        tag,
      });
    },
  },
  async run(event) {
    const {
      body,
      headers,
    } = event;

    const { [constants.TYPEFORM_SIGNATURE]: typeformSignature } = headers;

    if (typeformSignature) {
      const secret = this._getSecret();

      const hmac =
        createHmac(constants.ALGORITHM, secret)
          .update(body)
          .digest(constants.ENCODING);

      const signature = `${constants.ALGORITHM}=${hmac}`;

      if (typeformSignature !== signature) {
        throw new Error("signature mismatch");
      }
    }

    let formResponseString = "";
    const data = Object.assign({}, body.form_response);
    data.form_response_parsed = {};

    for (let i = 0; i < body.form_response.answers.length; i++) {
      const field = body.form_response.definition.fields[i];
      const answer = body.form_response.answers[i];

      let parsedAnswer;
      let value = answer[answer.type];

      if (value.label) {
        parsedAnswer = value.label;

      } else if (value.labels) {
        parsedAnswer = value.labels.join();

      } else if (value.choice) {
        parsedAnswer = value.choice;

      } else if (value.choices) {
        parsedAnswer = value.choices.join();

      } else {
        parsedAnswer = value;
      }

      data.form_response_parsed[field.title] = parsedAnswer;
      formResponseString += `### ${field.title}\n${parsedAnswer}\n`;
    }

    data.form_response_string = formResponseString;
    data.raw_webhook_event = body;

    if (data.landed_at) {
      data.landed_at = parseIsoDate(data.landed_at);
    }

    if (data.submitted_at) {
      data.submitted_at = parseIsoDate(data.submitted_at);
    }

    data.form_title = body.form_response.definition.title;
    delete data.answers;
    delete data.definition;

    this.$emit(data, {
      summary: JSON.stringify(data),
      id: data.token,
    });

    this.http.respond({
      status: 200,
    });
  },
  sampleEmit,
};

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
Typeform	`typeform`	`app`	This component uses the Typeform app.
N/A	`http`	`$.interface.http`	This component uses `$.interface.http` to generate a unique URL when the component is first instantiated. Each request to the URL will trigger the `run()` method of the component.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Form	`formId`	`string`	Select a value from the drop down menu.

Trigger Authentication#

Typeform uses OAuth authentication. When you connect your Typeform account, Pipedream will open a popup window where you can sign into Typeform and grant Pipedream permission to connect to your account. Pipedream securely stores and automatically refreshes the OAuth tokens so you can easily authenticate any Typeform API.

Pipedream requests the following authorization scopes when you connect your account:

offlineaccounts:readforms:writeforms:readimages:writeimages:readthemes:writethemes:readresponses:readresponses:writewebhooks:readwebhooks:writeworkspaces:readworkspaces:write

About Typeform#

Typeform lets you build no-code forms, quizzes, and surveys - and get more responses.

Action#

Classify Items Into Categories on Azure OpenAI Service

Description:Classify items into specific categories. [See the documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions)

Version:0.0.1

Key:azure_openai_service-classify-items-into-categories

View on GitHub

Azure OpenAI Service Overview#

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.

Action Code#

import azureOpenAI from "../../azure_openai_service.app.mjs";
import common from "../common/common-helper.mjs";

export default {
  ...common,
  key: "azure_openai_service-classify-items-into-categories",
  name: "Classify Items Into Categories",
  description: "Classify items into specific categories. [See the documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions)",
  version: "0.0.1",
  type: "action",
  props: {
    azureOpenAI,
    items: {
      label: "Items",
      description: "Items to categorize",
      type: "string[]",
    },
    categories: {
      label: "Categories",
      description: "Categories to classify items into",
      type: "string[]",
    },
    ...common.props,
  },
  methods: {
    ...common.methods,
    systemInstructions() {
      return "Your goal is to categorize items into specific categories and produce ONLY JSON. The user will provide both the items and categories. Please only categorize items into the specific categories, and no others, and output ONLY JSON.";
    },
    outputFormat() {
      return "Please only categorize items into the specific categories, and no others. Output a valid JSON string — an array of objects, where each object has the following properties: item, category. Do not return any English text other than the JSON, either before or after the JSON. I need to parse the response as JSON, and parsing will fail if you return any English before or after the JSON";
    },
    userMessage() {
      return `Categorize each of the following items:\n\n${this.items.join("\n")}\n\ninto one of the following categories:\n\n${this.categories.join("\n")}\n\n${this.outputFormat()}}`;
    },
    summary() {
      return `Categorized ${this.items.length} items into ${this.categories.length} categories.`;
    },
    formatOutput({
      messages, response,
    }) {
      if (!messages || !response) {
        throw new Error("Invalid API output, please reach out to https://pipedream.com/support");
      }
      const assistantResponse = response.choices?.[0]?.message?.content;
      let categorizations = assistantResponse;
      try {
        const categorizationJSON = assistantResponse.substring(
          assistantResponse.indexOf("```json") + 7,
          assistantResponse.lastIndexOf("```"),
        ).trim();
        categorizations = JSON.parse(categorizationJSON);
      } catch (err) {
        console.log("Failed to parse output, assistant returned malformed JSON");
      }
      return {
        categorizations,
        messages,
      };
    },
  },
};

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
Azure OpenAI Service	`azureOpenAI`	`app`	This component uses the Azure OpenAI Service app.
Items	`items`	`string[]`	Items to categorize
Categories	`categories`	`string[]`	Categories to classify items into
Temperature	`temperature`	`string`	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
N	`n`	`integer`	How many completions to generate
Stream	`stream`	`boolean`	If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
Stop	`stop`	`string`	Up to 4 sequences where the API will stop generating further tokens.
Max Tokens	`maxTokens`	`integer`	The maximum number of tokens allowed for the generated answer. By default, the number of tokens the model can return will be (4096 - prompt tokens).
Presence Penalty	`presencePenalty`	`string`	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
Frequency Penalty	`frequencyPenalty`	`string`	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
User	`user`	`string`	A unique identifier representing your end-user, which can help Azure OpenAI to monitor and detect abuse.

Action Authentication#

Azure OpenAI Service uses API keys for authentication. When you connect your Azure OpenAI Service account, Pipedream securely stores the keys so you can easily authenticate to Azure OpenAI Service APIs in both code and no-code steps.

Before you start, you'll need to deploy a model in the Azure OpenAI Service.

Once that's done, enter the name of your Azure OpenAI resource, the deployment name you chose when you deployed the model, and your Azure OpenAI key below.