Document Question Answering with Hugging Face API on New Submission (Instant) from Jotform API

Pipedream makes it easy to connect APIs for Hugging Face, Jotform and 2,400+ other apps remarkably fast.

Trigger workflow on

New Submission (Instant) from the Jotform API

Next, do this

Document Question Answering with the Hugging Face 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 Jotform trigger and Hugging Face 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 (Instant) trigger
1. Connect your Jotform account
2. Optional- Select a Team
3. Select a Form
Configure the Document Question Answering action
1. Connect your Hugging Face account
2. Select a Model ID
3. Configure Image URL
4. Configure Question
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 (Instant) on Jotform

Description:Emit new event when a form is submitted

Version:0.1.5

Key:jotform-new-submission

View on GitHub

Jotform Overview#

Jotform’s API is a powerhouse for automating form and survey data management. With Pipedream, harness this API to trigger workflows from new form submissions, manipulate and analyze your form data, and sync it across various platforms. Think streamlined data entry to CRMs, instant notifications for new leads or feedback, and timely data backups to cloud storage.

Trigger Code#

import jotform from "../../jotform.app.mjs";
import sampleEmit from "./test-event.mjs";

export default {
  key: "jotform-new-submission",
  name: "New Submission (Instant)",
  description: "Emit new event when a form is submitted",
  version: "0.1.5",
  type: "source",
  dedupe: "unique",
  props: {
    jotform,
    http: "$.interface.http",
    teamId: {
      propDefinition: [
        jotform,
        "teamId",
      ],
    },
    formId: {
      propDefinition: [
        jotform,
        "formId",
        (c) => ({
          teamId: c.teamId,
          excludeDeleted: true,
        }),
      ],
    },
  },
  hooks: {
    async deploy() {
      const { content: form } = await this.jotform.getForm(this.formId, this.teamId);
      const { content: submissions } = await this.jotform.getFormSubmissions({
        formId: this.formId,
        teamId: this.teamId,
        params: {
          limit: 25,
          orderby: "created_at",
        },
      });
      for (let submission of submissions.reverse()) {
        const meta = {
          id: submission.id,
          summary: form.title,
          ts: Date.now(),
        };
        this.$emit(submission, meta);
      }
    },
    async activate() {
      return (await this.jotform.createHook({
        endpoint: this.http.endpoint,
        formId: this.formId,
        teamId: this.teamId,
      }));
    },
    async deactivate() {
      return (await this.jotform.deleteHook({
        endpoint: this.http.endpoint,
        formId: this.formId,
        teamId: this.teamId,
      }));
    },
  },
  async run(event) {
    const { body } = event;
    let { content: submission } = await this.jotform.getFormSubmission({
      submissionId: body.submissionID,
      teamId: this.teamId,
    });

    // insert answers from the webhook event
    const rawRequest = JSON.parse(body.rawRequest);
    for (const key of Object.keys(rawRequest)) {
      const regex = /^q(\d+)_/;
      const match = key.match(regex);
      if (match && match[1]) {
        submission.answers[match[1]].answer = rawRequest[key];
      }
    }

    this.$emit(submission, {
      summary: body.formTitle || JSON.stringify(body),
      id: body.submissionID,
      ts: Date.now(),
    });
  },
  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
Jotform	`jotform`	`app`	This component uses the Jotform 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.
Team	`teamId`	`string`	Select a value from the drop down menu.
Form	`formId`	`string`	Select a value from the drop down menu.

Trigger Authentication#

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

About Jotform#

Jotform enables you to create online forms, collect responses directly in your email, and create fillable PDF forms.

Action#

Document Question Answering on Hugging Face

Description:Want to have a nice know-it-all bot that can answer any question?. This action allows you to ask a question and get an answer from a trained model. [See the docs](https://huggingface.co/docs/huggingface.js/inference/classes/HfInference#questionanswer).

Version:0.0.1

Key:hugging_face-document-question-answering

View on GitHub

Hugging Face Overview#

The Hugging Face API provides access to a vast range of machine learning models, primarily for natural language processing (NLP) tasks like text classification, translation, summarization, and question answering. It lets you leverage pre-trained models and fine-tune them on your data. Using the API within Pipedream, you can automate workflows that involve language processing, integrate AI insights into your apps, or respond to events with AI-generated content.

Action Code#

import app from "../../hugging_face.app.mjs";
import tag from "../common/tag.mjs";

export default {
  key: "hugging_face-document-question-answering",
  name: "Document Question Answering",
  description: "Want to have a nice know-it-all bot that can answer any question?. This action allows you to ask a question and get an answer from a trained model. [See the docs](https://huggingface.co/docs/huggingface.js/inference/classes/HfInference#questionanswer).",
  type: "action",
  version: "0.0.1",
  props: {
    app,
    modelId: {
      propDefinition: [
        app,
        "modelId",
        () => ({
          tagFilter: tag.DOCUMENT_QUESTION_ANSWERING,
        }),
      ],
    },
    imageUrl: {
      description: "The image url to use for answering the question.",
      propDefinition: [
        app,
        "imageUrl",
      ],
    },
    question: {
      type: "string",
      label: "Question",
      description: "The question to ask.",
    },
  },
  async run({ $: step }) {
    const {
      modelId,
      imageUrl,
      question,
    } = this;

    const image = await this.app.getBinaryFromUrl(imageUrl);

    const response = await this.app.inference({
      step,
      modelId,
      data: {
        inputs: {
          image,
          question,
        },
      },
    });

    step.export("$summary", `Successfully answered question with score ${response[0].score}`);

    return response;
  },
};

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
Hugging Face	`app`	`app`	This component uses the Hugging Face app.
Model ID	`modelId`	`string`	Select a value from the drop down menu.
Image URL	`imageUrl`	`string`	The image url to use for answering the question.
Question	`question`	`string`	The question to ask.

Action Authentication#

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

To retrieve your Access Tokens,

Navigate to your Hugging Face account and sign in
Go to “Settings” > “Access Tokens”

About Hugging Face#

Build, train and deploy state of the art models powered by the reference open source in machine learning.

More Ways to Connect Hugging Face + Jotform#

Other Popular Integrations#

Image Classification with Hugging Face API on New Submission (Instant) from Jotform API

Jotform + Hugging Face

Try it

Language Translation with Hugging Face API on New Submission (Instant) from Jotform API

Jotform + Hugging Face

Try it

Object Detection with Hugging Face API on New Submission (Instant) from Jotform API

Jotform + Hugging Face

Try it

Text Classification with Hugging Face API on New Submission (Instant) from Jotform API

Jotform + Hugging Face

Try it

Text Summarization with Hugging Face API on New Submission (Instant) from Jotform API

Jotform + Hugging Face

Try it

Popular Triggers#

New Submission (Instant) from the Jotform API

Emit new event when a form is submitted

Try it

Popular Actions#

Get Form Submissions with the Jotform API

Gets a list of form responses See the docs here

Try it

Get Monthly User Usage with the Jotform API

Gets number of form submissions received this month. Also, get number of SSL form submissions, payment form submissions and upload space used by user See the docs here

Try it

Get User Submissions with the Jotform API

Gets a list of all submissions for all forms on the account See the docs here

Try it

Document Question Answering with the Hugging Face API

Want to have a nice know-it-all bot that can answer any question?. This action allows you to ask a question and get an answer from a trained model. See the docs.

Try it

Image Classification with the Hugging Face API

This task reads some image input and outputs the likelihood of classes. This action allows you to classify images into categories. See the docs.

Try it