Document Question Answering with Hugging Face API

Pipedream makes it easy to connect APIs for Hugging Face and 2,500+ other apps remarkably fast.

Trigger workflow on

HTTP requests, schedules and app events

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#

Create a workflow to Document Question Answering with the Hugging Face API. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Configure the Document Question Answering action
1. Connect your Hugging Face account
2. Select a Model ID
3. Configure Image URL
4. Configure Question
Select a trigger to run your workflow on HTTP requests, schedules or app events
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Integrations#

Document Question Answering with Hugging Face API on New Requests from HTTP / Webhook API

HTTP / Webhook + Hugging Face

Try it

Document Question Answering with Hugging Face API on New Submission from Typeform API

Typeform + Hugging Face

Try it

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

Jotform + Hugging Face

Try it

Document Question Answering with Hugging Face API on New Custom Webhook Events from Stripe API

Stripe + Hugging Face

Try it

Document Question Answering with Hugging Face API on New Scheduled Tasks from Pipedream API

Pipedream + Hugging Face

Try it

Details#

This is a pre-built, source-available component from Pipedream's GitHub repo. The component is 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.

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

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;
  },
};

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
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.

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 Use Hugging Face#

Actions#

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

Language Translation with the Hugging Face API

This task is well known to translate text from one language to another. See the docs

Try it

Object Detection with the Hugging Face API

This task reads some image input and outputs the likelihood of classes and bounding boxes of detected objects. See the docs

Try it

Text Classification with the Hugging Face API

Usually used for sentiment-analysis this will output the likelihood of classes of an input. This action allows you to classify text into categories. See the docs

Try it

Text Summarization with the Hugging Face API

This task is well known to summarize longer text into shorter text. Be careful, some models have a maximum length of input. That means that the summary cannot handle full books for instance. Be careful when choosing your model. See the docs

Try it