Document Question Answering with Hugging Face API on New Row Added from Supabase API

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

Trigger workflow on

New Row Added from the Supabase 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 Supabase 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 Row Added trigger
1. Connect your Supabase account
2. Configure Table
3. Optional- Configure Row Identifier
4. Optional- Configure Column
5. Optional- Select a Filter
6. Optional- Configure Value
7. Configure Order By
8. Optional- Select a Sort Order
9. Configure timer
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 Row Added on Supabase

Description:Emit new event for every new row added in a table. [See documentation here](https://supabase.com/docs/reference/javascript/select)

Version:0.0.4

Key:supabase-new-row-added

View on GitHub

Supabase Overview#

Supabase is a real-time backend-as-a-service that provides developers with a suite of tools to quickly build and scale their applications. It offers database storage, authentication, instant APIs, and real-time subscriptions. With the Supabase API, you can perform CRUD operations on your database, manage users, and listen to database changes in real time. When integrated with Pipedream, you can automate workflows that react to these database events, synchronize data across multiple services, or streamline user management processes.

Trigger Code#

import base from "../common/base.mjs";
import {
  DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
  ConfigurationError,
} from "@pipedream/platform";
import constants from "../../common/constants.mjs";

export default {
  key: "supabase-new-row-added",
  name: "New Row Added",
  description: "Emit new event for every new row added in a table. [See documentation here](https://supabase.com/docs/reference/javascript/select)",
  version: "0.0.4",
  type: "source",
  props: {
    ...base.props,
    column: {
      propDefinition: [
        base.props.supabase,
        "column",
      ],
      optional: true,
    },
    filter: {
      propDefinition: [
        base.props.supabase,
        "filter",
      ],
      optional: true,
    },
    value: {
      propDefinition: [
        base.props.supabase,
        "value",
      ],
      optional: true,
    },
    orderBy: {
      propDefinition: [
        base.props.supabase,
        "column",
      ],
      label: "Order By",
      description: "Column name to order by",
    },
    sortOrder: {
      propDefinition: [
        base.props.supabase,
        "sortOrder",
      ],
    },
    db: "$.service.db",
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
  },
  methods: {
    _getOffset() {
      return this.db.get("offset") || 0;
    },
    _setOffset(offset) {
      this.db.set("offset", offset);
    },
  },
  async run() {
    const {
      table,
      column,
      filter,
      value,
      orderBy,
      sortOrder,
      rowIdentifier,
    } = this;

    if ((column || filter || value) && !(column && filter && value)) {
      throw new ConfigurationError("If `column`, `filter`, or `value` is used, all three must be entered");
    }

    const offset = this._getOffset();
    const client = await this.supabase._client();
    const query = client
      .from(table)
      .select()
      .order(orderBy, {
        ascending: sortOrder,
      })
      .range(offset, offset + constants.MAX_OFFSET);

    if (filter) {
      const filterMethod = this.supabase[filter];
      filterMethod(query, column, value);
    }

    const { data } = await query;
    this._setOffset(offset + data.length);

    for (const row of data) {
      let summary = "New row in table";
      if (row[rowIdentifier]) {
        summary = `${summary}: ${row[rowIdentifier]}`;
      }
      this.$emit(row, {
        summary,
      });
    }
  },
};

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
Supabase	`supabase`	`app`	This component uses the Supabase app.
Table	`table`	`string`	The name of the table to watch for new rows
Row Identifier	`rowIdentifier`	`string`	The column name to use as the row identifier
Column	`column`	`string`	Column name to search by
Filter	`filter`	`string`	Select a value from the drop down menu:`{ "label": "Equal", "value": "equalTo" }{ "label": "Not Equal", "value": "notEqualTo" }{ "label": "Greater Than", "value": "greaterThan" }{ "label": "Greater Than or Equal To", "value": "greaterThanOrEqualTo" }{ "label": "Less Than", "value": "lessThan" }{ "label": "Less Than or Equal To", "value": "lessThanOrEqualTo" }{ "label": "Contains (Case Sensitive)", "value": "patternMatch" }{ "label": "Contains (Case Insensitive)", "value": "patternMatchCaseInsensitive" }`
Value	`value`	`string`	Value of the column specified to search for
Order By	`orderBy`	`string`	Column name to order by
Sort Order	`sortOrder`	`string`	Select a value from the drop down menu:`ascendingdescending`
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`

Trigger Authentication#

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

Supabase provides a Service Key to get started. You can find the service_role in the API Settings page.

Finding the Supabase subdomain

About Supabase#

Supabase is an open source Firebase alternative.

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 + Supabase#

Other Popular Integrations#

Image Classification with Hugging Face API on New Row Added from Supabase API

Supabase + Hugging Face

Try it

Language Translation with Hugging Face API on New Row Added from Supabase API

Supabase + Hugging Face

Try it

Object Detection with Hugging Face API on New Row Added from Supabase API

Supabase + Hugging Face

Try it

Text Classification with Hugging Face API on New Row Added from Supabase API

Supabase + Hugging Face

Try it

Text Summarization with Hugging Face API on New Row Added from Supabase API

Supabase + Hugging Face

Try it

Popular Triggers#

New Row Added from the Supabase API

Emit new event for every new row added in a table. See documentation here

Try it

New Webhook Event (Instant) from the Supabase API

Emit new event for every insert, update, or delete operation in a table. This source requires user configuration using the Supabase website. More information in the README. Also see documentation here

Try it