Text Summarization with Hugging Face API on New Customer Created (Instant) from AmeriCommerce API

Pipedream makes it easy to connect APIs for Hugging Face, AmeriCommerce and 2,900+ other apps remarkably fast.

Trigger workflow on

New Customer Created (Instant) from the AmeriCommerce API

Next, do this

Text Summarization 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 AmeriCommerce 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 Customer Created (Instant) trigger
1. Connect your AmeriCommerce account
2. Select a Store ID
Configure the Text Summarization action
1. Connect your Hugging Face account
2. Select a Model ID
3. Configure Text
4. Optional- Configure Max Length
5. Optional- Configure Min Length
6. Optional- Configure Max Time
7. Optional- Configure Repetition Penalty
8. Optional- Configure Temperature
9. Optional- Configure Top K
10. Optional- Configure Top P
11. Optional- Configure Request Timeout
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 Customer Created (Instant) on AmeriCommerce

Description:Emit new event when a customer is created in your Americommerce store. [See the documentation](https://developers.cart.com/docs/rest-api/ZG9jOjM1MDU4Nw-webhooks#subscribing-to-a-webhook).

Version:0.0.1

Key:americommerce-new-customer-instant

View on GitHub

Trigger Code#

import common from "../common/webhook.mjs";
import events from "../common/events.mjs";
import sampleEmit from "./test-event.mjs";

export default {
  ...common,
  key: "americommerce-new-customer-instant",
  name: "New Customer Created (Instant)",
  description: "Emit new event when a customer is created in your Americommerce store. [See the documentation](https://developers.cart.com/docs/rest-api/ZG9jOjM1MDU4Nw-webhooks#subscribing-to-a-webhook).",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  methods: {
    ...common.methods,
    getEventType() {
      return events.CUSTOMER_CREATED;
    },
    generateMeta(resource) {
      const { customer } = resource;
      return {
        id: customer.id,
        summary: `New Customer: ${customer.first_name}`,
        ts: Date.parse(customer.created_at),
      };
    },
  },
  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
AmeriCommerce	`app`	`app`	This component uses the AmeriCommerce app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
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.
Store ID	`storeId`	`string`	Select a value from the drop down menu.

Trigger Authentication#

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

About AmeriCommerce#

The B2B Commerce Platform for Digital Transformations.

Action#

Text Summarization on Hugging Face

Description: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](https://huggingface.co/docs/huggingface.js/inference/classes/HfInference#summarization).

Version:0.0.2

Key:hugging_face-text-summarization

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 utils from "../../common/utils.mjs";
import tag from "../common/tag.mjs";

export default {
  key: "hugging_face-text-summarization",
  name: "Text Summarization",
  description: "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](https://huggingface.co/docs/huggingface.js/inference/classes/HfInference#summarization).",
  type: "action",
  version: "0.0.2",
  annotations: {
    destructiveHint: false,
    openWorldHint: true,
    readOnlyHint: true,
  },
  props: {
    app,
    modelId: {
      propDefinition: [
        app,
        "modelId",
        () => ({
          tagFilter: tag.SUMMARIZATION,
        }),
      ],
    },
    text: {
      type: "string",
      label: "Text",
      description: "The text to use for summarization.",
    },
    maxLength: {
      type: "integer",
      label: "Max Length",
      description: "The maximum length of the summary.",
      optional: true,
    },
    minLength: {
      type: "integer",
      label: "Min Length",
      description: "The minimum length of the summary.",
      optional: true,
    },
    maxTime: {
      type: "integer",
      label: "Max Time",
      description: "The maximum time in seconds to spend on the generation.",
      optional: true,
    },
    repetitionPenalty: {
      type: "string",
      label: "Repetition Penalty",
      description: "The parameter for repetition penalty. 1.0 means no penalty. See [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details.",
      optional: true,
    },
    temperature: {
      type: "string",
      label: "Temperature",
      description: "The value used to module the next token probabilities. Must be strictly positive. See [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details.",
      optional: true,
    },
    topK: {
      type: "integer",
      label: "Top K",
      description: "The number of highest probability vocabulary tokens to keep for top-k-filtering.",
      optional: true,
    },
    topP: {
      type: "string",
      label: "Top P",
      description: "If set to float < 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation.",
      optional: true,
    },
    requestTimeout: {
      type: "integer",
      label: "Request Timeout",
      description: "The maximum time in milliseconds to wait for a response from the API.",
      optional: true,
    },
  },
  async run({ $: step }) {
    const {
      modelId,
      text,
      maxLength,
      minLength,
      maxTime,
      repetitionPenalty,
      temperature,
      topK,
      topP,
      requestTimeout,
    } = this;

    const parameters = utils.reduceProperties({
      additionalProps: {
        max_length: maxLength,
        min_length: minLength,
        max_time: maxTime,
        repetition_penalty: utils.strToFloat(repetitionPenalty),
        temperature: utils.strToFloat(temperature),
        top_k: utils.strToFloat(topK),
        top_p: utils.strToFloat(topP),
      },
    });

    const response = await this.app.inference({
      step,
      modelId,
      data: {
        inputs: text,
        parameters,
      },
      timeout: requestTimeout,
    });

    step.export("$summary", "Successfully summarized text");

    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.
Text	`text`	`string`	The text to use for summarization.
Max Length	`maxLength`	`integer`	The maximum length of the summary.
Min Length	`minLength`	`integer`	The minimum length of the summary.
Max Time	`maxTime`	`integer`	The maximum time in seconds to spend on the generation.
Repetition Penalty	`repetitionPenalty`	`string`	The parameter for repetition penalty. 1.0 means no penalty. See this paper for more details.
Temperature	`temperature`	`string`	The value used to module the next token probabilities. Must be strictly positive. See this paper for more details.
Top K	`topK`	`integer`	The number of highest probability vocabulary tokens to keep for top-k-filtering.
Top P	`topP`	`string`	If set to float < 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation.
Request Timeout	`requestTimeout`	`integer`	The maximum time in milliseconds to wait for a response from the API.

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 + AmeriCommerce#

Other Popular Integrations#

Document Question Answering with Hugging Face API on New Customer Created (Instant) from AmeriCommerce API

AmeriCommerce + Hugging Face

Try it

Image Classification with Hugging Face API on New Customer Created (Instant) from AmeriCommerce API

AmeriCommerce + Hugging Face

Try it

Language Translation with Hugging Face API on New Customer Created (Instant) from AmeriCommerce API

AmeriCommerce + Hugging Face

Try it

Object Detection with Hugging Face API on New Customer Created (Instant) from AmeriCommerce API

AmeriCommerce + Hugging Face

Try it

Text Classification with Hugging Face API on New Customer Created (Instant) from AmeriCommerce API

AmeriCommerce + Hugging Face

Try it

Popular Triggers#

New Customer Created (Instant) from the AmeriCommerce API

Emit new event when a customer is created in your Americommerce store. See the documentation

Try it

New Product Instant from the AmeriCommerce API

Emit new event when a product is added to your Americommerce store. See the documentation

Try it

New Valid Order (Instant) from the AmeriCommerce API

Emit new event when a new valid order (not declined or cancelled) is created in your Americommerce store. See the documentation

Try it

Popular Actions#

Change Order Status with the AmeriCommerce API

Changes the status of an existing order. See the documentation

Try it

Create Or Update Order with the AmeriCommerce API

Creates a new order or updates an existing one. See the documentation here and here

Try it

Update Customer with the AmeriCommerce API

Updates the details of a registered customer. See the documentation

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