Background Removal with api4ai API on New Conversation Started from Vapi API

Pipedream makes it easy to connect APIs for api4ai, Vapi and 2,900+ other apps remarkably fast.

Trigger workflow on

New Conversation Started from the Vapi API

Next, do this

Background Removal with the api4ai 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 Vapi trigger and api4ai action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Conversation Started trigger
1. Connect your Vapi account
2. Configure timer
Configure the Background Removal action
1. Connect your api4ai account
2. Configure alert
3. Configure Image
4. Optional- Configure Mask mode
5. Optional- Select a Result image representation
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 Conversation Started on Vapi

Description:Emit new event when a voicebot starts a conversation.

Version:0.0.1

Key:vapi-new-conversation

View on GitHub

Vapi Overview#

The Vapi API delivers voice automation capabilities, letting you build powerful voice response systems. With Vapi, you can automate calls, send voice messages, and create dynamic interactions through speech recognition and text-to-speech. Pipedream's serverless platform allows you to integrate Vapi's API with numerous other services to automate workflows, react to events, and orchestrate complex voice-enabled processes.

Trigger Code#

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

export default {
  ...common,
  key: "vapi-new-conversation",
  name: "New Conversation Started",
  description: "Emit new event when a voicebot starts a conversation.",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  methods: {
    ...common.methods,
    getFunction() {
      return this.vapi.listCalls;
    },
    getSummary(item) {
      return `New Conversation: ${item.id}`;
    },
  },
  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
Vapi	`vapi`	`app`	This component uses the Vapi app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`

Trigger Authentication#

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

About Vapi#

Vapi is the platform to build, test and deploy voicebots in minutes rather than months.

Action#

Background Removal on api4ai

Description:Automatically and quickly remove image background with high accuracy. Powered by API4AI.

Version:0.0.3

Key:api4ai-background-removal

View on GitHub

Background Removal Overview#

⭐️ Background Removal offers advanced image analysis for foreground segmentation and effortless background removal.

bg-removal

🤖 Demo

Discover the Background Removal Web demo for free and get a feel for its capabilities before diving deeper. No registration is required: https://api4.ai/apis/bg-removal#demo-wrapper

Action Code#

import app from "../../api4ai.app.mjs";
import {
  retryWithExponentialBackoff, representFile,
} from "../../common/utils.mjs";

export default {
  name: "Background Removal",
  description:
    "Automatically and quickly remove image background with high accuracy. Powered by API4AI.",
  key: "api4ai-background-removal",
  version: "0.0.3",
  annotations: {
    destructiveHint: true,
    openWorldHint: true,
    readOnlyHint: false,
  },
  type: "action",
  props: {
    app,
    alert: {
      type: "alert",
      alertType: "info",
      content: "Subscribe to [API4AI Background Removal](https://rapidapi.com/api4ai-api4ai-default/api/background-removal4/pricing) on the RapidAPI hub before you start using it.",
    },
    image: {
      propDefinition: [
        app,
        "image",
      ],
    },
    mask: {
      type: "boolean",
      label: "Mask mode",
      description:
        "Return the foreground object mask instead of the image with the background removed.",
      default: false,
      optional: true,
    },
    representation: {
      type: "string",
      label: "Result image representation",
      description:
        "Return the result image as:\n  * **path** to a file (default)\n  * **URL** to a file hosted by api4ai (valid for 1 day)\n  * **Base64** string with file's content\n  * **Buffer** encoded in JSON with a file's content\n  * **Array** of bytes with a file's content",
      default: "Path to file",
      optional: true,
      options: [
        "Path to file",
        "URL to file",
        "Base64 string",
        "JSON Buffer",
        "Array",
      ],
    },
  },
  async run({ $ }) {
    // Initialize output.
    let summary = "";
    let result = "";
    const objects = [];
    let width = 0;
    let height = 0;

    // Prepare query params.
    const mode = this.mask
      ? "fg-mask"
      : "fg-image";
    const representation = this.representation == "URL to file"
      ? "url"
      : "base64";

    // Perform request and parse results.
    const cb = () =>
      this.app.makeRequest(
        $,
        "https://background-removal4.p.rapidapi.com/v1/results",
        this.image,
        {
          mode,
          representation,
        },
      );
    const response = await retryWithExponentialBackoff(cb);
    const isOk = response?.results?.[0]?.status?.code === "ok";
    summary = response?.results?.[0]?.status?.message || JSON.stringify(response);
    if (isOk) {
      result = response.results[0].entities[0].image;
      const rawObjects = response.results[0].entities[1].objects;
      rawObjects.forEach(function (o) {
        const box = {
          x: o.box[0],
          y: o.box[1],
          w: o.box[2],
          h: o.box[3],
        };
        const cls = Object.keys(o.entities[0].classes)[0];
        objects.push({
          class: cls,
          box: box,
        });
      });
      const format = response.results[0].entities[0].format;
      result = representFile(result, format, this.representation);
      width = response.results[0].width;
      height = response.results[0].height;
    }
    else {
      throw new Error(summary);
    }

    $.export("$summary", summary);
    $.export("result", result);
    $.export("objects", objects);
    $.export("width", width);
    $.export("height", height);
  },
};

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
api4ai	`app`	`app`	This component uses the api4ai app.
Image	`image`	`string`	Input image. Provide either a file URL or a path to a file in the /tmp directory (for example, /tmp/myFile.pdf).
Mask mode	`mask`	`boolean`	Return the foreground object mask instead of the image with the background removed.
Result image representation	`representation`	`string`	Select a value from the drop down menu:`Path to fileURL to fileBase64 stringJSON BufferArray`