Create Image (Dall-E) with OpenAI (ChatGPT) API on New Output Created Event from Phantombuster API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Phantombuster and 2,900+ other apps remarkably fast.

Trigger workflow on

New Output Created Event from the Phantombuster API

Next, do this

Create Image (Dall-E) with the OpenAI (ChatGPT) 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 Phantombuster trigger and OpenAI (ChatGPT) action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Output Created Event trigger
1. Connect your Phantombuster account
2. Configure timer
3. Select a Agent ID
Configure the Create Image (Dall-E) action
1. Connect your OpenAI (ChatGPT) account
2. Select a Model
3. Configure Prompt
4. Optional- Select a Response Format
5. Optional- Select a Size
6. Configure syncDir
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 Output Created Event on Phantombuster

Description:Emit new events when new outputs are created. [See the docs here](https://hub.phantombuster.com/reference/get_agents-fetch-output-1)

Version:0.0.1

Key:phantombuster-new-output

View on GitHub

Phantombuster Overview#

Phantombuster is a tool that lets you automate interactions with web platforms to extract data, manage social media campaigns, and automate web actions. Using its API on Pipedream, you can seamlessly integrate these automation capabilities into complex workflows. Imagine orchestrating a symphony where Phantombuster plays the strings—pulling data from LinkedIn, sending tailored tweets, or automating lead generation—while Pipedream conducts, integrating these actions with other apps and services for a harmonious data-driven performance.

Trigger Code#

import app from "../../phantombuster.app.mjs";
import { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } from "@pipedream/platform";

export default {
  key: "phantombuster-new-output",
  name: "New Output Created Event",
  description: "Emit new events when new outputs are created. [See the docs here](https://hub.phantombuster.com/reference/get_agents-fetch-output-1)",
  version: "0.0.1",
  type: "source",
  props: {
    app,
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    db: "$.service.db",
    agentId: {
      propDefinition: [
        app,
        "agentId",
      ],
    },
  },
  methods: {
    setLastUpdated(lastUpdated) {
      this.db.set("lastUpdated", lastUpdated);
    },
    getLastUpdated() {
      return this.db.get("lastUpdated") || 0;
    },
    setLastContainerId(lastContainerId) {
      this.db.set("lastContainerId", lastContainerId);
    },
    getLastContainerId() {
      return this.db.get("lastContainerId") || 0;
    },
  },
  async run() {
    const resp = await this.app.getOutput({ //always there is one last output for an agent
      params: {
        id: this.agentId,
      },
    });
    if (this.getLastContainerId() != resp.containerId ||
      (resp.mostRecentEndedAt && this.getLastUpdated() < resp.mostRecentEndedAt)) {
      this.$emit(
        resp,
        {
          id: resp.mostRecentEndedAt || Date.now(),
          summary: resp.output,
          ts: resp.mostRecentEndedAt || Date.now(),
        },
      );
      this.setLastUpdated(resp.mostRecentEndedAt);
      this.setLastContainerId(resp.containerId);
    }
  },
};

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
Phantombuster	`app`	`app`	This component uses the Phantombuster app.
	`timer`	`$.interface.timer`
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Agent ID	`agentId`	`string`	Select a value from the drop down menu.

Trigger Authentication#

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

Your API key resides in your Phantombuster Org settings page. This page is also accessible through your navbar's menu, under the label "Org settings". Please notice that for security reasons, you key will only be shown once, on creation. You better copy it in a safe place before refreshing or leaving the page.

For more info, refer to Phantombuster's API documentation

About Phantombuster#

Code-free automations and data extraction. Chain actions and data extraction on the web to generate business leads, marketing audiences and overall growth. Phantombuster gives you the tools and know-how to grow your business faster.

Action#

Create Image (Dall-E) on OpenAI (ChatGPT)

Description:Creates an image given a prompt returning a URL to the image. [See the documentation](https://platform.openai.com/docs/api-reference/images)

Version:0.1.25

Key:openai-create-image

View on GitHub

OpenAI (ChatGPT) Overview#

OpenAI provides a suite of powerful AI models through its API, enabling developers to integrate advanced natural language processing and generative capabilities into their applications. Here’s an overview of the services offered by OpenAI's API:

Use Python or Node.js code to make fully authenticated API requests with your OpenAI account:

Action Code#

import openai from "../../openai.app.mjs";
import constants from "../../common/constants.mjs";
import fs from "fs";
import { IMAGE_MODELS } from "../../common/models.mjs";

export default {
  name: "Create Image (Dall-E)",
  version: "0.1.25",
  annotations: {
    destructiveHint: false,
    openWorldHint: true,
    readOnlyHint: false,
  },
  key: "openai-create-image",
  description: "Creates an image given a prompt returning a URL to the image. [See the documentation](https://platform.openai.com/docs/api-reference/images)",
  type: "action",
  props: {
    openai,
    model: {
      label: "Model",
      description: "Choose the DALL·E models to generate image(s) with.",
      type: "string",
      options: IMAGE_MODELS,
      reloadProps: true,
    },
    prompt: {
      label: "Prompt",
      description: "A text description of the desired image(s). The maximum length is 1000 characters for dall-e-2 and 4000 characters for dall-e-3.",
      type: "string",
    },
    responseFormat: {
      label: "Response Format",
      description: "The format in which the generated images are returned.",
      type: "string",
      optional: true,
      options: constants.IMAGE_RESPONSE_FORMATS,
      default: "url",
      reloadProps: true,
    },
    size: {
      label: "Size",
      description: "The size of the generated images.",
      type: "string",
      optional: true,
      options: constants.IMAGE_SIZES,
      default: "1024x1024",
    },
    syncDir: {
      type: "dir",
      accessMode: "write",
      sync: true,
    },
  },
  async additionalProps() {
    const props = {};
    if (!this.model && !this.responseFormat) {
      return props;
    }
    if (this.responseFormat === "tmp") {
      props.filename = {
        type: "string",
        label: "Filename",
        description: "Filename of the new file in `/tmp` directory. Make sure to include the extension.",
      };
    }
    if (this.model && this.model !== "dall-e-3") {
      props.n = {
        type: "integer",
        label: "N",
        description: "The number of images to generate. Must be between 1 and 10.",
        optional: true,
        default: 1,
      };
    } else {
      props.quality = {
        type: "string",
        label: "Quality",
        description: "The quality of the image",
        options: constants.IMAGE_QUALITIES,
        optional: true,
        default: "standard",
      };
      props.style = {
        type: "string",
        label: "Style",
        description: "The style of the image",
        options: constants.IMAGE_STYLES,
        optional: true,
        default: "natural",
      };
    }
    return props;
  },
  async run({ $ }) {
    const response = await this.openai.createImage({
      $,
      data: {
        prompt: this.prompt,
        n: this.n,
        size: this.size,
        response_format: this.responseFormat === "url"
          ? this.responseFormat
          : "b64_json",
        model: this.model,
        quality: this.quality,
        style: this.style,
      },
    });

    if (this.responseFormat === "tmp") {
      const n = this.n || 1;
      const fileData = [];
      for (let i = 0; i < n; i++) {
        // if N > 0, name subsequent files "filename_1.ext", "filename_2.ext", etc.
        const filename = i === 0
          ? this.filename
          : this.filename.replace(/(\.[^/.]+)$/, `_${i}$1`);
        const outputFilePath = filename.includes("tmp/")
          ? filename
          : `${process.env.STASH_DIR || "/tmp"}/${filename}`;
        await fs.writeFileSync(outputFilePath, Buffer.from(response.data[0].b64_json.toString(), "base64"));
        fileData.push({
          tmp: [
            filename,
            outputFilePath,
          ],
        });
      }
      response.data = fileData;
    }

    if (response.data.length) {
      $.export("$summary", `Successfully created ${response.data.length} image${response.data.length === 1
        ? ""
        : "s"}`);
    }

    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
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
Model	`model`	`string`	Select a value from the drop down menu:`dall-e-2dall-e-3`
Prompt	`prompt`	`string`	A text description of the desired image(s). The maximum length is 1000 characters for dall-e-2 and 4000 characters for dall-e-3.
Response Format	`responseFormat`	`string`	Select a value from the drop down menu:`{ "label": "URL", "value": "url" }{ "label": "Write file to /tmp directory", "value": "tmp" }{ "label": "Base64 JSON", "value": "b64_json" }`
Size	`size`	`string`	Select a value from the drop down menu:`256x256512x5121024x10241792x10241024x1792`
syncDir	`syncDir`	`dir`

Create Image (Dall-E) with OpenAI (ChatGPT) API on New Output Created Event from Phantombuster API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Phantombuster and 2,900+ other apps remarkably fast.

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

1-24of2,900+apps by most popular

1
-
24
of
2,900+
apps by most popular