Create Image with Azure OpenAI Service API on New Document Status Changed from Docsumo API

Pipedream makes it easy to connect APIs for Azure OpenAI Service, Docsumo and 2,400+ other apps remarkably fast.

Trigger workflow on

New Document Status Changed from the Docsumo API

Next, do this

Create Image with the Azure OpenAI Service 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 Docsumo trigger and Azure OpenAI Service action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Document Status Changed trigger
1. Connect your Docsumo account
2. Configure timer
Configure the Create Image action
1. Connect your Azure OpenAI Service account
2. Configure Prompt
3. Optional- Configure N
4. Optional- Select a Size
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 Document Status Changed on Docsumo

Description:Emit new event when document status is changed

Version:0.0.1

Key:docsumo-document-status-changed

View on GitHub

Docsumo Overview#

The Docsumo API offers robust capabilities for extracting and processing data from various types of documents, like invoices, receipts, and bank statements. It applies intelligent OCR (Optical Character Recognition) to transform unstructured documents into structured data. With Pipedream, you can harness this power to automate workflows, such as digitizing financial records, validating document data, or integrating extracted information into databases or other apps, all with minimal code.

Trigger Code#

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

export default {
  name: "New Document Status Changed",
  description: "Emit new event when document status is changed",
  key: "docsumo-document-status-changed",
  version: "0.0.1",
  type: "source",
  props: {
    app,
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    db: "$.service.db",
  },
  hooks: {
    async deploy() {
      const documents = await this.listAllDocuments();
      this.setDocuments(this.getDocumentsStatusMap(documents));
    },
  },
  methods: {
    setDocuments(documents) {
      this.db.set("documents", documents);
    },
    getDocuments() {
      return this.db.get("documents") || {};
    },
    getDocumentsStatusMap(documents) {
      const documentsStatusMap = {};
      for (const document of documents) {
        documentsStatusMap[document.doc_id] = document.status;
      }
      return documentsStatusMap;
    },
    getDocumentsMappedByDocId(documents) {
      const documentsMap = {};
      for (const document of documents) {
        documentsMap[document.doc_id] = document;
      }
      return documentsMap;
    },
    async listAllDocuments(params) {
      const PAGE_SIZE = 200;
      let page = 0;
      const documents = [];

      while (true) {
        const res = await this.app.listDocuments({
          ...params,
          limit: PAGE_SIZE,
          offset: (page * PAGE_SIZE),
        });
        if (res.data.documents.length === 0) {
          break;
        }
        documents.push(...res.data.documents);
        page++;
      }

      return documents;
    },
    emitEvent(doc, isNew) {
      this.$emit(doc, {
        id: `${doc.doc_id}-${doc.status}`,
        summary: `${isNew
          ? "New"
          : "Changed"
        } - ${doc.doc_id}`,
        ts: Date.now(),
      });
    },
  },
  async run() {
    const documents = await this.listAllDocuments();
    const changedDocuments = [];
    const newDocuments = [];
    const documentsMappedByDocId = this.getDocumentsMappedByDocId(documents);
    const prevDocumentsStatusMap = this.getDocuments();

    // Iterate over documentsStatusMap map
    for (const [
      docId,
      doc,
    ] of Object.entries(documentsMappedByDocId)) {
      // If document is new
      if (!prevDocumentsStatusMap[docId]) {
        newDocuments.push(doc);
      }

      // If document status has changed
      else if (prevDocumentsStatusMap[docId] !== doc.status) {
        changedDocuments.push(doc);
      }
    }

    this.setDocuments(this.getDocumentsStatusMap(documents));
    for (const doc of changedDocuments) {
      this.emitEvent(doc, false);
    }
    for (const doc of newDocuments) {
      this.emitEvent(doc, true);
    }
  },
};

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
Docsumo	`app`	`app`	This component uses the Docsumo app.
	`timer`	`$.interface.timer`
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.

Trigger Authentication#

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

About Docsumo#

Make fast & accurate decisions from unstructured documents. Document AI software that converts unstructured documents to actionable data.

Action#

Create Image on Azure OpenAI Service

Description:Creates an image given a prompt, and returns a URL to the image. [See the documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#image-generation)

Version:0.0.1

Key:azure_openai_service-create-image

View on GitHub

Azure OpenAI Service Overview#

The Azure OpenAI Service API provides access to powerful AI models that can understand and generate human-like text. With Pipedream, you can harness this capability to create a variety of serverless workflows, automating tasks like content creation, code generation, and language translation. By integrating the API with other apps on Pipedream, you can streamline processes, analyze sentiment, and even automate customer support.

Action Code#

import azureOpenAI from "../../azure_openai_service.app.mjs";
import constants from "../common/constants.mjs";
const delay = (ms) => new Promise((res) => setTimeout(res, ms));

export default {
  key: "azure_openai_service-create-image",
  name: "Create Image",
  description: "Creates an image given a prompt, and returns a URL to the image. [See the documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#image-generation)",
  version: "0.0.1",
  type: "action",
  props: {
    azureOpenAI,
    prompt: {
      label: "Prompt",
      description: "A text description of the desired image(s). The maximum length is 1000 characters.",
      type: "string",
    },
    n: {
      label: "N",
      description: "The number of images to generate. Must be between 1 and 10.",
      type: "integer",
      optional: true,
      default: 1,
    },
    size: {
      label: "Size",
      description: "The size of the generated images.",
      type: "string",
      optional: true,
      options: constants.IMAGE_SIZES,
      default: "1024x1024",
    },
  },
  async run({ $ }) {
    const { id: operationId } = await this.azureOpenAI.createImage({
      data: {
        prompt: this.prompt,
        n: this.n,
        size: this.size,
      },
      $,
    });

    let response;
    do {
      response = await this.azureOpenAI.getImageResult({
        operationId,
        $,
      });
      if (response?.status === "succeeded") {
        break;
      }
      await delay(5000);
    } while (true);

    if (response.id) {
      $.export("$summary", `Successfully created image with ID ${response.id}.`);
    }

    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
Azure OpenAI Service	`azureOpenAI`	`app`	This component uses the Azure OpenAI Service app.
Prompt	`prompt`	`string`	A text description of the desired image(s). The maximum length is 1000 characters.
N	`n`	`integer`	The number of images to generate. Must be between 1 and 10.
Size	`size`	`string`	Select a value from the drop down menu:`256x256512x5121024x1024`

Action Authentication#

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

Before you start, you'll need to deploy a model in the Azure OpenAI Service.

Once that's done, enter the name of your Azure OpenAI resource, the deployment name you chose when you deployed the model, and your Azure OpenAI key below.