What do you want to automate

with Weaviate and Google Cloud Document AI?

import { axios } from "@pipedream/platform"
export default defineComponent({
  props: {
    weaviate: {
      type: "app",
      app: "weaviate",
    }
  },
  async run({steps, $}) {
    return await axios($, {
      url: `https://${this.weaviate.$auth.cluster_url}/v1/schema`,
      headers: {
        Authorization: `Bearer ${this.weaviate.$auth.api_key}`,
      },
    })
  },
})

import { DocumentProcessorServiceClient } from '@google-cloud/documentai/build/src/v1/index.js';
import { promises as fs } from 'fs';
import { get } from 'https';
import { writeFile } from 'fs/promises';
import { join } from 'path';

export default defineComponent({
  props: {
    google_cloud_document_ai: {
      type: "app",
      app: "google_cloud_document_ai",
    }
  },
  async run({ steps, $ }) {
    //Sample pdf file to process by Google Document AI API
    const url = 'https://www.learningcontainer.com/wp-content/uploads/2019/09/sample-pdf-file.pdf';
    const filePath = join('/tmp', 'my_document.pdf');

    const downloadFile = async () => {
      const res = await new Promise((resolve) => get(url, resolve));
      const chunks = [];

      for await (const chunk of res) {
        chunks.push(chunk);
      }

      await writeFile(filePath, Buffer.concat(chunks));
      console.log(`File downloaded successfully to ${filePath}`);
    };

    await downloadFile();

    const projectId = this.google_cloud_document_ai.$auth.project_id;
    const location = this.google_cloud_document_ai.$auth.location;
    const processorId = this.google_cloud_document_ai.$auth.processor_id;

    // Instantiates a client
    // apiEndpoint regions available: eu-documentai.googleapis.com, us-documentai.googleapis.com (Required if using eu based processor)
    // const client = new DocumentProcessorServiceClient({apiEndpoint: 'eu-documentai.googleapis.com'});
    const client = new DocumentProcessorServiceClient();

    async function testRequest() {
      // The full resource name of the processor, e.g.:
      // projects/project-id/locations/location/processor/processor-id
      // You must create new processors in the Cloud Console first
      const name = `projects/${projectId}/locations/${location}/processors/${processorId}`;

      // Read the file into memory.		
      const imageFile = await fs.readFile(filePath);

      // Convert the image data to a Buffer and base64 encode it.
      const encodedImage = Buffer.from(imageFile).toString('base64');

      const request = {
        name,
        rawDocument: {
          content: encodedImage,
          mimeType: 'application/pdf',
        },
      };

      // Recognizes text entities in the PDF document
      const [result] = await client.processDocument(request);
      const { document } = result;

      // Get all of the document text as one big string
      const { text } = document;

      // Extract shards from the text field
      const getText = textAnchor => {
        if (!textAnchor.textSegments || textAnchor.textSegments.length === 0) {
          return '';
        }

        // First shard in document doesn't have startIndex property
        const startIndex = textAnchor.textSegments[0].startIndex || 0;
        const endIndex = textAnchor.textSegments[0].endIndex;

        return text.substring(startIndex, endIndex);
      };

      // Read the text recognition output from the processor
      const [page1] = document.pages;
      const { paragraphs } = page1;
      let concatenatedText = "";
      for (const paragraph of paragraphs) {
        const paragraphText = getText(paragraph.layout.textAnchor);
        concatenatedText += paragraphText;
      }
      return concatenatedText;
    }

    return await testRequest();
  }
})