smartai/test/test.document.openai.ts

import { expect, tap } from '@push.rocks/tapbundle';
import * as qenv from '@push.rocks/qenv';
import * as smartrequest from '@push.rocks/smartrequest';
import * as smartfile from '@push.rocks/smartfile';

const testQenv = new qenv.Qenv('./', './.nogit/');

import * as smartai from '../ts/index.js';

let testSmartai: smartai.SmartAi;

tap.test('OpenAI Document: should create a smartai instance with OpenAI provider', async () => {
  testSmartai = new smartai.SmartAi({
    openaiToken: await testQenv.getEnvVarOnDemand('OPENAI_TOKEN'),
  });
  await testSmartai.start();
});

tap.test('OpenAI Document: should document a pdf', async () => {
  const pdfUrl = 'https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf';
  const pdfResponse = await smartrequest.SmartRequest.create()
    .url(pdfUrl)
    .get();
  const result = await testSmartai.openaiProvider.document({
    systemMessage: 'Classify the document. Only the following answers are allowed: "invoice", "bank account statement", "contract", "other". The answer should only contain the keyword for machine use.',
    userMessage: "Classify the document.",
    messageHistory: [],
    pdfDocuments: [Buffer.from(await pdfResponse.arrayBuffer())],
  });
  console.log(result);
  expect(result.message).toBeTruthy();
});

tap.test('OpenAI Document: should recognize companies in a pdf', async () => {
  const pdfBuffer = await smartfile.fs.toBuffer('./.nogit/demo_without_textlayer.pdf');
  const result = await testSmartai.openaiProvider.document({
    systemMessage: `
      summarize the document.

      answer in JSON format, adhering to the following schema:
      \`\`\`typescript
        type TAnswer = {
          entitySender: {
            type: 'official state entity' | 'company' | 'person';
            name: string;
            address: string;
            city: string;
            country: string;
            EU: boolean; // whether the entity is within EU
          };
          entityReceiver: {
            type: 'official state entity' | 'company' | 'person';
            name: string;
            address: string;
            city: string;
            country: string;
            EU: boolean; // whether the entity is within EU
          };
          date: string; // the date of the document as YYYY-MM-DD
          title: string; // a short title, suitable for a filename
        }
      \`\`\`
    `,
    userMessage: "Classify the document.",
    messageHistory: [],
    pdfDocuments: [pdfBuffer],
  });
  console.log(result);
  expect(result.message).toBeTruthy();
});

tap.test('OpenAI Document: should stop the smartai instance', async () => {
  await testSmartai.stop();
});

export default tap.start();