WebPDFLoader

# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
<IntegrationInstallTooltip></IntegrationInstallTooltip>

<Npm2Yarn>
  @langchain/community @langchain/core pdf-parse
</Npm2Yarn>

import fs from "fs/promises";
import { WebPDFLoader } from "@langchain/community/document_loaders/web/pdf"

const nike10kPDFPath = "../../../../data/nke-10k-2023.pdf";

// Read the file as a buffer
const buffer = await fs.readFile(nike10kPDFPath);

// Create a Blob from the buffer
const nike10kPDFBlob = new Blob([buffer], { type: 'application/pdf' });

const loader = new WebPDFLoader(nike10kPDFBlob, {
  // required params = ...
  // optional params = ...
})

const docs = await loader.load()
docs[0]

Document {
  pageContent: 'Table of Contents\n' +
    'UNITED STATES\n' +
    'SECURITIES AND EXCHANGE COMMISSION\n' +
    'Washington, D.C. 20549\n' +
    'FORM 10-K\n' +
    '(Mark One)\n' +
    '☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934\n' +
    'FOR THE FISCAL YEAR ENDED MAY 31, 2023\n' +
    'OR\n' +
    '☐ TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934\n' +
    'FOR THE TRANSITION PERIOD FROM                         TO                         .\n' +
    'Commission File No. 1-10635\n' +
    'NIKE, Inc.\n' +
    '(Exact name of Registrant as specified in its charter)\n' +
    'Oregon93-0584541\n' +
    '(State or other jurisdiction of incorporation)(IRS Employer Identification No.)\n' +
    'One Bowerman Drive, Beaverton, Oregon 97005-6453\n' +
    '(Address of principal executive offices and zip code)\n' +
    '(503) 671-6453\n' +
    "(Registrant's telephone number, including area code)\n" +
    'SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:\n' +
    'Class B Common StockNKENew York Stock Exchange\n' +
    '(Title of each class)(Trading symbol)(Name of each exchange on which registered)\n' +
    'SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:\n' +
    'NONE\n' +
    'Indicate by check mark:YESNO\n' +
    '•if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act.þ ̈\n' +
    '•if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. ̈þ\n' +
    '•whether the registrant (1) has filed all reports required to be filed by Section 13 or 15(d) of the Securities Exchange Act of 1934 during the preceding\n' +
    '12 months (or for such shorter period that the registrant was required to file such reports), and (2) has been subject to such filing requirements for the\n' +
    'past 90 days.\n' +
    'þ ̈\n' +
    '•whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to Rule 405 of Regulation S-T\n' +
    '(§232.405 of this chapter) during the preceding 12 months (or for such shorter period that the registrant was required to submit such files).\n' +
    'þ ̈\n' +
    '•whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company or an emerging growth company. See the definitions of “large accelerated filer,”\n' +
    '“accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of the Exchange Act.\n' +
    'Large accelerated filerþAccelerated filer☐Non-accelerated filer☐Smaller reporting company☐Emerging growth company☐\n' +
    '•if an emerging growth company, if the registrant has elected not to use the extended transition period for complying with any new or revised financial\n' +
    'accounting standards provided pursuant to Section 13(a) of the Exchange Act.\n' +
    ' ̈\n' +
    "•whether the registrant has filed a report on and attestation to its management's assessment of the effectiveness of its internal control over financial\n" +
    'reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by the registered public accounting firm that prepared or issued its audit\n' +
    'report.\n' +
    'þ\n' +
    '•if securities are registered pursuant to Section 12(b) of the Act, whether the financial statements of the registrant included in the filing reflect the\n' +
    'correction of an error to previously issued financial statements.\n' +
    ' ̈\n' +
    '•whether any of those error corrections are restatements that required a recovery analysis of incentive-based compensation received by any of the\n' +
    "registrant's executive officers during the relevant recovery period pursuant to § 240.10D-1(b).\n" +
    ' ̈\n' +
    '•\n' +
    'whether the registrant is a shell company (as defined in Rule 12b-2 of the Act).☐þ\n' +
    "As of November 30, 2022, the aggregate market values of the Registrant's Common Stock held by non-affiliates were:\n" +
    'Class A$7,831,564,572 \n' +
    'Class B136,467,702,472 \n' +
    '$144,299,267,044 ',
  metadata: {
    pdf: {
      version: '1.10.100',
      info: [Object],
      metadata: null,
      totalPages: 107
    },
    loc: { pageNumber: 1 }
  },
  id: undefined
}

console.log(docs[0].metadata)

{
  pdf: {
    version: '1.10.100',
    info: {
      PDFFormatVersion: '1.4',
      IsAcroFormPresent: false,
      IsXFAPresent: false,
      Title: '0000320187-23-000039',
      Author: 'EDGAR Online, a division of Donnelley Financial Solutions',
      Subject: 'Form 10-K filed on 2023-07-20 for the period ending 2023-05-31',
      Keywords: '0000320187-23-000039; ; 10-K',
      Creator: 'EDGAR Filing HTML Converter',
      Producer: 'EDGRpdf Service w/ EO.Pdf 22.0.40.0',
      CreationDate: "D:20230720162200-04'00'",
      ModDate: "D:20230720162208-04'00'"
    },
    metadata: null,
    totalPages: 107
  },
  loc: { pageNumber: 1 }
}

<Npm2Yarn>
  pdfjs-dist
</Npm2Yarn>

import { WebPDFLoader } from "@langchain/community/document_loaders/web/pdf";

const blob = new Blob(); // e.g. from a file input

const customBuildLoader = new WebPDFLoader(blob, {
  // you may need to add `.then(m => m.default)` to the end of the import
  // @lc-ts-ignore
  pdfjs: () => import("pdfjs-dist/legacy/build/pdf.js"),
});

import { WebPDFLoader } from "@langchain/community/document_loaders/web/pdf";

// new Blob(); e.g. from a file input
const eliminatingExtraSpacesLoader = new WebPDFLoader(new Blob(), {
  parsedItemSeparator: "",
});