anything-llm/collector/processSingleFile/convert/asPDF.js

const { v4 } = require("uuid");
const { PDFLoader } = require("langchain/document_loaders/fs/pdf");
const {
  createdDate,
  trashFile,
  writeToServerDocuments,
} = require("../../utils/files");
const { tokenizeString } = require("../../utils/tokenizer");
const { default: slugify } = require("slugify");

async function asPDF({ fullFilePath = "", filename = "" }) {
  const pdfLoader = new PDFLoader(fullFilePath, {
    splitPages: true,
  });

  console.log(`-- Working ${filename} --`);
  const pageContent = [];
  const docs = await pdfLoader.load();
  for (const doc of docs) {
    console.log(
      `-- Parsing content from pg ${
        doc.metadata?.loc?.pageNumber || "unknown"
      } --`
    );
    if (!doc.pageContent.length) continue;
    pageContent.push(doc.pageContent);
  }

  if (!pageContent.length) {
    console.error(`Resulting text content was empty for ${filename}.`);
    trashFile(fullFilePath);
    return { success: false, reason: `No text content found in ${filename}.` };
  }

  const content = pageContent.join("");
  const data = {
    id: v4(),
    url: "file://" + fullFilePath,
    title: docs[0]?.metadata?.pdf?.info?.Title || filename,
    docAuthor: docs[0]?.metadata?.pdf?.info?.Creator || "no author found",
    description: "No description found.",
    docSource: "pdf file uploaded by the user.",
    chunkSource: filename,
    published: createdDate(fullFilePath),
    wordCount: content.split(" ").length,
    pageContent: content,
    token_count_estimate: tokenizeString(content).length,
  };

  writeToServerDocuments(data, `${slugify(filename)}-${data.id}`);
  trashFile(fullFilePath);
  console.log(`[SUCCESS]: ${filename} converted & ready for embedding.\n`);
  return { success: true, reason: null };
}

module.exports = asPDF;