You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
48 lines
1.4 KiB
48 lines
1.4 KiB
const { v4 } = require("uuid");
|
|
const { tokenizeString } = require("../../utils/tokenizer");
|
|
const {
|
|
createdDate,
|
|
trashFile,
|
|
writeToServerDocuments,
|
|
} = require("../../utils/files");
|
|
const OCRLoader = require("../../utils/OCRLoader");
|
|
const { default: slugify } = require("slugify");
|
|
|
|
async function asImage({ fullFilePath = "", filename = "" }) {
|
|
let content = await new OCRLoader().ocrImage(fullFilePath);
|
|
|
|
if (!content?.length) {
|
|
console.error(`Resulting text content was empty for ${filename}.`);
|
|
trashFile(fullFilePath);
|
|
return {
|
|
success: false,
|
|
reason: `No text content found in ${filename}.`,
|
|
documents: [],
|
|
};
|
|
}
|
|
|
|
console.log(`-- Working ${filename} --`);
|
|
const data = {
|
|
id: v4(),
|
|
url: "file://" + fullFilePath,
|
|
title: filename,
|
|
docAuthor: "Unknown", // TODO: Find a better author
|
|
description: "Unknown", // TODO: Find a better description
|
|
docSource: "a text file uploaded by the user.",
|
|
chunkSource: "",
|
|
published: createdDate(fullFilePath),
|
|
wordCount: content.split(" ").length,
|
|
pageContent: content,
|
|
token_count_estimate: tokenizeString(content),
|
|
};
|
|
|
|
const document = writeToServerDocuments(
|
|
data,
|
|
`${slugify(filename)}-${data.id}`
|
|
);
|
|
trashFile(fullFilePath);
|
|
console.log(`[SUCCESS]: ${filename} converted & ready for embedding.\n`);
|
|
return { success: true, reason: null, documents: [document] };
|
|
}
|
|
|
|
module.exports = asImage;
|