Failing to use parse for odt/docx but pdf is fine

[jsmusgrave]

Having trouble with parse opening non-pdf files. Sample code below. (In my production code, I would be using a file from a bucket, so not a local file, but same result.)

import { LlamaParseReader } from "llamaindex";
import { ParserLanguages } from "@llamaindex/cloud/api/dist";
import fs from "fs";

type LlamaParseReaderParams = Partial<Omit<LlamaParseReader, "language" | "apiKey">>  & {
    language?: ParserLanguages | ParserLanguages[] | undefined;
    apiKey?: string | undefined;
}

async function main() {
    const path = "/tmp/somedoc.pdf"
    if (!fs.existsSync(path)) {
        console.error(`File ${path} does not exist`);
        process.exit(1);
    } else {
        console.log(`File ${path} exists`);
    }

    const apiKey = process.env.LLAMAINDEX_KEY;
    const params : LlamaParseReaderParams = { 
        verbose: true,
        parsingInstruction: "Extract the text from the document a long with any images and tables.  This is a document for a course and the contents of the images are important.",
        fastMode: false,
        gpt4oMode: true,
        useVendorMultimodalModel: true,
        vendorMultimodalModelName: "anthropic-sonnet-3.5",
        // vendorMultimodalApiKey?: string | undefined;
        premiumMode: true,
        resultType: "markdown", 
        apiKey: apiKey,
        doNotCache: true,
    };

    // set up the llamaparse reader
    const reader = new LlamaParseReader(params);

    const buffer = fs.readFileSync(path);
    const documents = await reader.loadDataAsContent(new Uint8Array(buffer));

    let allText = "";
    documents.forEach(doc => {
        allText += doc.text;
    });

    console.log(allText);
  } 
  main().catch(console.error);

llamaindex v 0.6.20
node version v20.10.0

[jsmusgrave]

On digging in, it appears the mime-type parsing may be busted... but that appears that is being worked on...

[jsmusgrave]

Ah, ha! There already is an issue for this! 🤦
#1313

[jsmusgrave]

Nope. That didn't fix it.