doc2markdown.
Home

Source documents → knowledge base

Prepare documents for your knowledge base

Convert PDF and Word, review layout cleanup and export separate Markdown documents with source information and images.

PDF / Word → Markdown

Drag and drop files here, or click to select files

Supported formats: *.pdf, *.doc, *.docx, *.rtf, *.odt (Max: 1 files, 20MB each)

Select Files

Conversion settings

Processing method

From source files to reviewed documents

  1. 01

    Convert source files

    Upload PDF or Word individually or use the batch tab for up to five files. Choose a conversion mode suited to the source.

  2. 02

    Review each document

    Open the knowledge preparation tool. Edit names and sources, compare optional cleanup with the original and undo changes if needed.

  3. 03

    Export and import

    Download a ZIP with independent Markdown documents, local images and a source manifest, then import the reviewed files into your knowledge base.

A complete sample

Inspect the input and the finished package

These synthetic PDF and Word files let you try the workflow and inspect actual Markdown, source metadata and images.

Word sourcePDF sourceFinished document ZIP
documents/
  01-Operations guide/
    document.md
    assets/
  02-Travel policy/
    document.md
manifest.json
README.md

Import the document package

This package contains full Markdown documents. Your knowledge platform handles chunking, indexing and retrieval.

  1. 01Unzip the package. Import only the document.md files inside documents/ as knowledge content.
  2. 02Keep each document's assets/ folder for viewing images. Image ingestion depends on the platform you use.
  3. 03Keep manifest.json and README.md outside the imported content. Check source pages and partial results before indexing.