PDF, Word, PowerPoint & Excel to Markdown for LLM and RAG

Turn documents into clean Markdown your AI pipeline can use. Give it links to PDF, DOCX, PPTX, XLSX, HTML, CSV or text files and get one row per document with its Markdown, page and table counts, and optional chunks ready for embedding.

Paste a few document links and press Start.

What people use it for

• RAG and AI agents: feed documents into a vector store or an LLM as Markdown instead of messy raw text.
• Search and knowledge bases: convert a folder of reports, decks and spreadsheets into one format.
• Data teams: pull the text and the ruled tables out of PDFs without opening them.

What it handles

File	How it converts
PDF	Text page by page. Tables drawn with ruling lines become Markdown tables.
Word (DOCX)	Headings, paragraphs, lists and tables.
PowerPoint (PPTX)	Slide titles and text, in slide order.
Excel (XLSX)	Each sheet as a Markdown table.
HTML, CSV, text	Cleaned to Markdown.

What it does not do

• It does not read scanned pages. A page that is only an image has no text layer, so it comes back empty and is listed in pagesWithoutText.
• Tables drawn without lines in a PDF come through as aligned text, not as a Markdown table.
• PDF headings are not detected, so PDF text comes back as paragraphs.
• Password-protected files are not supported.

Input

Field	What it does
Document URLs	Direct links to the files. Sites whose robots.txt disallows automated access are skipped.
Add RAG chunks	Also returns the Markdown split into chunks at paragraph boundaries.
Chunk size and Chunk overlap	Characters per chunk and how much carries over.
Mark PDF page breaks	Puts a <!-- page N --> comment before each PDF page.
Max PDF pages per document	A cap on pages converted, and so on cost.
Max file size (MB)	Larger files are skipped.

Output

One item per converted document:

{
  "url": "https://www.irs.gov/pub/irs-pdf/fw9.pdf",
  "fileName": "fw9.pdf",
  "fileType": "pdf",
  "title": "Form W-9 (Rev. March 2024)",
  "pageCount": 6,
  "pagesConverted": 6,
  "pagesWithoutText": [],
  "tableCount": 1,
  "charCount": 37929,
  "wordCount": 6311,
  "markdown": "Form W-9 Request for Taxpayer Identification Number and Certification ...",
  "chunks": [{ "index": 0, "text": "..." }]
}

The example values are illustrative. Files that could not be converted are not charged and are listed with the reason in the run's SUMMARY record.

Privacy

Your files are fetched only for your run and converted in memory. Nothing is kept outside your own run's storage.

FAQ

How do I convert a PDF to Markdown for an LLM or RAG? Paste the PDF link into Document URLs and press Start. Turn on Add RAG chunks to also get the text split into overlapping chunks ready to embed in a vector store.

Does it keep tables? Tables in Word and Excel files, and PDF tables drawn with ruling lines, come back as Markdown tables. PDF tables without lines come through as aligned text.

Can it convert scanned PDFs? No. It does not run OCR, so a page that is only an image comes back empty and is listed in pagesWithoutText.

Can I convert Word, PowerPoint and Excel files too? Yes. DOCX, PPTX, XLSX, HTML, CSV and text files all convert to Markdown in the same run.

Can I call it from an API or an AI agent? Yes. Like any Apify Actor it runs from the Apify API, the Python and JavaScript clients, or an integration, and returns one row per document.

Pricing

You pay per document converted, plus a small charge per PDF page. Word, PowerPoint, Excel and HTML files have no page charge. The prices are on the Pricing tab. Max PDF pages per document caps what one document can cost.

Feedback

Need another file type or a fix? Open an issue on the Issues tab.