PDF to Markdown: DOCX, PPTX, XLSX, OCR & RAG Chunks
Pricing
from $5.00 / 1,000 document processeds
Convert PDF, DOCX, PPTX, XLSX, and HTML to clean Markdown that preserves tables and headings. Optional Tesseract OCR for scanned pages and heading-aware RAG chunks with source, page, and section metadata.
HTTP(S) links to PDF, DOCX, PPTX, XLSX, or HTML documents. HTML pages are cleaned with a readability pass before Markdown conversion. One bad URL does not fail the run.
[ { "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf" }]Upload PDF, Word, PowerPoint, Excel, or HTML files. The Console stores each file in a key-value store and passes the record URL to the Actor.
Read documents already stored in an Apify key-value store. Combine with keys below, or leave keys empty to convert every supported record.
Specific record keys to convert (for example report.pdf). Leave empty to convert every PDF/DOCX/PPTX/XLSX/HTML record in the store.
Auto (recommended) and Fast use MarkItDown for office/HTML and PyMuPDF for born-digital PDFs. Accurate uses Docling layout + table reconstruction when Docling is installed in the image; this Store build does not include Docling, so Accurate falls back to Fast and still returns Markdown.
Write each successful conversion as a .md record (document--.md) in the default key-value store, in addition to the dataset row.
Run Tesseract on PDF pages (or images) that have no usable text layer. Leave off for born-digital PDFs — it is the slowest and most expensive option. Uses the system Tesseract binary, not a cloud OCR API.
Tesseract language. This build ships English only (eng). Other codes are not available.
Split the Markdown into overlapping chunks for embeddings / vector stores. Each chunk keeps source, page, and section (heading path) metadata.
Target characters per chunk. 800–1500 works well for most embedding models. Tables larger than this stay in one chunk so rows are not split.
Characters copied from the end of the previous chunk onto the next one so sentences are not cut off at the boundary.
Start a new chunk when the heading path changes (for example ## Revenue → ### Q3) and attach the heading path as section metadata.
Useful for Zapier / Make / RAG loaders that expect one dataset item per chunk. The parent document row is still written.
Skip (do not fail the run) any file larger than this. Keeps memory and download time predictable.
Only the first N PDF pages (or PPTX slides / XLSX sheets) are converted. Extra pages are billed after the first 10 on successful documents.
Give up on a single document after this many seconds and move on.