Split PDFs into RAG chunks with page numbers

Created by

Salih Küçükkayış

Actor

Document to Markdown — PDF, Word, PowerPoint, Excel, OCR

Convert PDFs to Markdown and split them into ready-to-embed chunks for RAG. Each chunk keeps its page range and nearest heading for citations, and tables are never cut in half. $2 per 1,000 pages, chunking included.

Try for free

Document to Markdown — PDF, Word, PowerPoint, Excel, OCRsaliga/document-to-markdown

URL

File

Type

Title

+6 fields

Input

File URLs(required):https://raw.githubusercontent.com/microsoft/markitdown/main/packages/markitdown/tests/test_files/test.pdf+1

RAG chunk size (characters):1500

Chunk overlap (characters):200

Output fields

URL

File

Type

Title

Pages

OCR pages

Tables

Words

Markdown

Error

How it works

Sign up on Apify or log in

The Document to Markdown — PDF, Word, PowerPoint, Excel, OCR Actor is ready to run with the inputs already set for "Split PDFs into RAG chunks with page numbers". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Split PDFs into RAG chunks with page numbers" task

The Document to Markdown — PDF, Word, PowerPoint, Excel, OCR Actor will start running based on the input automatically. You can also change all the input fields, like file urls, RAG chunk size (characters), and more, to match your specific use case.

Receive the "Split PDFs into RAG chunks with page numbers" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as URL, file, type, and more.

Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Split PDFs into RAG chunks with page numbers" task via API.