PDF to Markdown chunks for RAG, with page citations

Created by

Rigel

Actor

PDF to Markdown for RAG & LLMs: OCR, DOCX, Excel

Splits a PDF into RAG-ready chunks: text, pageStart, pageEnd and headingPath for every chunk, so your vector store can cite the page. Example: pages 1-8 of the NIST Cybersecurity Framework 2.0 (public domain), 15 chunks of up to 1,500 characters. Replace the URL with your own PDF. About $0.0044 for this example: $0.002 per document plus $0.0003 per page.

Try for free

PDF to Markdown for RAG & LLMs: OCR, DOCX, Excelrigel/doc-to-markdown

File name

Status

Page count

Pages processed

+2 fields

Input

Document URLs

url:https://nvlpubs.nist.gov/nistpubs/CSWP/NIST.CSWP.29.pdf

Output:chunks

Chunk size:1500

Chunk overlap:150

Pages:1-8

Output fields

File name

Status

Page count

Pages processed

Error code

Error

How it works

Sign up on Apify or log in

The PDF to Markdown for RAG & LLMs: OCR, DOCX, Excel Actor is ready to run with the inputs already set for "PDF to Markdown chunks for RAG, with page citations". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "PDF to Markdown chunks for RAG, with page citations" task

The PDF to Markdown for RAG & LLMs: OCR, DOCX, Excel Actor will start running based on the input automatically. You can also change all the input fields, like document urls, output, and more, to match your specific use case.

Receive the "PDF to Markdown chunks for RAG, with page citations" 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 file name, status, page count, 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 "PDF to Markdown chunks for RAG, with page citations" task via API.