Go to example tasks

Convert a research paper PDF to Markdown with RAG chunks

Turn a two-column academic PDF into clean Markdown with headings and paragraphs in reading order, split into heading-aware chunks ready for a vector database.

Try for free
PDF & DOCX to Markdown for AI and RAG
PDF & DOCX to Markdown for AI and RAGpraised_tumbler/pdf-docx-to-markdown
Source
Status
Format
Title
+6 fields
Text
Number
Boolean
List
Object

Input

Document URLs:https://raw.githubusercontent.com/mozilla/pdf.js/master/web/compressed.tracemonkey-pldi-09.pdf
RAG chunk size (tokens):500
Chunk overlap (tokens):50
Return Markdown per page (PDF):false

Output fields

Source
Status
Format
Title
Pages
Words
Billed pages
Warnings
Error
Markdown

How it works

Sign up on Apify or log in

The PDF & DOCX to Markdown for AI and RAG Actor is ready to run with the inputs already set for "Convert a research paper PDF to Markdown with RAG chunks". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Convert a research paper PDF to Markdown with RAG chunks" task

The PDF & DOCX to Markdown for AI and RAG Actor will start running based on the input automatically. You can also change all the input fields, like document urls, RAG chunk size (tokens), and more, to match your specific use case.

Receive the "Convert a research paper PDF to Markdown with RAG chunks" 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 source, status, format, 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 "Convert a research paper PDF to Markdown with RAG chunks" task via API.

Image

Integrate "Convert a research paper PDF to Markdown with RAG chunks" into your workflow

Connect "Convert a research paper PDF to Markdown with RAG chunks" with 100+ integrations, or run it via API or MCP.

Webhook

Webhook

n8n

n8n

Make

Make

Zapier

Zapier

Airbyte

Airbyte

Keboola

Keboola

IFTTT

IFTTT

Hubspot

Hubspot

GDrive

GDrive

Gmail

Gmail

Apify MCP

Apify MCP

GitHub

GitHub

Slack

Slack

LangChain

LangChain

LlamaIndex

LlamaIndex

Flowise

Flowise

Pinecone

Pinecone

OpenAI

OpenAI

Mastra

Mastra

Clay

Clay

Frequently asked questions

Yes. Columns are detected from the page layout and read left then right, with full-width titles kept in place.

Pages without a text layer are read with OCR that runs inside the Actor. Choose the OCR language in the input.

No. The conversion runs inside the Actor without any external API.