Pricing

from $3.00 / 1,000 converted pages

Try for free

Go to Apify Store

PDF to Markdown & JSON for RAG (OCR, DOCX, PPTX, XLSX)

Try for free

Convert PDF, DOCX, PPTX, XLSX and HTML into clean Markdown and JSON for AI and RAG pipelines. Fast mode is cheap and near-instant; accurate mode adds full layout and table analysis. OCR for scanned PDFs, tables as Markdown/HTML/JSON, page or token chunking with token counts.

Pricing

from $3.00 / 1,000 converted pages

Rating

0.0

(0)

Developer

Maximillian Ruddy

Actor stats

Bookmarked

Total users

Monthly active users

21 hours ago

Last modified

Categories

Document URLs

sources

Required

URLs of documents to convert. Supported: PDF (text or scanned), DOCX, PPTX, XLSX, HTML.

Type:array

Conversion mode

mode

Optional

fast (default): pypdfium2 text extraction + pdfplumber tables + RapidOCR for scanned pages only. About as fast as reading the file (roughly 0.3-1s/page on a normal text PDF), priced near the market rate, and good enough for most RAG/LLM use. Docling's ML models never load. accurate: full docling layout analysis + TableFormer table-structure recognition. Much slower (roughly 15-70s/page on a 4 GB/1 vCPU worker) and priced higher (accurate-page + table charges), but reconstructs reading order, headings and complex table structure more faithfully - worth it for dense forms, multi-column layouts, or tables you need pixel-accurate. DOCX/PPTX/XLSX/HTML always use docling's fast native (non-ML) backends in both modes. Memory: fast mode runs fine at the default 2048 MB. Accurate mode needs 4096 MB; set it in the run options, or the run stops before charging anything.

Type:string

Default:fast

Options:

fastaccurate

Output format

outputFormat

Optional

Which fields to fill on each dataset item.

Type:string

Default:both

Options:

markdownjsonboth

Chunking strategy

chunking

Optional

How to split each document's text into the chunks output field.

Type:string

Default:none

Options:

nonepagetokens

Tokens per chunk

chunkTokens

Optional

Target chunk size in tokens, used only when chunking = "tokens".

Type:integer

Minimum:50

Maximum:8000

Default:800

OCR mode

ocr

Optional

auto: OCR only pages with little or no extractable text (scanned pages). off: never OCR. force: OCR every PDF page.

Type:string

Default:auto

Options:

autooffforce

Table format

tableFormat

Optional

Encoding used for each entry in the structured tables output field. The Markdown body always renders tables as Markdown for readability.

Type:string

Default:markdown

Options:

markdownhtmljson

Max pages per document

maxPagesPerDocument

Optional

Spend guard: stop converting a single document after this many pages. Extra pages are skipped, not charged.

Type:integer

Minimum:1

Maximum:2000

Default:50

Document Parser — PDF/DOCX to Markdown & JSON for RAG

genuine_qa/document-parser

Convert PDF, DOCX, PPTX, XLSX, HTML and images into clean Markdown or JSON for RAG and LLM pipelines. Powered by IBM's open-source Docling.

Rahul Bhiwagade

PDF to Markdown Extractor & Document Parser: Tables, JSON, OCR

fguiraud/document-to-markdown-tables

Extract text and tables from PDF, Word, Excel, PowerPoint, HTML and scanned images. Returns LLM-ready Markdown, tables as JSON/CSV, RAG chunks and metadata. OCR for scanned PDFs, optional AI field extraction (invoices, forms). No API key; pay per document.

Fernando Guiraud

Doc-to-Markdown/JSON RAG Prep - Convert PDF & DOCX for RAG

bigjoecoding/doc-to-markdown-json-rag-prep

Convert PDF, DOCX, PPTX and webpages to clean Markdown and RAG-ready JSON chunks for your embedding pipeline. No LLM cost. $0.03 per document.

Joseph Curry

PDF & DOCX to Markdown — Document Extractor for LLM/RAG

fetchbase/document-to-markdown

Convert PDF and Word (DOCX) documents into clean Markdown, text, or JSON. Smart PDF paragraph reflow, page markers for RAG citations, full DOCX structure (headings, lists, tables), custom auth headers. No browser — parses in seconds. Charged per page processed — no startup fee.

Fetchbase

PDF to Markdown & JSON (RAG-Ready)

basisweb/pdf-to-markdown-rag

Convert PDFs to clean Markdown and structured JSON (text + tables) for RAG, LLMs, and vector DBs. Batch URLs, pay per page.

BasisWeb

PDF to Markdown Converter: Docling Parser for AI & RAG

raional/pdf-to-markdown-converter

Convert PDF, DOCX, PPTX, XLSX, HTML and images to clean Markdown and structured JSON using IBM's open-source Docling library. Preserves headings, tables, and page structure. RAG-ready chunked output mode for LLM pipelines.

Raion Al

PDF Extractor: PDF → Clean Markdown + JSON for LLM/RAG

boxbox10/pdf-extractor

Turn any PDF URL into clean, LLM-ready Markdown + structured JSON (title, metadata, per-page text, page count, word count, token count). Perfect for RAG pipelines, AI agents, and LLM document ingestion.

Marvin Eguilos

Document Structure Extractor — Markdown to JSON outline

shoebill-dev27/doc-structure-extractor

Turn Markdown documents into structured JSON: nested heading tree with section text, fenced code blocks, links, parsed tables, and size statistics. Pure parsing, no LLM cost.

Shinobu Otani

PDF to Markdown & JSON for LLMs/RAG

wmora/pdf-to-markdown

Deterministic, non-AI extraction of native-text PDFs into per-page Markdown and structured JSON (headings, paragraphs, tables) for LLM ingestion.

Will M

PDF to Markdown & JSON Converter (Docling)

actorzlab/docling-pdf-converter

Convert PDF documents to clean Markdown, structured JSON, and plain text using IBM's open-source Docling AI. Handles text PDFs and scanned documents (OCR), extracts tables and images. No external API key required — runs fully on-device.