Pricing

Pay per event

Try for free

Go to Apify Store

PDF Text Extractor & Markdown for LLM RAG: OCR, Tables, Chunks

Try for free

Convert PDF to clean Markdown for LLM & RAG pipelines: text extractor with OCR fallback (50 languages), GitHub-flavored table reconstruction (incl. tables spanning pages), right-to-left script support, and optional RAG chunking. ~$0.005 for a 20-page text PDF. Pay only for pages with real text.

Pricing

Pay per event

Rating

0.0

(0)

Developer

Pankovs

Actor stats

Bookmarked

Total users

Monthly active users

2 days ago

Last modified

Categories

Developer tools

PDF URLs

pdfs

Optional

http(s) URLs of PDF files to convert. At least one URL is required unless a file is uploaded via pdfFile.

Type:string[]

Default:

[]

Upload a PDF (optional)

pdfFile

Optional

Upload a single PDF from your computer via the Apify Console. Processed in addition to any URLs in pdfs.

Type:string

OCR mode

ocrMode

Optional

auto: OCR only pages with too little extractable text. always: OCR every page. never: text layer only.

Type:string

Default:auto

Options:

autoalwaysnever

OCR languages

ocrLanguages

Optional

Tesseract language codes for scanned pages, joined with '+', e.g. eng+deu (up to 5). 50 languages: eng (English), rus (Russian), deu (German), fra (French), spa (Spanish), por (Portuguese), ita (Italian), pol (Polish), lav (Latvian), ukr (Ukrainian), nld (Dutch), swe (Swedish), dan (Danish), nor (Norwegian), fin (Finnish), ces (Czech), slk (Slovak), hun (Hungarian), ron (Romanian), tur (Turkish), ell (Greek), ara (Arabic), heb (Hebrew), fas (Persian), urd (Urdu), hin (Hindi), ben (Bengali), tam (Tamil), tel (Telugu), mar (Marathi), tha (Thai), vie (Vietnamese), ind (Indonesian), msa (Malay), chi_sim (Chinese (Simplified)), chi_tra (Chinese (Traditional)), jpn (Japanese), kor (Korean), bul (Bulgarian), srp (Serbian (Cyrillic)), hrv (Croatian), slv (Slovenian), lit (Lithuanian), est (Estonian), cat (Catalan), glg (Galician), eus (Basque), afr (Afrikaans), swa (Swahili), fil (Filipino). All are built in. Pick only the languages present in your scans: each extra language makes OCR slower. If OCR confidence is low, the page's script is detected automatically (Latin, Cyrillic, Greek, Arabic, Hebrew, Devanagari, Bengali, Tamil, Telugu, Thai, Chinese, Japanese, Korean) and the page is re-read with that script's language added. Pages OCR'd with low confidence (below 60%) are flagged in warnings and not charged.

Type:string

Default:eng

Max pages per PDF

maxPagesPerPdf

Optional

Stop processing a PDF after this many pages.

Type:integer

Minimum:1

Default:200

Extract tables

extractTables

Optional

Rebuild tables from the text layer as GitHub-flavored Markdown tables (| cell | cell |), kept whole in RAG chunks. Low-confidence layouts stay plain text. Not applied to OCR pages.

Type:boolean

Default:true

Output RAG chunks

outputChunks

Optional

Also split the Markdown into overlapping chunks for retrieval-augmented generation.

Type:boolean

Default:false

Chunk size (characters)

chunkSize

Optional

Target chunk length in characters, used when outputChunks is enabled.

Type:integer

Minimum:100

Default:2000

Chunk overlap (characters)

chunkOverlap

Optional

Number of characters each chunk overlaps with the previous one. At most half of chunkSize: a larger value is reduced to chunkSize / 2 and the item gets a warning.

Type:integer

Minimum:0

Default:200

Include page markers

includePageMarkers

Optional

Insert an HTML comment marker before each page's Markdown, e.g. .

Type:boolean

Default:false

Website Content Crawler - Clean Text, Markdown & RAG Chunks

topapi/website-content-crawler

Crawl any website or URL list for $1.20 per 1,000 pages: one row per page with clean text, Markdown, HTML, metadata, links, headings, tables and RAG chunks. Plain HTTP first, headless Chrome only for JavaScript pages. Sitemaps, llms.txt, PDF/DOCX text, Bing/DuckDuckGo search, change monitor.

Top Api

PDF Text Extractor & Document Parser: DOCX, XLSX, OCR, Markdown

yabanana99/pdf-word-excel-to-markdown

Parse Word, PowerPoint, Excel and PDF documents into clean Markdown and structured JSON: tables extracted cell-by-cell, document metadata, and RAG-ready chunks with heading paths. Built-in OCR for scans and images.

Daniele Giovane

PDF to Text API | Document Extraction for LLMs & RAG

andok/pdf-text-converter

Convert bulk PDF documents via URL into clean, raw text. The perfect document scraper for LLMs, vector databases, and RAG pipelines.

Andok

PDF Text Extractor

jirimoravcik/pdf-text-extractor

PDF Text Extractor allows you to extract text from PDF files. It also supports chunking of the text to prepare the data for usage with large language models.

Jiří Moravčík

1.1K

PDF Text Extractor — Markdown, Tables, OCR & RAG Chunks

nanare-sudo/pdf-text-extractor-rag

Extract text, GFM Markdown, tables (2D arrays + CSV) and heading-aware RAG chunks with page anchors from PDFs. URLs, base64 upload, key-value store, password-protected PDFs, page ranges, OCR fallback (eng/deu/fra/spa) only for pages without a text layer. Failed PDFs are never charged.

Leonardo Berisha

Website & PDF to RAG JSONL Crawler

orbiscribe/linked-pdf-website-rag-crawler

Paste webpage and PDF URLs and get Markdown, JSONL chunks, PDF inventory, source warnings, and RAG-ready records.

Orbiscribe Labs

PDF Text Extractor - Multi-Column Layout, OCR & Metadata

webdata_labs/pdf-text-extractor

[💵 $0.005 per PDF + $0.0004 per page · no start fee] Any PDF URL into clean, layout-aware text that reads multi-column pages in the right order. Whole document and page by page, plus metadata, bookmarks and links. Optional OCR reads scanned pages, billed only for the pages it reads.

WebData Labs

Markdown Maker: HTML to Markdown 📝

shahidirfan/Markdown-Maker

Instantly convert complex HTML into clean, structured Markdown. This lightweight actor is optimized to render web content into a format that is easily readable for AI LLMs, reducing token usage and improving context. Perfect for RAG pipelines and preparing data for training.

Shahid Irfan

5.0

(1)

PDF & Image to Text (OCR) — Scanned PDFs, Photos, Screenshots

tidydata/pdf-image-text-extractor

Extract text from PDFs and images by URL. Exact text from digital PDFs, automatic OCR (Tesseract) for scanned pages, photos and screenshots in 8 languages. Page-by-page output, ready for LLMs, search and RAG pipelines.

tidydata

PDF to Markdown for RAG & LLMs — Tables

vivid_astronaut/pdf-to-markdown-for-rag

Convert PDFs into structured Markdown for RAG and LLM ingestion while preserving tables, headings, and reading order. No external parsing API key; tiered per-page pricing.