PDF Text Extractor & Markdown for LLM RAG: OCR, Tables, Chunks
Pricing
Pay per event
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.
All notable changes to PDF to Markdown for LLM & RAG. Sections: Added, Changed, Fixed.
document $0.00416 (was $0.0026) and text-page $0.000192 (was $0.00012), so a 20-page text PDF now costs $0.008 (was $0.005). ocr-page stays at $0.01. Runs also carry Apify's standard start event ($0.00005 per GB of memory), which lets Apify cover the first 5 seconds of every run.1 Introduction 3, 2 Approach 6) no longer turns into headings. Before, papers like GPT-3 got a second copy of every top level section title, with the page number stuck on, right at the start of the document.Input-Input Layer5 repeated over each attention chart in the appendix of "Attention Is All You Need") no longer become headings, and no longer get glued onto the real section title next to them. The appendix now starts with a clean Attention Visualizations heading, so chunksMeta headings cites the real section there.1 Introduction, 2.2 Architecture), are now Markdown headings. Before, only titles in a larger font were found, so a paper like the LLaMA paper got a single heading in 27 pages. Subsections are nested by their number (3.1 under 3, 3.2.1 under 3.2), so chunksMeta headings now gives the full section path, for example ["Attention Is All You Need", "3 Model Architecture", "3.2 Attention", "3.2.1 Scaled Dot-Product Attention"].ocrMode set to never, a page with no text layer (for example a scanned page) is now flagged in warnings (Page 1 has no extractable text and OCR was not run (ocrMode=never)...) instead of coming back as a silently empty page. The page is still free.chunksMeta list (one entry per chunk, same order) gives pageStart, pageEnd and headings, so answers can cite "page 4, section 3.2". The chunks list stays the same plain text list as before.pagesProcessed field: how many pages were actually converted.chunkSize characters: before a heading, at a paragraph or sentence end, or at least between words, within 15% of chunkSize. Words are no longer cut in half (...Long Bea / y over 2 BLEU), a heading is no longer left at the end of a chunk, and the overlap starts at the beginning of a word.metadata.created is always an ISO 8601 date in UTC when the PDF has a readable date, including old free-text dates like Tuesday, 21 September, 1999 5:45:50 PM. Time zone offsets in PDF dates are now applied.maxPagesPerPdf stops before the end of a PDF, the item now says so in warnings (for example Stopped at maxPagesPerPdf=6 of 28 pages). Before, the rest of the document was skipped silently.chunkOverlap close to chunkSize no longer makes a run crawl or return a huge number of nearly identical chunks. The overlap is now at most half of chunkSize; a larger value is reduced and the item says so in warnings.2 Publication 1040 (2025), Publication 1040 (2025) 3) are now removed like other repeated footers instead of showing up as a heading on every page.TAX AND / EARNED / INCOME) becomes one heading, and a long sentence in a slightly larger font (like a licence note above a paper title) stays a normal paragraph instead of a heading per line.arXiv:1706.03762v7 [cs.CL] 2 Aug 2023) no longer appears as a big heading in the middle of the text. Table of contents lines with dot leaders are no longer headings.28.4 instead of 28 . 4, 1948 года. instead of 1948 года ., step_num instead of step _ num.Requests the Secretariat) instead of R e q u e s t s.English-to-German, LLaMA-65B (was Englishto-German, LLaMA- 65B).الجمعية, المتحدة and في.2.3 · 10^19 instead of 2.3 · 1019.1,025 1,050) and the first rows of a block could fall out of the table.Model | BLEU | Training Cost header is kept.7B 13B in one cell). A model or group name printed once for several rows (like LLaMA next to 7B, 13B, 33B, 65B) is now repeated on each of its rows.http://[::ffff:127.0.0.1]/), or that redirect to them, are now refused like their IPv4 equivalents. The item gets a clear error and nothing is charged. Public PDF links work as before.ocrLanguages don't cover (e.g. a Greek or Chinese page with the default eng), the page is re-read with the right language and a warning tells you which setting to use.ocrLanguages accepts up to 5 languages. A longer list stops the run right away with a clear message, and nothing is charged (more languages made OCR much slower and less accurate).