AI Document Extractor: PDF, DOCX to Markdown + RAG chunks
Pricing
from $2.00 / 1,000 documents
AI Document Extractor: PDF, DOCX to Markdown + RAG chunks
Convert PDF, Word (DOCX) and text files to clean Markdown or text, split into RAG-ready chunks with page numbers and token estimates. Headings rebuilt from PDFs, scanned PDFs flagged, failed files free.
Pricing
from $2.00 / 1,000 documents
Rating
0.0
(0)
Developer
Momi
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 days ago
Last modified
Categories
Security
Limited permissionsShare
AI Document Extractor — PDF, DOCX & TXT to Markdown + RAG chunks
Turn PDF, Word (DOCX) and text files into clean Markdown or plain text, already split into chunks for RAG, embeddings and LLM prompts. Paste file URLs, get structured JSON back — no API keys, no code.
What you get for each document
- Markdown with structure: headings are rebuilt from font sizes in PDFs (and kept from DOCX), so LLMs see sections, not a wall of text.
- RAG-ready chunks: configurable size and overlap, each with
startPage/endPage(PDF) and anapproxTokensestimate — ready for your vector database. - Metadata: title, author, creation date (when present), pages, words, characters, approximate tokens.
- Scanned PDF detection: if most pages contain no text layer, the item is flagged
needsOcr: trueinstead of silently returning empty text. - Clean errors: broken links, HTML pages or unsupported files return an item with
error— and are not charged.
Supported files
| Type | Notes |
|---|---|
| Text-based PDFs. Line joining, de-hyphenation, heading detection, rotated margin text removed. | |
| DOCX | Word 2007+ documents, headings and bold kept. Tables are flattened to text. |
| TXT / MD | UTF-8 text; Markdown headings are recognized. |
Max 50 MB per file. Use direct file links (a URL that downloads the file), not web pages.
Output example
Use cases
- RAG pipelines: feed chunks straight into Pinecone, Weaviate, Qdrant, pgvector or any embedding API.
- LLM prompts: summarize contracts, papers, manuals or reports with structure preserved.
- Bulk conversion: convert hundreds of PDFs/DOCX to Markdown for a knowledge base or a static site.
- Automations: call it from Make, Zapier, n8n or the Apify API whenever a new document arrives.
Pricing
Pay per event: a small fee per document plus per page (for DOCX/TXT one "page" = 3,000 characters). Failed downloads and unsupported files are free. Limit pages with Max pages per PDF and total spend with Maximum cost per run.
Limits
- No OCR in this version: scanned PDFs are detected and flagged, not transcribed.
- Complex layouts (multi-column pages, tables) are extracted as readable text, not as tables.
- Files are processed only for this run and are not stored beyond your own run storage.
Feedback
Need OCR, PPTX, XLSX or table extraction? Open an issue on the Issues tab — features are prioritized by requests.
