Tools / Split PDF Text into Clean Chunks
Split PDF Text into Clean Chunks
Tune target chunk size, max characters, paragraph boundaries and table handling after conversion. Sensible defaults mean no config before upload.
Drop a PDF here
or drag and drop a file
Advanced options
Limits: up to 100 pages · OCR up to 25 pages
- No account required
- Optional local OCR
- Files up to 40 MB
Converting in your browser
Preparing your PDF…
- Checking document
- Detecting page structure
- Reading scanned pages (OCR)
- Reading tables and images
- Cleaning text
- Creating Markdown
Conversion complete
View conversion details
Review recommended
View removed headers and footers
Download Markdown
More exports
Nothing was uploaded. Clear the page to discard results from memory.
What you get
Sized JSONL chunks with heading context — tune target size, max characters and paragraph boundaries.
- RAG chunks (.jsonl)
- Structured JSON
- Markdown (.md)
- ZIP package
Limits: Low SEO priority; keep content concise.
How it works
- Upload a PDF — defaults start conversion immediately.
- Adjust chunk settings on the result page if needed.
- Download updated chunks.jsonl.
Example output
Unchunked text
Installation Manual — entire document text in one block spanning 48 pages with no chunk boundaries...
Sized chunks
Chunk 1 (1,240 chars, pages 1-3): Introduction and overview... Chunk 2 (980 chars, pages 3-5): Safety requirements and warnings...
Use cases
- Match chunk size to your embedding model
- Keep tables intact for retrieval
Related tools
FAQ
Must I configure before upload?
No. Defaults run immediately; settings appear after conversion.
Can tables be split?
By default tables are not split across chunks.
Does this use an LLM to rewrite text?
No. Chunking is deterministic over cleaned extracted content.