lmocr

lmocr is a Rust CLI that converts PDFs and images to Markdown using an OpenRouter multimodal model.

Most OCR treats pages as isolated blobs. lmocr treats a document as one stream: pages run serially, each LLM call sees the previous page tail, and the results are stitched back together.

• Clean seams: joins sentences and de-hyphenates words split across page breaks.
• Less cruft: skips blank pages and can filter running headers, footers, and page numbers instead of mixing them into the text.
• Tunable output: presets for Markdown, audiobooks, and search; --exclude and custom -i instructions for everything else.
• Layout-aware: the vision path can preserve tables as HTML and translate charts, graphics, checkboxes, and structured layouts into useful Markdown instead of dropping them.
• LLM cleanup on every non-blank page: text PDFs take a cheaper pdftotext path; scans and images use vision. Both still get document-aware cleanup.
• Practical for long documents: retries and resumable caching are built in.

Examples: make a PDF listenable without hearing page numbers and running headers every minute; convert a report without losing the table or figure that carries the point.

Install

# needed for PDF inputs only (macOS); image inputs have no external dependencies
brew install poppler

# from crates.io
cargo install lmocr

# or from a checkout
cargo install --path . --locked

Setup

# configure once
lmocr auth

# or set per-run
export OPENROUTER_API_KEY=sk-or-v1-...

Usage

lmocr /path/to/file.pdf -o out.md
lmocr /path/to/file.pdf -p 10-12 --exclude headers,footers,page-numbers
lmocr /path/to/file.pdf --preset audiobook
lmocr screenshot.png -o out.md
lmocr ./scanned_pages/ -o out.md   # folder of images = multi-page document

Run lmocr -h for the full option list.

Presets

Note: --exclude flags are redundant with audiobook since it already strips those elements.

Custom instructions

The -i / --instruction flag appends custom rules to the OCR prompt:

lmocr doc.pdf -i "Translate all text to French"
lmocr doc.pdf -i "Number headings with outline format (1, 1.1, 1.1.1)"
lmocr doc.pdf -i "Omit all image descriptions"

How it works

• Text-based PDFs use a pdftotext fast path — no vision API call, much cheaper and faster.
• Scanned / image-heavy PDFs render each page as a PNG and send it to the vision model.
• This is automatic based on extracted-text coverage. No flag needed.
• Images are sent directly to the vision model. TIFF/BMP are transcoded to PNG for upload; a folder of images is processed as one multi-page document (sorted lexicographically) with full cross-page stitching.

Configuration

# API key is stored by `lmocr auth` at:
#   macOS: ~/Library/Application Support/ai.lmocr.lmocr/config.toml
#   Linux: ~/.config/lmocr/config.toml

# Or set per-session:
export OPENROUTER_API_KEY=sk-or-v1-...

Cache lives at .lmocr/cache/ relative to the current directory. To clear it:

rm -rf .lmocr/cache
# or skip cache for a single run:
lmocr doc.pdf --no-cache

The cache key includes: source file, page number, DPI, model, preset, excludes, prompt version, custom instruction, and previous-page context. Changing any of these invalidates the cached result for that page.

Reliability Notes

• --max-retries means retries after the first attempt (total attempts = retries + 1).
• Retry loop uses linear backoff.
• Image OCR retries now include automatic lower-DPI fallbacks (300 -> 240 -> 200 -> 180 -> 150) before failing a page.
• Continuity logic merges split sentences and de-hyphenates page-break fragments.
• Boundary artifact stripping removes common leaked seam headers when they interrupt sentence flow, including default mode.

Development

Run cargo test before contributing. Maintainer regression evals are documented in project/EVAL.md.

License

MIT

AI training

The author reserves rights to this work under applicable text-and-data-mining provisions and asks that it not be used as AI training data.