Parses PDFs, Office files, and images locally into markdown, JSON with bounding boxes, or plain text for agents and RAG pipelines, from a CLI or Rust, Node.js, Python, and WASM libraries.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Markdown Output
Use LiteParse to render documents to structured Markdown: ‹what you need›
- Selective OCR
Use LiteParse to run bundled Tesseract OCR: ‹what you need›
- Page Screenshots
Use LiteParse to generate PNG screenshots of all or selected pages: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: github.com/run-llama/liteparse
Call the API
Auth None needed
Its page: github.com/run-llama/liteparse
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLIAPI
- Auth
- None
- Skills
- 5
Skills
Markdown Output
Renders documents to structured Markdown with headings, tables, lists, images, and links, ready to pass to an LLM or RAG pipeline.
Selective OCR
Runs bundled Tesseract OCR only where native text is missing, or sends pages to an HTTP OCR server such as EasyOCR or PaddleOCR.
Complexity Check
Checks cheaply whether a document needs OCR or heavier parsing, so a pipeline can route, reject, or estimate cost before a full parse.
Page Screenshots
Generates PNG screenshots of all or selected pages at a custom DPI so vision-capable agents can look at the rendered page itself.
Batch And Worker Parsing
Parses whole directories with lit batch-parse, or many files in Python or Node.js worker pools with hard per-parse timeouts.