LiteParse — Local Document Parsing

Overview

LiteParse is an open-source document parser (Rust core, Python/Node bindings) for local, layout-aware text extraction. It produces layout text, structured JSON, or heuristic Markdown. Spatial text items may span several words; Python emit_word_boxes=True adds word boxes when needed.

Verified release: Python liteparse 2.15.0 (September 29, 2026); CLI and synthetic local PDF/image fixtures tested on Python 3.13. Node/Rust examples below are source-checked and illustrative. Images convert through bundled Rust libraries, not ImageMagick. No cloud account is needed, but missing Tesseract language data can download from GitHub and an explicitly configured HTTP OCR service receives document images.

For parser selection vs MarkItDown, PDF manipulation libraries, or LlamaParse, see references/choosing_a_parser.md.

When to Use This Skill

Use LiteParse when you need:

• Fast local parsing of PDFs or converted Office/image files without cloud dependencies
• Spatial text with bounding boxes for layout-aware RAG, citation grounding, or figure/table region logic
• OCR on scanned PDFs or images (bundled Tesseract, or a user-run HTTP OCR server)
• Page screenshots (PNG) for multimodal agents that must see charts, figures, or handwriting
• Batch ingestion of literature folders, supplementary PDFs, or protocol libraries
• Page subsets or password-protected PDFs

When Not to Use

Installation

uv pip install "liteparse==2.15.0"

This installs the Python bindings and the **lit** CLI. Verify:

lit --help
python -c "import liteparse; print(liteparse.__version__)"

Optional system tool (for Office inputs):

• LibreOffice — Word, Excel, PowerPoint, OpenDocument, CSV/TSV

PNG, JPEG, TIFF, WebP, SVG and other supported images convert natively.

Install commands are in references/ocr_and_formats.md.

Node.js / TypeScript (optional): npm i @llamaindex/liteparse@2.15.0 — see references/api_reference.md.

Quick Start

Python

from liteparse import LiteParse

parser = LiteParse(quiet=True)
result = parser.parse("paper.pdf")
print(result.text)

for page in result.pages:
    print(f"Page {page.page_num}: {len(page.text_items)} items")

CLI

# Layout-preserved text (default)
lit parse paper.pdf

# Structured JSON with bounding boxes
lit parse paper.pdf --format json -o paper.json

# Heuristic Markdown, including headings, tables and links
lit parse paper.pdf --format markdown -o paper.md

# Disable OCR on text-native PDFs (faster)
lit parse paper.pdf --no-ocr

Core Workflows

1. Parse to layout-preserved text

Best for quick full-document text or feeding chunkers that do not need coordinates.

parser = LiteParse(ocr_enabled=True, quiet=True)
result = parser.parse("document.pdf")
full_text = result.text

lit parse document.pdf -o output.txt

2. Parse to structured JSON (bounding boxes)

Use when building layout-aware RAG, highlighting source regions, or joining text with screenshots.

from liteparse import LiteParse

parser = LiteParse(output_format="json", quiet=True)
result = parser.parse("document.pdf")

# Programmatic access
for page in result.pages:
    for item in page.text_items:
        bbox = (item.x, item.y, item.width, item.height)
        # item.text, item.confidence, item.font_name, item.font_size

lit parse document.pdf --format json -o document.json

JSON field layout: references/output_formats.md.

3. Parse specific pages

parser = LiteParse(target_pages="1-5,10,15-20", quiet=True)
result = parser.parse("long_paper.pdf")

lit parse long_paper.pdf --target-pages "1-5,10"

4. Parse from bytes or stdin

Useful for uploads, S3 downloads, or piping remote PDFs.

with open("document.pdf", "rb") as f:
    result = parser.parse(f.read())

curl -sL https://example.com/report.pdf | lit parse -

5. Page screenshots for multimodal agents

Screenshots capture visual content that text extraction alone misses (figures, complex tables, handwriting).

from pathlib import Path

parser = LiteParse(dpi=150, quiet=True)
shots = parser.screenshot("document.pdf", page_numbers=[1, 2, 3])
out = Path("screenshots")
out.mkdir(exist_ok=True)
for s in shots:
    (out / f"page_{s.page_num}.png").write_bytes(s.image_bytes)

lit screenshot document.pdf --target-pages "1,3,5" -o ./screenshots
lit screenshot document.pdf --dpi 300 -o ./screenshots

Combine JSON parse + screenshots when an agent needs both coordinates and pixels for the same pages.

6. Batch-parse a directory

Use the CLI or bundled script. OCR workers parallelize OCR tasks; they do not parallelize whole-document PDFium parsing. Python worker pools provide process-level parallelism and hard parse timeouts; see the API reference.

lit batch-parse ./papers ./parsed --format json --recursive
lit batch-parse ./papers ./parsed --extension .pdf --no-ocr

python scripts/batch_parse_dir.py ./papers ./parsed --format json --recursive

The wrapper mirrors subdirectories, preserves source suffixes (paper.pdf.json), and rejects existing outputs or partial-page results. It emits a documented Python JSON subset, not the native CLI schema. Native lit batch-parse uses paper.json, so same-stem inputs in one directory can collide; restrict the input extension or use the wrapper.

7. OCR configuration

OCR is on by default. Tesseract is bundled; missing .traineddata files are downloaded on demand, including when a custom tessdata directory is set.

parser = LiteParse(
    ocr_enabled=True,
    ocr_language="eng",       # Tesseract codes: fra, deu, etc.
    num_workers=4,            # parallel OCR (default: CPU cores - 1)
    dpi=150,                  # higher DPI → better OCR, slower
)

lit parse scan.pdf --ocr-language fra
lit parse scan.pdf --no-ocr
lit parse scan.pdf --ocr-server-url http://localhost:8080/ocr

Offline / air-gapped: pre-populate every requested .traineddata file, then set TESSDATA_PREFIX or pass --tessdata-path. A directory setting alone does not prohibit downloads. Details: references/ocr_and_formats.md.

8. Encrypted PDFs

parser = LiteParse(password="secret", quiet=True)
result = parser.parse("protected.pdf")

lit parse protected.pdf --password secret

9. Search text items by phrase

Merge adjacent items and return combined bounding boxes for a phrase (e.g. section titles).

from liteparse import search_items

page = result.get_page(1)
matches = search_items(page.text_items, "Materials and Methods", case_sensitive=False) if page else []

Multi-Format Inputs

Non-PDF inputs convert to PDF internally. Office conversion depends on LibreOffice and available fonts. Inspect representative converted pages; formulas, layout, and scientific symbols can change during conversion.

Performance Tips

• **--no-ocr** on born-digital PDFs — largest speedup
• **target_pages** — parse only methods/supplement sections
• **num_workers** — scale OCR across CPU cores
• **max_pages** — cap parsed pages (default 1000); compare result.total_pages, selected page numbers, and result.page_errors before declaring ingestion complete
• **lit batch-parse** — directory-scale jobs with --recursive and --extension
• Lower **dpi** (e.g. 100) when OCR quality is already sufficient

Validate extraction

• Confirm requested page numbers and total source pages; page caps and target_pages intentionally omit content. continue_on_page_error=True permits partial results, so inspect page_errors.
• Compare a rendered page with text/Markdown for columns, tables, subscripts, units and references. Markdown is heuristic and does not recover chart data or guarantee mathematical transcription.
• Native CLI JSON uses pages[].page, while Python uses page.page_num; native CLI confidence defaults to 1.0 for native text. Do not treat confidence as proof of correctness or OCR provenance.
• Store page dimensions with boxes and scale coordinates to screenshot dimensions; screenshot pixels are not PDF points.

Reference Files

Troubleshooting

Resources

• GitHub: https://github.com/run-llama/liteparse
• Docs: https://developers.llamaindex.ai/liteparse/
• PyPI: https://pypi.org/project/liteparse/2.15.0/
• npm: https://www.npmjs.com/package/@llamaindex/liteparse
• OCR API spec: https://github.com/run-llama/liteparse/blob/main/OCR_API_SPEC.md