Back: Catalog

liteparse

LiteParse is an open-source parsing tool that processes PDF and various document formats locally. Thanks to its PDFium-based structure, it can extract text along with coordinate information and integrate with Tesseract or external OCR servers. Without cloud dependency, Markdown adapts to local workflows by producing JSON and plain text outputs.

LI

liteparse

95

run-llama · PDF & Document Processing

STARS13.0K
FORKS893
COMMITS1.1K
CONTRIBUTORS30
VERSIONnode-v2.14.4
UPDATED4 days ago
RustPDF AyrıştırmaOCRBelge İşlemeApache-2.0

Common commercial products in this category: Adobe Acrobat, ABBYY FineReader, Foxit PDF Editor

What can it do?
  • You quickly extract text and coordinate information from PDF documents.
  • By analyzing the complexity of the documents, you pre-set the OCR requirement.
  • You convert document pages into visual screenshots for LLM agents.
User reviews
  • ↑ PositiveGitHub Issue

    [RFC] Rust Processing Module - High-Performance PDF Text Extraction

    “# [RFC] Rust Processing Module - High-Performance PDF Text Extraction ## Proposal Summary Build a **Rust processing module** for LiteParse to provide high-performance PDF text extraction with spatial layout reconstruction, maintaining full compatibility with the existing…”

  • ↓ NegativeGitHub Issue

    C# wrapping WASM LiteParse : upstream bug in @llamaindex/[email protected]: any parse that actually triggers OCR pani

    “### Description I build a C# wrapper around the WASM Liteparse package in order to inegrate the native .Net Tesseract Package. Eversthing works fine, except: Confirmed upstream bug in @llamaindex/[email protected]: any parse that actually triggers OCR (custom ocrEngine or not…”

Website GitHub

My note

Alternative pages

Adobe Acrobat alternativesABBYY FineReader alternativesFoxit PDF Editor alternatives

More in: PDF & Document Processing