{"categories":[{"label":"Text Processing","url":"https://skillfed.io/packages/category/text-processing/2"},{"label":"Information Analysis","url":"https://skillfed.io/packages/category/scientific-engineering-information-analysis/2"}],"enrichment":{"capability":"LiteParse provides Python bindings for fast, lightweight PDF and document parsing with spatial text extraction, OCR support, and output to JSON, plain text, or Markdown.","skillfed_tags":["pdf-parsing","ocr","rag-pipeline"],"use_cases":["Convert PDFs to Markdown for ingestion into LLM and RAG systems with preserved structure and links.","Extract and route documents based on complexity signals (scanned vs. digital text) to optimize processing cost.","Batch-parse large document collections via the CLI or Python API with configurable OCR and image extraction.","Recover structured data from PDFs including images, annotations, form fields, and tagged logical structure.","Generate PNG screenshots of specific document pages for preview or archival purposes."],"what_it_does":"LiteParse is a Python wrapper around a Rust-based PDF and document parser that extracts text while preserving spatial layout information. It supports multiple input formats (PDF, Office documents, images) and can output structured data as JSON, plain text, or reconstructed Markdown. The package includes built-in OCR via Tesseract, configurable image extraction, annotation and form-field parsing, and a CLI tool (`lit`) for command-line workflows.\n\nTypical use cases include feeding documents into RAG pipelines and LLMs by converting PDFs to clean Markdown, routing documents to different processing pipelines based on complexity detection, and extracting structured data (images, links, annotations) from mixed document types. The package is designed to be lightweight and fast, with no runtime Python dependencies, though some features (like OCR and Office format support) require optional system libraries.","worth_installing":"Yes. LiteParse is actively maintained, has no known vulnerabilities, supports modern Python versions, and solves a real problem (document parsing for LLM/RAG workflows) with a clean API. The permissive Apache-2.0 license and zero runtime Python dependencies keep friction low. Install it if you need to parse PDFs or mixed document formats into structured text or Markdown; skip it only if you have a simpler use case or a strong preference for pure-Python solutions."},"id":"liteparse","links":{"html":"https://skillfed.io/packages/liteparse","md":"https://skillfed.io/packages/liteparse.md","pypi":"https://pypi.org/project/liteparse/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-08-13","license_spdx":"Apache-2.0","license_treatment":"permissive","name":"liteparse","python_support":"supports_current","summary":"Python bindings for LiteParse - fast, lightweight PDF and document parsing"},"popularity":{"monthly_downloads":383995,"position":7070,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"2.12.0"}