Extract layout-aware text, OCR, and bounding boxes from PDFs and office documents.
npx skills add https://github.com/dralkh/seerai --skill liteparse-dralkh
Please help me install this Agent Skill. Skill: liteparse Source: https://github.com/dralkh/seerai/tree/main/skills/liteparse Command: npx skills add https://github.com/dralkh/seerai --skill liteparse-dralkh
This Skill removes the friction of turning PDFs, scans, office files, and images into usable text and structured data while preserving page layout and coordinates.
Ask the skill to parse the attached document or folder and return layout-preserved text, JSON, or screenshots as needed.
High-intent search queries and answers about installing and using this skill.
To extract text and bounding boxes locally, you can use this Skill to parse PDFs and office documents, yielding layout-aware text or JSON without relying on cloud services.
Yes, you can batch parse a folder of research papers to output layout-preserved text or JSON, supporting literature review ingestion and structured data extraction.
You can run OCR on scanned PDF documents by using this Skill to read image-only pages and extract text, optionally rendering page screenshots for multimodal review.
Optional LibreOffice and ImageMagick dependencies are required for conversions when parsing office documents, alongside the required local LiteParse bindings for core extraction.
Local PDF parsing supports handling encrypted PDFs and extracting specific page subsets, allowing targeted document region inspection and citation grounding.
jasrajtulsiExtract layout-aware text and bounding boxes from PDFs and converted files.
ClawBioSearch PubMed and preprint servers, summarize literature, and build citation graphs.
Ritabrata-ChakrabortyExtract spatial text and bounding boxes from local documents with OCR.
attentiondotnetExtract text from PDFs, DOCX, PPTX, and scanned documents via OCR.
