pdf-harvester

Extract text, tables, and metadata from PDFs for RAG pipelines.

2|Updated Jan 2, 2026
One-click install
npx skills add https://github.com/mindmorass/reflex --skill pdf-harvester
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf-harvester
Source: https://github.com/mindmorass/reflex/tree/main/plugins/reflex/skills/pdf-harvester
Command: npx skills add https://github.com/mindmorass/reflex --skill pdf-harvester

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines the extraction of text, tables, and metadata from PDF documents, enabling fast ingestion into RAG pipelines and searchable archives.

Core Features & Use Cases

  • Text and layout-preserving extraction from PDFs, including support for tables and conversion to Markdown.
  • OCR for image-based or scanned documents to recover content with pytesseract.
  • Academic paper parsing with structure detection for abstracts, sections, and references, plus metadata extraction.

Quick Start

Run a sample PDF through the harvest process to extract text, tables, and metadata, then inspect the resulting data structure.

Frequently Asked Questions about pdf-harvester

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text and tables from PDF documents?

Text and table extraction from PDFs is accomplished by parsing the document structure with pdfplumber or PyMuPDF to recover text, preserve layout, and convert tables to Markdown format. This handles both native PDFs and scanned documents with OCR support via pytesseract.

Can I extract text from scanned PDFs and image-based documents?

Scanned PDFs require OCR processing. This Skill applies pytesseract with pdf2image to convert scanned pages to searchable text, recovering content from image-based documents where traditional text extraction fails.

How do I ingest PDF data into a RAG pipeline?

PDF harvesting extracts text, tables, and metadata in structured formats ready for RAG pipeline ingestion. The extracted content becomes searchable and queryable for retrieval-augmented generation workflows.

What's the best way to parse academic papers and extract metadata?

Academic paper parsing detects document structure—abstracts, sections, references—and extracts metadata. Integration with arxiv enables automated paper fetching, making large-scale research corpus ingestion feasible.

Do I need system-level dependencies to process PDFs with OCR?

Yes. OCR functionality requires Tesseract OCR installed at the system level, alongside Python libraries pdfplumber, PyMuPDF, pytesseract, and pdf2image. This setup enables both standard and scanned document processing.

What file formats and document types does PDF extraction support?

Extraction supports native PDFs, scanned documents, research papers, manuals, and reports. Output includes searchable text, table data in Markdown, and extracted metadata suitable for downstream processing.