skills.rest
neverprepared
neverpreparedOFFICIAL
Explore all skills by this author →
GitHub

pdf-harvester

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

Updated Aug 27, 2026
Search Tags:#ocr#pdf#rag#text-extraction#table-extraction#data-ingest
One-click install
npx skills add https://github.com/neverprepared/ink-bunny --skill pdf-harvester-neverprepared
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-harvester
Source: https://github.com/neverprepared/ink-bunny/tree/main/reflex/plugins/reflex/skills/pdf-harvester
Command: npx skills add https://github.com/neverprepared/ink-bunny --skill pdf-harvester-neverprepared

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

PDFs contain valuable text and tabular data but extracting and indexing them for knowledge bases is often slow and error-prone.

Core Features & Use Cases

  • Text extraction with layout preservation from PDFs, enabling accurate content ingestion.
  • Table extraction and conversion to Markdown for seamless downstream processing.
  • OCR fallback to handle scanned documents and academic papers, plus support for common patterns.

Quick Start

Ingest a PDF by extracting text, tables, and metadata into your RAG pipeline.

Frequently Asked Questions about pdf-harvester

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

FAQPage Schema
How do I extract tables from PDF files for RAG ingestion?▼

Extract tables from PDFs by converting them into Markdown format for RAG ingestion. This approach preserves structural data, enabling seamless downstream processing and accurate content indexing for research papers and reports.

Can I use OCR to extract text from scanned PDF documents?▼

Yes, you can extract text from scanned PDFs using an OCR fallback. By leveraging tesseract and pdf2image, the system processes scanned documents and academic papers across multiple pages to retrieve text.

What is the best way to chunk academic papers for a knowledge base?▼

The best way to chunk academic papers is using modular chunking strategies like pages, sections, or paragraphs. An academic paper pattern applies these strategies to structure extracted text for RAG workflows.

Does pdfplumber or PyMuPDF work better for text extraction with layout preservation?▼

Both pdfplumber and PyMuPDF support text extraction with layout preservation. They enable accurate content ingestion from PDFs, allowing you to choose the extraction method that best fits your document structure.

Why does text extraction fail on multi-page scanned reports?▼

Text extraction fails on scanned reports because the content is image-based rather than text-based. Applying an OCR fallback with pdf2image and tesseract processes these scanned images across multiple pages to harvest the text.

Related Skills

Explore More Data & Analytics Skills→
mindmorassmindmorass
2

pdf-harvester

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

Community
Advanced
kreuzberg-devkreuzberg-dev
8.9k

chunking-embeddings

Create text chunks and FastEmbed vector embeddings for RAG pipelines.

Official
Advanced
Himanshu040604Himanshu040604

rag-implementation

Developes RAG systems integrating vector databases and advanced retrieval strategies for LLM applications.

Community
Advanced
89jobrien89jobrien
4

PDF Processing

Extract text and tables from native and scanned PDFs using pdfplumber.

Community
Advanced