skills.rest
iflytek
iflytekOFFICIAL
Explore all skills by this author →
WebsiteGitHub

ifly-pdf&image-ocr

Extract text from images and PDFs and convert PDFs to JSON, Markdown, or Word.

217|27|Updated Mar 30, 2026
Search Tags:#ocr#multilingual#document-processing#text-extraction#image-ocr#pdf-ocr
One-click install
npx skills add https://github.com/iflytek/iFly-Skills --skill ifly-pdf-image-ocr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ifly-pdf&image-ocr
Source: https://github.com/iflytek/iFly-Skills/tree/main/ifly-pdf-image-ocr
Command: npx skills add https://github.com/iflytek/iFly-Skills --skill ifly-pdf-image-ocr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

OCRing images and PDFs to extract text and convert PDFs into editable formats, enabling quick digitization and content reuse across languages.

Core Features & Use Cases

  • Image OCR (LLM OCR): multi-language text extraction with layout preservation from images.
  • PDF OCR: extract text from PDFs and convert to Word, Markdown, or JSON with page-level outputs.
  • Document conversion: convert PDFs into editable formats while preserving structure.
  • Use Case: quickly digitize contracts or invoices and repurpose content in Word or Markdown.

Quick Start

Run the image_ocr.py script on an image to extract text or run pdf_ocr.py on a PDF to extract text and convert it to Word or Markdown.

Frequently Asked Questions about ifly-pdf&image-ocr

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

FAQPage Schema
How do I extract text from images and PDFs while preserving layout?▼

Extract text from images and PDFs using LLM OCR to maintain layout structure. It digitizes multilingual sources and outputs editable formats like Word, Markdown, or JSON for content reuse.

Can I convert PDF documents to editable Word or Markdown files directly?▼

PDF OCR converts documents into editable Word, Markdown, or JSON files while preserving structure. It provides page-level outputs to digitize contracts or invoices for automated data extraction.

Does multilingual OCR support extracting text from documents in different languages?▼

Multilingual OCR supports text extraction from images and PDFs across various languages. It applies LLM OCR workflows to digitize international documents and output structured JSON or Markdown files.

What is the best way to digitize invoices and contracts for automated workflows?▼

Digitize invoices and contracts by running image or PDF OCR scripts to extract text. The process converts document content into JSON, Markdown, or Word formats, enabling automated data extraction and reuse.

Do I need an API key to perform document processing and text extraction?▼

Document processing and text extraction require an API key for authentication. Configuring the API key enables LLM OCR workflows to convert multilingual images and PDFs into structured editable outputs.

Why does PDF OCR output text in JSON or Markdown instead of plain text?▼

PDF OCR outputs JSON or Markdown to preserve document structure and enable format-specific data extraction. This allows downstream applications to parse page-level content from digitized multilingual sources effectively.

Related Skills

Explore More Data & Analytics Skills→
Zenobia000Zenobia000
2

nutrient-document-processing

Automates PDF DOCX XLSX PPTX HTML and image document processing via Nutrient DWS API.

Community
Intermediate
Blake-JohnBlake-John

pymupdf

Convert PDF documents into Markdown, JSON, and text for LLM workflows.

Community
Intermediate
Brilly-BohyunBrilly-Bohyun

ocr-and-documents

Extract text from PDFs and scanned documents using OCR and Python libraries.

Community
Advanced
faramirezsfaramirezs

ocr-and-documents

Extract text and data from PDFs, scans, images, and EPUBs using OCR.

Community
Intermediate