skills.rest
UnicomAI
UnicomAICOMMUNITY
Explore all skills by this author →
GitHub

yj-ocr-parser

Parses PDF documents and images into Markdown via a document parsing API.

2.5k|134|Updated Jun 6, 2025
Search Tags:#api#OCR#Markdown#image recognition#table extraction#document extraction#PDF parsing
One-click install
npx skills add https://github.com/UnicomAI/wanwu --skill yj-ocr-parser
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: yj-ocr-parser
Source: https://github.com/UnicomAI/wanwu/tree/main/configs/microservice/bff-service/configs/agent-skills/ontology/yj-ocr-parser
Command: npx skills add https://github.com/UnicomAI/wanwu --skill yj-ocr-parser

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It converts PDF documents and images (jpg/png/jpeg) into structured Markdown content, eliminating manual transcription of tables, formulas, and text from documents.

Core Features & Use Cases

  • PDF to Markdown Conversion: Parses PDF files into Markdown with heading hierarchy, HTML-format tables, LaTeX formulas, and image links.
  • Image Text Recognition: Extracts content from jpg, jpeg, and png images into editable text.
  • Use Case: A user has a scanned report saved as report.pdf and needs its tables and formulas in editable form; the skill calls the parsing API and returns the full Markdown content.

Quick Start

Parse the file /home/user/documents/report.pdf and show me the extracted Markdown content.

Frequently Asked Questions about yj-ocr-parser

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

FAQPage Schema
How do I convert a PDF to Markdown using an API?▼

Send a multipart/form-data POST request to the parsing endpoint with the PDF file and file_name, including a Bearer token in the Authorization header. The response content field contains the Markdown output with tables in HTML and formulas in LaTeX.

What file formats does this document parser support?▼

It supports PDF files and images in jpg, jpeg, and png formats. Vector formats like SVG and other formats such as gif or bmp are not supported.

How do I extract text from an image file?▼

Upload the jpg, jpeg, or png image through the same parsing API using curl with the file path and file name. The API returns recognized text content in Markdown format.

What are the file size and rate limits for PDF parsing?▼

Files are limited to 20MB, and larger files should be split before parsing. The API allows 3 requests per minute, and large files may take longer since the call is synchronous.

Why does the parsing API return a 400 or 429 error?▼

A 400 code indicates incorrect request parameters, so verify the file path and file_name. A 429 code means the token hit the rate limit, so wait and retry later.

Related Skills

Explore More Data & Analytics Skills→
webdevtodayjasonwebdevtodayjason

ocr-and-documents

Extract text from PDFs, scanned documents, and images using OCR.

Community
Advanced
PriyanshKuniyalPriyanshKuniyal

rag-implementation

Build and manage RAG systems integrating vector databases for LLMs.

Community
Advanced
vecearvecear

doc-to-vector-dataset-generator

Convert documents into chunked JSONL datasets with metadata for embedding search.

Community
Advanced
RepairYourTechRepairYourTech
6

ollama

Run open-source LLMs locally via the Ollama runtime REST API.

Community
Intermediate