Skip to content
TakoAPI
Back to skills

paddleocr-doc-parsing

by bobholamovic

PDF & Documents
3.7kDownloads reported by clawskills.sh
27Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Parse documents using PaddleOCR's API.

Description

What This Skill Does

Extracts structured content from PDFs and images via a PaddleOCR API endpoint. Handles text, tables, formulas, charts, and multi-column layouts in a single call. The agent runs a Python script against the API and presents results based on what the user asks for.

Unlike basic OCR tools, it preserves full document structure including tables, formulas, reading order, and layout across complex multi-column and mixed-content documents.

When to Use It

  • Pulling all tables from an invoice PDF
  • Extracting LaTeX formulas from a research paper
  • Parsing multi-column magazine or newspaper layouts
  • Getting structured data out of scanned financial reports
  • Reading figures and charts from technical documents

Example Workflow

INPUT

User asks: Extract all the tables from this financial report PDF

AGENT
  1. 1

    Runs python scripts/vl_caller.py --file-path "financial_report.pdf" --pretty

  2. 2

    Reads the saved JSON result from the temp directory path printed to stderr

  3. 3

    Locates table data in result[n].prunedResult and result[n].markdown fields

  4. 4

    Displays all tables in full without truncating or summarizing

OUTPUT

All tables from the document rendered in structured markdown, with the full raw JSON saved to a temp file for reference

Requirements

  • PADDLEOCR_DOC_PARSING_API_URL environment variable (full endpoint URL from a PaddleOCR-compatible service)
  • PADDLEOCR_ACCESS_TOKEN environment variable (API access token from the same service)

Installation

clawhub install bobholamovic/paddleocr-doc-parsing

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links