switchboard
P

PaddleOCR

Featured

by PaddlePaddle

Converts documents, receipts, and images into structured data with OCR, layout analysis, and table recognition, exposed to agents via a Python API, CLI, and MCP server.

4
Skills
None
Auth
No
Streaming
No
Push

Skills

Text Recognition

Extracts printed and handwritten text from images and scanned PDFs across more than 80 languages.

Layout Analysis

Detects document structure including headings, paragraphs, figures, and reading order before extraction.

Table Recognition

Parses tables from scans into structured HTML or Markdown while preserving row and column spans.

Document Pipeline

Runs end-to-end pipelines chaining detection, recognition, and structure parsing into JSON output.

Content & MediaData & Analyticsocrdocument-parsingtable-recognitionlayout-analysispdf-extractioncomputer-visionbaidu
Visit Agent

Related Agents

D

Docling

Parses PDF, DOCX, PPTX, XLSX, HTML, audio, and image files into a unified DoclingDocument and exports Markdown, HTML, D…

Content & MediaData & Analytics
APICLIMCP
5 skillsNone
M

MarkItDown

Converts PDF, Office, HTML, image, audio, and ZIP files into structured Markdown for LLM pipelines, preserving headings…

Content & MediaData & Analytics
CLIMCP
5 skillsNone
M

MinerU

Converts PDFs, Office documents, and scanned pages into LLM-ready Markdown or JSON, preserving tables, formulas, and re…

Data & AnalyticsResearch & Knowledge
APICLI
3 skillsAPI Key
K

Keenable

Serves a hundred-billion-document web index built for agents rather than human search pages, returning dense structured…

Research & KnowledgeInfrastructure & Ops
APIMCP
3 skillsAPI Key
paddleocr
Converts documents, receipts, and images into structured data with OCR, layout analysis, and table recognition, exposed to agents via a Python API, CLI, and MCP server.
fields
namePaddleOCR
providerPaddlePaddle
urlhttps://paddleocr.com
categoriescontent-media · data-analytics
accessapi · cli · mcp
authnone
streamingfalse
pushfalse
verifiedtrue
tagsocr, document-parsing, table-recognition, layout-analysis, pdf-extraction, computer-vision, baidu
skills
text-recognitionText RecognitionExtracts printed and handwritten text from images and s…
layout-analysisLayout AnalysisDetects document structure including headings, paragrap…
table-recognitionTable RecognitionParses tables from scans into structured HTML or Markdo…
doc-pipelineDocument PipelineRuns end-to-end pipelines chaining detection, recogniti…
→ https://paddleocr.com