YomiToku-Pro SageMaker API (1.3.1)

Download OpenAPI specification:Download

YomiToku-Pro is a Japanese document AI engine for OCR and layout analysis.

health

Health check endpoints for monitoring service status

Basic health check

Simple health check endpoint that returns 200 OK if the service is running. Used by SageMaker for health monitoring.

Responses

Response samples

Content type

application/json

{"status": "healthy",
"message": "Service is running"
}

ocr

Document OCR and layout analysis endpoints

Document OCR and Layout Analysis

Perform OCR and layout analysis on document images or PDFs.

**Supported Content Types:**
- `application/pdf` - PDF documents (multi-page supported)
- `image/jpeg` - JPEG images
- `image/png` - PNG images  
- `image/tiff` - TIFF images

**Request Body:**
Send the binary file data directly in the request body with appropriate Content-Type header.

**Response:**
Returns structured OCR results including:
- Extracted text with bounding boxes
- Layout analysis (paragraphs, tables, figures)
- Reading order estimation
- Table structure recognition

**Example Usage:**
```bash
curl -X POST "http://localhost:8080/invocations" \
     -H "Content-Type: application/pdf" \
     --data-binary @document.pdf
```

header Parameters

content-type

required

string (Content-Type)

Examples:

application/pdf - PDF Document
image/jpeg - JPEG Image
image/png - PNG Image
image/tiff - TIFF Image

Content type of the uploaded file

Responses

Response samples

Content type

application/json

{"result": [{"preprocess": {"angle": 0,
"angle_score": 0
},
"paragraphs": [{"box": [0,
0,
0,
0
],
"contents": "string",
"direction": "string",
"order": 0,
"role": "string",
"indent_level": 0
}
],
"tables": [{"box": [0,
0,
0,
0
],
"n_row": 0,
"n_col": 0,
"rows": [{"box": [0,
0,
0,
0
],
"score": 0
}
],
"cols": [{"box": [0,
0,
0,
0
],
"score": 0
}
],
"spans": [{"box": [0,
0,
0,
0
],
"score": 0
}
],
"cells": [{"col": 0,
"row": 0,
"col_span": 0,
"row_span": 0,
"box": [0,
0,
0,
0
],
"contents": "string"
}
],
"order": 0,
"caption": {"box": [0,
0,
0,
0
],
"contents": "string",
"direction": "string",
"order": 0,
"role": "string",
"indent_level": 0
}
}
],
"words": [{"points": [[0,
0
],
[0,
0
],
[0,
0
],
[0,
0
]
],
"content": "string",
"direction": "string",
"rec_score": 0,
"det_score": 0
}
],
"figures": [{"box": [0,
0,
0,
0
],
"order": 0,
"paragraphs": [{"box": [0,
0,
0,
0
],
"contents": "string",
"direction": "string",
"order": 0,
"role": "string",
"indent_level": 0
}
],
"role": "string",
"direction": "string",
"caption": {"box": [0,
0,
0,
0
],
"contents": "string",
"direction": "string",
"order": 0,
"role": "string",
"indent_level": 0
},
"decode": "string"
}
]
}
]
}