OCR

Optical Character Recognition endpoint that extracts text and structured data from images and PDF documents.

POST /v1/ocr

Request Body

Les paramètres suivants peuvent être inclus dans le corps de la requête :

Paramètres

model

string

Required

Default Value: alphaedge-ocr-3-2512

ID of the OCR model to use.

image

string

Required

Base64 encoded image or image URL.

structured_output

boolean

Default Value: false

Whether to return structured output with bounding boxes.

Successful Response

Les champs suivants sont retournés dans une réponse réussie :

Champs de réponse

id

string

Required

A unique identifier for the OCR result.

object

string

Required

The object type, which is always "ocr.result".

model

string

Required

The OCR model used.

text

string

Required

The extracted text content.

bboxes

array<BBox>

Array of bounding boxes with text and coordinates.

Examples

Exemples de code pour utiliser cet endpoint :

typescript

import { AlphaEdge } from '@alphaedge/alphaedge';

const alphaedge = new AlphaEdge({
  apiKey: process.env.ALPHAEDGE_API_KEY,
});

const result = await alphaedge.ocr.create({
  model: 'alphaedge-ocr-3-2512',
  image: 'data:image/png;base64,...',
  structured_output: true
});

python

from alphaedge import AlphaEdge

alphaedge = AlphaEdge(api_key="your-api-key")

result = alphaedge.ocr.create(
    model="alphaedge-ocr-3-2512",
    image="data:image/png;base64,...",
    structured_output=True
)

curl

curl https://api.alphaedge-ai.com/v1/ocr \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ALPHAEDGE_API_KEY" \
  -d '{
    "model": "alphaedge-ocr-3-2512",
    "image": "data:image/png;base64,...",
    "structured_output": true
  }'

Response

Exemple de réponse de l'API :

json

{
  "id": "ocr-abc123",
  "object": "ocr.result",
  "model": "alphaedge-ocr-3-2512",
  "text": "Extracted text content...",
  "bboxes": [
    {
      "text": "Hello",
      "bbox": [10, 20, 100, 30],
      "confidence": 0.98
    }
  ]
}