Extract Data Endpoint¶
Extract structured data from documents or text using a trained DeepTagger project.
Endpoint¶
Request¶
Headers¶
Header | Required | Description |
---|---|---|
x-api-key |
Yes | Your DeepTagger API key |
Content-Type |
Yes | multipart/form-data for files, application/x-www-form-urlencoded for text |
Parameters¶
Parameter | Type | Required | Description |
---|---|---|---|
fo_id |
string | Yes | Project ID (e.g., fo_1759714105892 ) |
file |
binary | Conditional | Document file (PDF, image). Required if no text |
text |
string | Conditional | Raw text content. Required if no file |
Examples¶
File Upload¶
curl -X POST https://deeptagger.com/api/v1/extract_data \
-H "x-api-key: YOUR_API_KEY" \
-F "fo_id=fo_1759714105892" \
-F "file=@invoice.pdf"
Text Input¶
curl -X POST https://deeptagger.com/api/v1/extract_data \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/x-www-form-urlencoded" \
-d "fo_id=fo_1759714105892" \
-d "text=Invoice content here..."
Python¶
import requests
url = "https://deeptagger.com/api/v1/extract_data"
headers = {"x-api-key": "YOUR_API_KEY"}
# File upload
with open("invoice.pdf", "rb") as f:
files = {"file": f}
data = {"fo_id": "fo_1759714105892"}
response = requests.post(url, headers=headers, data=data, files=files)
print(response.json())
JavaScript/Node.js¶
const FormData = require('form-data');
const fs = require('fs');
const axios = require('axios');
const form = new FormData();
form.append('fo_id', 'fo_1759714105892');
form.append('file', fs.createReadStream('invoice.pdf'));
axios.post('https://deeptagger.com/api/v1/extract_data', form, {
headers: {
'x-api-key': 'YOUR_API_KEY',
...form.getHeaders()
}
})
.then(response => console.log(response.data))
.catch(error => console.error(error));
Response¶
Success (200 OK)¶
{
"invoice_number": "INV-2025-001",
"date": "2025-01-15",
"total": "$1,234.56",
"vendor": "Acme Corp"
}
The structure depends on your project configuration.
Errors¶
See Error Handling for detailed error responses.
Supported File Types¶
- PDF (
.pdf
) - Images (
.jpg
,.jpeg
,.png
,.tiff
) - Text (via
text
parameter)
Maximum file size: Check your plan limits.
Processing Time¶
- Text: ~2-5 seconds
- PDF: ~5-15 seconds
- Images: ~3-10 seconds
Next Steps¶
- Error Handling
- Rate Limits
- n8n Integration (recommended for automation)