Skip to main content
GET
/
extract
/
{job_id}
curl -X GET "https://prod.visionapi.unsiloed.ai/extract/{job_id}" \
  -H "api-key: your-api-key"

{
  "job_id": "36b2c5dc-942c-4b20-8451-39764246f9aa",
  "status": "completed",
  "file_name": "invoice.pdf",
  "created_at": "2026-01-19T21:10:51.324693+00:00",
  "updated_at": "2026-01-19T21:10:55.165642+00:00",
  "metadata": {
    "order": ["invoice_number", "company_name", "total_amount"],
    "page_count": 1
  },
  "result": {
    "invoice_number": {
      "score": 0.7970692802977641,
      "value": "25G1IZT000009999",
      "bboxes": [
        {
          "bbox": [150, 80, 320, 110]
        }
      ],
      "page_no": 1
    },
    "company_name": {
      "score": 0.9945,
      "value": "Acme Corporation",
      "bboxes": [
        {
          "bbox": [72, 100, 400, 140]
        }
      ],
      "page_no": 1
    },
    "total_amount": {
      "score": 0.9876,
      "value": "1250000",
      "bboxes": [
        {
          "bbox": [150, 250, 300, 280]
        }
      ],
      "page_no": 1
    }
  }
}

​
Overview

The Get Job Results endpoint retrieves the processed data from a completed job. This endpoint should only be called after confirming the job status is “COMPLETED” using the status endpoint.
Results are only available for completed jobs. Check job status first to ensure processing has finished.

​
Response

The response structure depends on the job type (extraction, parsing, classification, etc.).

​
Extraction Job Results

​
job_id
string
Unique identifier for the extraction job
​
status
string
Current status of the job (e.g., “completed”, “processing”, “failed”)
​
file_name
string | null
Original filename of the uploaded document
​
created_at
string
ISO 8601 timestamp when the job was created
​
updated_at
string
ISO 8601 timestamp when the job was last updated
​
metadata
object
Job metadata containing:
  • order: Array of extracted field names in order
  • page_count: Number of pages in the document
​
result
object
The extracted data matching the provided JSON schema. Each field contains:
  • score: Confidence score (0-1) for the extraction
  • value: The extracted value
  • bboxes: Array of bounding box objects with bbox coordinates
  • page_no: Page number where the value was found (1-indexed)
curl -X GET "https://prod.visionapi.unsiloed.ai/extract/{job_id}" \
  -H "api-key: your-api-key"

{
  "job_id": "36b2c5dc-942c-4b20-8451-39764246f9aa",
  "status": "completed",
  "file_name": "invoice.pdf",
  "created_at": "2026-01-19T21:10:51.324693+00:00",
  "updated_at": "2026-01-19T21:10:55.165642+00:00",
  "metadata": {
    "order": ["invoice_number", "company_name", "total_amount"],
    "page_count": 1
  },
  "result": {
    "invoice_number": {
      "score": 0.7970692802977641,
      "value": "25G1IZT000009999",
      "bboxes": [
        {
          "bbox": [150, 80, 320, 110]
        }
      ],
      "page_no": 1
    },
    "company_name": {
      "score": 0.9945,
      "value": "Acme Corporation",
      "bboxes": [
        {
          "bbox": [72, 100, 400, 140]
        }
      ],
      "page_no": 1
    },
    "total_amount": {
      "score": 0.9876,
      "value": "1250000",
      "bboxes": [
        {
          "bbox": [150, 250, 300, 280]
        }
      ],
      "page_no": 1
    }
  }
}

​
Complete Workflow Example

Here’s a complete example of submitting a job, monitoring its progress, and retrieving results: 
import requests
import time
import json

def process_document_with_results(file_path, schema, api_key):
    """Complete workflow: submit job, wait for completion, get results"""
    
    headers = {"api-key": api_key}
    
    # Step 1: Submit extraction job
    files = {"pdf_file": open(file_path, "rb")}
    data = {"schema_data": json.dumps(schema)}
    
    response = requests.post(
        "https://prod.visionapi.unsiloed.ai/extract",
        files=files,
        data=data,
        headers=headers
    )
    
    if response.status_code != 200:
        raise Exception(f"Failed to submit job: {response.text}")
    
    job_id = response.json()["job_id"]
    print(f"Job submitted: {job_id}")
    
    # Step 2: Poll for completion
    while True:
        status_response = requests.get(
            f"https://prod.visionapi.unsiloed.ai/extract/{job_id}",
            headers=headers
        )
        
        if status_response.status_code != 200:
            raise Exception(f"Failed to check status: {status_response.text}")
            
        job = status_response.json()
        status = job["status"]
        print(f"Job status: {status}")
        
        if status == "COMPLETED" or status == "completed":
            break
        elif status == "FAILED" or status == "failed":
            raise Exception(f"Job failed: {job.get('error', 'Unknown error')}")
        
        time.sleep(5)  # Wait 5 seconds before checking again
    
    # Step 3: Get results
    results_response = requests.get(
        f"https://prod.visionapi.unsiloed.ai/extract/{job_id}",
        headers=headers
    )
    
    if results_response.status_code != 200:
        raise Exception(f"Failed to get results: {results_response.text}")
    
    return results_response.json()

# Usage example
schema = {
    "type": "object",
    "properties": {
        "company_name": {
            "type": "string",
            "description": "Name of the company"
        },
        "total_amount": {
            "type": "number",
            "description": "Total financial amount"
        }
    },
    "required": ["company_name"],
    "additionalProperties": False
}

try:
    results = process_document_with_results("document.pdf", schema, "your-api-key")
    print("Extraction completed!")
    print("Results:", results)
except Exception as e:
    print(f"Error: {e}")

​
Result Data Structure

​
Extracted Field Format

Each extracted field in the result object contains:
  • score: A confidence score between 0 and 1 indicating extraction confidence
  • value: The extracted value as a string
  • bboxes: Array of bounding box objects indicating where the value was found
  • page_no: The page number where the value was located (1-indexed)

​
Bounding Box Format

Bounding boxes use the format [x1, y1, x2, y2] where:
  • x1, y1: Top-left corner coordinates
  • x2, y2: Bottom-right corner coordinates
  • Coordinates are in pixels from the top-left of the page
  • Page numbers are 1-indexed

​
Confidence Scores

  • 0.9-1.0: Very high confidence, extraction is very likely correct
  • 0.8-0.9: High confidence, extraction is likely correct
  • 0.7-0.8: Good confidence, may warrant review for critical applications
  • 0.6-0.7: Medium confidence, should be reviewed
  • Below 0.6: Low confidence, likely needs manual verification

​
Error Handling

The job hasn’t completed yet. Wait for the status to change to “COMPLETED” before requesting results.
The job encountered an error during processing. Check the error message for details about what went wrong.
Either the job doesn’t exist, or the results have been cleaned up. Results are typically stored for 7 days.
The job ID is invalid or the job has been deleted. Verify you’re using the correct job ID.

Authorizations

​
api-key
string
header
required

Path Parameters

​
job_id
string
required

The unique identifier of the extraction job

Response

200 - application/json

Extraction job status and results retrieved successfully

Extraction job status and results