Extract Data

curl -X POST "https://prod.visionapi.unsiloed.ai/v2/extract" \
  -H "accept: application/json" \
  -H "api-key: your-api-key" \
  -H "Content-Type: multipart/form-data" \
  -F "pdf_file=@document.pdf;type=application/pdf" \
  -F "schema_data={\"type\":\"object\",\"properties\":{\"title\":{\"type\":\"string\",\"description\":\"Document title\"},\"date\":{\"type\":\"string\",\"description\":\"Document date\"}},\"required\":[\"title\",\"date\"],\"additionalProperties\":false}"

import requests
import json

url = "https://prod.visionapi.unsiloed.ai/v2/extract"
headers = {
    "accept": "application/json",
    "api-key": "your-api-key"
}

# Define extraction schema using JSON Schema format
schema = {
    "type": "object",
    "properties": {
        "title": {
            "type": "string",
            "description": "Document title"
        },
        "date": {
            "type": "string",
            "description": "Document date"
        }
    },
    "required": ["title", "date"],
    "additionalProperties": False
}

# Prepare file and schema data
files = {
    "pdf_file": ("document.pdf", open("document.pdf", "rb"), "application/pdf")
}

data = {
    "schema_data": json.dumps(schema)
}

# Optional: Enable citations
# data["enable_citations"] = "true"

# Optional: Select model tier (default: gamma)
# data["model"] = "gamma"

# Optional: Agentic verification & validation layer for higher accuracy (slower)
# data["high_accuracy_mode"] = "true"

response = requests.post(url, headers=headers, files=files, data=data)

if response.status_code == 200:
    result = response.json()
    print(f"Extraction job created: {result['job_id']}")
    print(f"Status: {result['status']}")
    print(f"Quota remaining: {result['quota_remaining']}")
else:
    print("Error:", response.status_code, response.text)

files["pdf_file"][1].close()

const formData = new FormData();
formData.append('pdf_file', fileInput.files[0]);

const schema = {
  type: "object",
  properties: {
    title: {
      type: "string",
      description: "Document title"
    },
    date: {
      type: "string",
      description: "Document date"
    }
  },
  required: ["title", "date"],
  additionalProperties: false
};

formData.append('schema_data', JSON.stringify(schema));

// Optional: Enable citations
// formData.append('enable_citations', 'true');

// Optional: Select model tier (default: gamma)
// formData.append('model', 'gamma');

// Optional: Agentic verification & validation layer for higher accuracy (slower)
// formData.append('high_accuracy_mode', 'true');

const response = await fetch('https://prod.visionapi.unsiloed.ai/v2/extract', {
  method: 'POST',
  headers: {
    'accept': 'application/json',
    'api-key': 'your-api-key'
  },
  body: formData
});

if (response.ok) {
  const result = await response.json();
  console.log(`Extraction job created: ${result.job_id}`);
  console.log(`Status: ${result.status}`);
  console.log(`Quota remaining: ${result.quota_remaining}`);

  // Poll for job completion using GET /extract/{job_id}

} else {
  console.error('Extraction failed:', response.status, await response.text());
}

{
  "job_id": "945b4578-691f-4c74-8184-dde654093b11",
  "status": "queued",
  "message": "PDF citation processing started",
  "quota_remaining": 48988
}

{
  "detail": "Either pdf_file or file_url must be provided"
}

POST

extract

curl -X POST "https://prod.visionapi.unsiloed.ai/v2/extract" \
  -H "accept: application/json" \
  -H "api-key: your-api-key" \
  -H "Content-Type: multipart/form-data" \
  -F "pdf_file=@document.pdf;type=application/pdf" \
  -F "schema_data={\"type\":\"object\",\"properties\":{\"title\":{\"type\":\"string\",\"description\":\"Document title\"},\"date\":{\"type\":\"string\",\"description\":\"Document date\"}},\"required\":[\"title\",\"date\"],\"additionalProperties\":false}"

import requests
import json

url = "https://prod.visionapi.unsiloed.ai/v2/extract"
headers = {
    "accept": "application/json",
    "api-key": "your-api-key"
}

# Define extraction schema using JSON Schema format
schema = {
    "type": "object",
    "properties": {
        "title": {
            "type": "string",
            "description": "Document title"
        },
        "date": {
            "type": "string",
            "description": "Document date"
        }
    },
    "required": ["title", "date"],
    "additionalProperties": False
}

# Prepare file and schema data
files = {
    "pdf_file": ("document.pdf", open("document.pdf", "rb"), "application/pdf")
}

data = {
    "schema_data": json.dumps(schema)
}

# Optional: Enable citations
# data["enable_citations"] = "true"

# Optional: Select model tier (default: gamma)
# data["model"] = "gamma"

# Optional: Agentic verification & validation layer for higher accuracy (slower)
# data["high_accuracy_mode"] = "true"

response = requests.post(url, headers=headers, files=files, data=data)

if response.status_code == 200:
    result = response.json()
    print(f"Extraction job created: {result['job_id']}")
    print(f"Status: {result['status']}")
    print(f"Quota remaining: {result['quota_remaining']}")
else:
    print("Error:", response.status_code, response.text)

files["pdf_file"][1].close()

const formData = new FormData();
formData.append('pdf_file', fileInput.files[0]);

const schema = {
  type: "object",
  properties: {
    title: {
      type: "string",
      description: "Document title"
    },
    date: {
      type: "string",
      description: "Document date"
    }
  },
  required: ["title", "date"],
  additionalProperties: false
};

formData.append('schema_data', JSON.stringify(schema));

// Optional: Enable citations
// formData.append('enable_citations', 'true');

// Optional: Select model tier (default: gamma)
// formData.append('model', 'gamma');

// Optional: Agentic verification & validation layer for higher accuracy (slower)
// formData.append('high_accuracy_mode', 'true');

const response = await fetch('https://prod.visionapi.unsiloed.ai/v2/extract', {
  method: 'POST',
  headers: {
    'accept': 'application/json',
    'api-key': 'your-api-key'
  },
  body: formData
});

if (response.ok) {
  const result = await response.json();
  console.log(`Extraction job created: ${result.job_id}`);
  console.log(`Status: ${result.status}`);
  console.log(`Quota remaining: ${result.quota_remaining}`);

  // Poll for job completion using GET /extract/{job_id}

} else {
  console.error('Extraction failed:', response.status, await response.text());
}

{
  "job_id": "945b4578-691f-4c74-8184-dde654093b11",
  "status": "queued",
  "message": "PDF citation processing started",
  "quota_remaining": 48988
}

{
  "detail": "Either pdf_file or file_url must be provided"
}

Overview

The /v2/extract endpoint extracts structured data from PDF documents. It supports optional bounding box citations and handles large documents efficiently.

The endpoint returns a job ID for asynchronous processing. Use the job management endpoints to check status and retrieve results.

Request

file

The PDF file to process for data extraction. Maximum file size: 500MB. Either pdf_file or file_url must be provided.

string

URL to a PDF file to process. Either pdf_file or file_url must be provided.

string

required

JSON schema defining the structure and fields to extract from the document. Must be a valid JSON Schema format with type definitions, properties, and required fields.

string

default:"gamma"

Model tier to use for extraction. Available tiers: alpha, beta, gamma, delta.Recommended: gamma (default), the thorough tier. Tiers: alpha (fast), beta (balanced), gamma (thorough), delta (advanced).

boolean

default:"false"

Return bounding box coordinates for extracted values. When enabled, each extracted field includes a citation object with precise location data in the source document.

boolean

default:"false"

Enable an agentic verification and validation layer for higher accuracy and consistency. Extracted values are independently cross-checked against the document, and only fields flagged as uncertain are re-verified and reconciled before the result is returned. Slower; off by default. Set to true to enable per request.

string

Optional name identifying the schema, stored with the job for traceability.

boolean

default:"false"

Run a pre-flight PII check before extraction. If PII is found at or above pii_block_severity, no extraction job is created and the endpoint returns HTTP 200 with "status": "pii_blocked" and "blocked": true in the body, so check those fields before polling.

string

default:"standard"

PII detection engine used when detect_pii is enabled: standard (default) or advanced (higher precision).

string

default:"high"

Severity threshold that blocks extraction when detect_pii is enabled: any, low, medium, or high.

Response

string

Unique identifier for the extraction job

string

Initial job status (typically “queued”)

string

Descriptive message about the job creation

number

Number of Credits remaining in your quota

PII-Blocked Response

When detect_pii is enabled and PII at or above the threshold is found, the endpoint returns HTTP 200 with no job created. Check status and blocked to tell this apart from a normal submission. The reason is "pii_detected" when pii_block_severity is any, or "pii_detected:<severity>" for the other thresholds:

{
  "job_id": null,
  "status": "pii_blocked",
  "blocked": true,
  "reason": "pii_detected:high",
  "severity": "high",
  "engine": "standard",
  "ocr_used": true,
  "total_findings": 4,
  "by_category": {"financial": 2, "contact": 2},
  "by_type": {"CREDIT_CARD": 2, "EMAIL_ADDRESS": 2},
  "summary": null,
  "spans": []
}

Extraction Results Format

Once the job is completed, the results will contain the extracted data with additional metadata:

object

Each extracted field returns an object with the following structure:

string|number|array|object

The extracted value matching the schema type

object

Confidence scores for the field:

Show score_structure

number

Confidence (0-1) that the value was located in the document. 0.0 when citations are disabled.

number | null

Confidence (0-1) in the extracted value itself.

object | null

Where the value was found. null when citations are disabled or the value could not be grounded:

Show citation_structure

array

Bounding box [left, top, right, bottom] in PDF point space (origin: top-left).

number

Page number where the value was found (1-indexed).

number

Page width in PDF points.

number

Page height in PDF points.

Example Extraction Results

For a simple financial document schema:

Schema

{
  "type": "object",
  "properties": {
    "Individuals": {
      "type": "string",
      "description": "Percentage Holding"
    },
    "LIC of India": {
      "type": "string",
      "description": "No of Shares Held"
    },
    "United bank of india": {
      "type": "string",
      "description": "No of shares held by United bank of india"
    }
  },
  "required": [
    "Individuals",
    "LIC of India",
    "United bank of india"
  ],
  "additionalProperties": false
}

Extraction Results

{
  "Individuals": {
    "value": "10.57",
    "score": {
      "grounding_score": 0.97,
      "extraction_score": 0.99
    },
    "citation": {
      "bbox": [79, 381, 524, 565],
      "page": 2,
      "page_width": 612,
      "page_height": 792
    }
  },
  "LIC of India": {
    "value": "1515000",
    "score": {
      "grounding_score": 0.98,
      "extraction_score": 0.99
    },
    "citation": {
      "bbox": [79, 381, 524, 565],
      "page": 2,
      "page_width": 612,
      "page_height": 792
    }
  },
  "United bank of india": {
    "value": "500000",
    "score": {
      "grounding_score": 0.99,
      "extraction_score": 0.99
    },
    "citation": {
      "bbox": [79, 381, 524, 565],
      "page": 2,
      "page_width": 612,
      "page_height": 792
    }
  }
}

curl -X POST "https://prod.visionapi.unsiloed.ai/v2/extract" \
  -H "accept: application/json" \
  -H "api-key: your-api-key" \
  -H "Content-Type: multipart/form-data" \
  -F "pdf_file=@document.pdf;type=application/pdf" \
  -F "schema_data={\"type\":\"object\",\"properties\":{\"title\":{\"type\":\"string\",\"description\":\"Document title\"},\"date\":{\"type\":\"string\",\"description\":\"Document date\"}},\"required\":[\"title\",\"date\"],\"additionalProperties\":false}"

import requests
import json

url = "https://prod.visionapi.unsiloed.ai/v2/extract"
headers = {
    "accept": "application/json",
    "api-key": "your-api-key"
}

# Define extraction schema using JSON Schema format
schema = {
    "type": "object",
    "properties": {
        "title": {
            "type": "string",
            "description": "Document title"
        },
        "date": {
            "type": "string",
            "description": "Document date"
        }
    },
    "required": ["title", "date"],
    "additionalProperties": False
}

# Prepare file and schema data
files = {
    "pdf_file": ("document.pdf", open("document.pdf", "rb"), "application/pdf")
}

data = {
    "schema_data": json.dumps(schema)
}

# Optional: Enable citations
# data["enable_citations"] = "true"

# Optional: Select model tier (default: gamma)
# data["model"] = "gamma"

# Optional: Agentic verification & validation layer for higher accuracy (slower)
# data["high_accuracy_mode"] = "true"

response = requests.post(url, headers=headers, files=files, data=data)

if response.status_code == 200:
    result = response.json()
    print(f"Extraction job created: {result['job_id']}")
    print(f"Status: {result['status']}")
    print(f"Quota remaining: {result['quota_remaining']}")
else:
    print("Error:", response.status_code, response.text)

files["pdf_file"][1].close()

const formData = new FormData();
formData.append('pdf_file', fileInput.files[0]);

const schema = {
  type: "object",
  properties: {
    title: {
      type: "string",
      description: "Document title"
    },
    date: {
      type: "string",
      description: "Document date"
    }
  },
  required: ["title", "date"],
  additionalProperties: false
};

formData.append('schema_data', JSON.stringify(schema));

// Optional: Enable citations
// formData.append('enable_citations', 'true');

// Optional: Select model tier (default: gamma)
// formData.append('model', 'gamma');

// Optional: Agentic verification & validation layer for higher accuracy (slower)
// formData.append('high_accuracy_mode', 'true');

const response = await fetch('https://prod.visionapi.unsiloed.ai/v2/extract', {
  method: 'POST',
  headers: {
    'accept': 'application/json',
    'api-key': 'your-api-key'
  },
  body: formData
});

if (response.ok) {
  const result = await response.json();
  console.log(`Extraction job created: ${result.job_id}`);
  console.log(`Status: ${result.status}`);
  console.log(`Quota remaining: ${result.quota_remaining}`);

  // Poll for job completion using GET /extract/{job_id}

} else {
  console.error('Extraction failed:', response.status, await response.text());
}

{
  "job_id": "945b4578-691f-4c74-8184-dde654093b11",
  "status": "queued",
  "message": "PDF citation processing started",
  "quota_remaining": 48988
}

{
  "detail": "Either pdf_file or file_url must be provided"
}

Citations

The enable_citations parameter controls whether bounding box coordinates are returned with extracted data. Citations provide references back to the source document, allowing you to trace where each extracted value was found.

With Citations Enabled

When enable_citations is set to True, each extracted field includes a citation object with precise location data (or null when the value could not be grounded):

{
  "invoice_number": {
    "value": "INV-2025-001",
    "score": {
      "grounding_score": 0.97,
      "extraction_score": 0.99
    },
    "citation": {
      "bbox": [139, 209, 280, 222],
      "page": 1,
      "page_width": 595,
      "page_height": 842
    }
  }
}

Bbox coordinate system:

bbox: [left, top, right, bottom] in PDF point space (origin: top-left)
Standard A4 page = 595 x 842 points
page_width / page_height included for scaling to any display size

Without Citations (Default)

When enable_citations is False (default), no grounding pass runs. On the default gamma tier each field still uses the nested shape, with grounding_score: 0.0 and citation: null. On the alpha, beta, and delta tiers the response uses a legacy flat shape instead: {"value": ..., "score": <number>} with no citation key. The nested gamma shape:

{
  "invoice_number": {
    "value": "INV-2025-001",
    "score": {
      "grounding_score": 0.0,
      "extraction_score": 0.97
    },
    "citation": null
  }
}

Set enable_citations to True when you need to trace extracted values back to their exact location in the document, such as for UI highlighting or audit trails.

JSON Schema Definition

The schema_data parameter must be a valid JSON Schema that defines the structure of data to extract. All schemas must follow the JSON Schema specification with proper type definitions, properties, and constraints.

Basic Schema Structure

All extraction schemas must include:

type: “object” (root level)
properties: Object defining the fields to extract
required: Array of required field names
additionalProperties: Set to False for strict validation

Financial Document Schema Example

This example demonstrates extracting shareholding patterns and board information from financial documents:

{
  "type": "object",
  "properties": {
    "Individuals": {
      "type": "string",
      "description": "Percentage Holding"
    },
    "LIC of India": {
      "type": "number",
      "description": "No of Shares Held"
    },
    "board of directors": {
      "type": "array",
      "description": "list of names of board of directors",
      "items": {
        "type": "object",
        "required": [
          "names of board of directors"
        ],
        "properties": {
          "names of board of directors": {
            "type": "string",
            "description": "names of all the members of board of directors of ACRE"
          }
        },
        "additionalProperties": false
      }
    },
    "shareholding pattern": {
      "type": "array",
      "description": "shareholding pattern",
      "items": {
        "type": "object",
        "required": [
          "name of shareholders",
          "number of shares held"
        ],
        "properties": {
          "name of shareholders": {
            "type": "string",
            "description": "name of the shareholders in ACRE Table"
          },
          "number of shares held": {
            "type": "string",
            "description": "numbers of shares held by shareholders in ACRE Table"
          }
        },
        "additionalProperties": false
      }
    }
  },
  "required": [
    "Individuals",
    "LIC of India",
    "board of directors",
    "shareholding pattern"
  ],
  "additionalProperties": false
}

Advanced Financial Schema Example

This example shows a more complex schema for extracting detailed shareholding information:

{
  "type": "object",
  "properties": {
    "shares held by Punjab National bank": {
      "type": "string",
      "description": "shares held by Punjab National bank"
    },
    "shares held by IFCI": {
      "type": "string",
      "description": "shares held by IFCI"
    },
    "shareholding pattern": {
      "type": "object",
      "description": "shareholding pattern",
      "properties": {
        "Percentage holding": {
          "type": "array",
          "description": "percentage holding of shareholders in ACRE",
          "items": {
            "type": "string",
            "description": "percentage holding of shareholders in ACRE"
          }
        },
        "Name of shareholders": {
          "type": "array",
          "description": "Names of shareholders in ACRE",
          "items": {
            "type": "string",
            "description": "Names of shareholders in ACRE"
          }
        }
      },
      "required": ["Percentage holding", "Name of shareholders"],
      "additionalProperties": false
    },
    "names of board of directors": {
      "type": "array",
      "description": "list of names of members of board of directors in ACRE",
      "items": {
        "type": "object",
        "properties": {
          "names of board of directors": {
            "type": "string",
            "description": "list of names of members of board of directors in ACRE"
          }
        },
        "required": ["names of board of directors"],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "shares held by Punjab National bank", 
    "shares held by IFCI", 
    "shareholding pattern", 
    "names of board of directors"
  ],
  "additionalProperties": false
}

Citation Extraction Schema

{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Document title or paper title"
    },
    "authors": {
      "type": "array",
      "description": "List of author names",
      "items": {
        "type": "string"
      }
    },
    "publication_date": {
      "type": "string",
      "description": "Publication date in YYYY-MM-DD format"
    },
    "journal_name": {
      "type": "string",
      "description": "Name of journal or publication venue"
    },
    "doi": {
      "type": "string",
      "description": "Digital Object Identifier"
    },
    "abstract": {
      "type": "string",
      "description": "Document abstract or summary"
    },
    "keywords": {
      "type": "array",
      "description": "Key terms and subject keywords",
      "items": {
        "type": "string"
      }
    },
    "references": {
      "type": "array",
      "description": "List of cited references",
      "items": {
        "type": "string"
      }
    }
  },
  "required": ["title", "authors"],
  "additionalProperties": false
}

Legal Document Schema

{
  "type": "object",
  "properties": {
    "document_type": {
      "type": "string",
      "description": "Type of legal document (contract, agreement, etc.)"
    },
    "parties": {
      "type": "array",
      "description": "Names of parties involved",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string",
            "description": "Party name"
          },
          "role": {
            "type": "string",
            "description": "Party role (e.g., buyer, seller, contractor)"
          }
        },
        "required": ["name", "role"],
        "additionalProperties": false
      }
    },
    "effective_date": {
      "type": "string",
      "description": "Document effective date"
    },
    "key_terms": {
      "type": "array",
      "description": "Important terms and conditions",
      "items": {
        "type": "string"
      }
    },
    "obligations": {
      "type": "array",
      "description": "Key obligations and responsibilities",
      "items": {
        "type": "object",
        "properties": {
          "party": {
            "type": "string",
            "description": "Party responsible for the obligation"
          },
          "obligation": {
            "type": "string",
            "description": "Description of the obligation"
          }
        },
        "required": ["party", "obligation"],
        "additionalProperties": false
      }
    }
  },
  "required": ["document_type", "parties", "effective_date"],
  "additionalProperties": false
}

JSON Schema Field Types

string

Text content, single values. Use for names, descriptions, dates as text.

number

Numeric values, amounts, quantities. Use for counts, percentages, monetary values.

integer

Whole numbers only. Use for counts, IDs, years.

boolean

True/false values. Use for yes/no questions, flags.

array

Lists of items. Must include items property defining the type of array elements.

object

Structured data with nested fields. Must include properties defining nested structure.

null

Null values. Can be combined with other types using array notation: ["string", "null"]

Job Management Integration

After creating an extraction job, you can poll for completion using the job status endpoints:

import requests
import time

# After creating the extraction job, you receive a job_id
job_id = "945b4578-691f-4c74-8184-dde654093b11"

headers = {
    "accept": "application/json",
    "api-key": "your-api-key"
}

# Poll for job completion
while True:
    response = requests.get(
        f"https://prod.visionapi.unsiloed.ai/extract/{job_id}",
        headers=headers
    )

    if response.status_code == 200:
        result = response.json()
        status = result.get("status", "").lower()
        print(f"Job status: {status}")

        if status == "completed":
            print("Extraction completed!")
            print("Extracted data:", result.get("result"))
            break
        elif status == "failed":
            print(f"Job failed: {result.get('error', 'Unknown error')}")
            break
    else:
        print(f"Error checking status: {response.status_code}")
        break

    time.sleep(5)  # Wait 5 seconds before checking again

Advanced Schema Patterns

Nested Object Structures

For complex documents with hierarchical data:

{
  "type": "object",
  "properties": {
    "company_info": {
      "type": "object",
      "description": "Company identification and basic information",
      "properties": {
        "name": {
          "type": "string",
          "description": "Full company name"
        },
        "ticker": {
          "type": "string",
          "description": "Stock ticker symbol"
        },
        "sector": {
          "type": "string",
          "description": "Business sector"
        }
      },
      "required": ["name"],
      "additionalProperties": false
    },
    "financial_data": {
      "type": "object",
      "description": "Financial metrics and performance data",
      "properties": {
        "revenue": {
          "type": "number",
          "description": "Total revenue"
        },
        "profit_margin": {
          "type": "number",
          "description": "Profit margin percentage"
        }
      },
      "required": ["revenue"],
      "additionalProperties": false
    }
  },
  "required": ["company_info", "financial_data"],
  "additionalProperties": false
}

Array of Complex Objects

For extracting lists of structured data:

{
  "type": "object",
  "properties": {
    "transactions": {
      "type": "array",
      "description": "List of financial transactions",
      "items": {
        "type": "object",
        "properties": {
          "date": {
            "type": "string",
            "description": "Transaction date"
          },
          "amount": {
            "type": "number",
            "description": "Transaction amount"
          },
          "description": {
            "type": "string",
            "description": "Transaction description"
          },
          "category": {
            "type": "string",
            "description": "Transaction category"
          }
        },
        "required": ["date", "amount", "description"],
        "additionalProperties": false
      }
    }
  },
  "required": ["transactions"],
  "additionalProperties": false
}

Error Handling

Bad Request

Invalid JSON schema format or missing required parameters

Unauthorized

Invalid or missing API key

Payment Required

Insufficient or expired credits

Payload Too Large

File size exceeds the 500MB limit

Unprocessable Entity

Invalid file format, malformed JSON schema, or processing error

Too Many Requests

Rate limit exceeded

Internal Server Error

Server error during processing

Authorizations

api-key

string

header

required

Body

multipart/form-data

schema_data

string

required

JSON schema defining the structure and fields to extract from the document. Example: {"type":"object","properties":{"invoice_number":{"type":"string","description":"The invoice number"}},"required":["invoice_number"],"additionalProperties":false}

pdf_file

file

The PDF file to process for data extraction. Maximum file size: 500MB. Either pdf_file or file_url must be provided.

file_url

string

URL to a PDF file to process. Either pdf_file or file_url must be provided.

model

enum<string>

default:gamma

Model tier to use for extraction. Options: alpha, beta, gamma (default, recommended), delta

Available options:

alpha,

beta,

gamma,

delta

enable_citations

boolean

default:false

Return bounding box coordinates for extracted values

high_accuracy_mode

boolean

default:false

Enable an agentic verification and validation layer for higher accuracy/consistency. Extracted values are independently cross-checked against the document and uncertain fields are re-verified and reconciled before the result is returned. Slower. Off by default; set true to enable per request.

schema_name

string | null

Optional name identifying the schema, stored with the job for traceability.

detect_pii

boolean

default:false

Run a pre-flight PII check before extraction. If PII is found at or above pii_block_severity, no extraction job is created and the endpoint returns HTTP 200 with "status": "pii_blocked" and "blocked": true in the body.

pii_engine

enum<string>

default:standard

PII detection engine: 'standard' (default) or 'advanced' (higher precision).

Available options:

standard,

advanced

pii_block_severity

enum<string>

default:high

Severity threshold that blocks extraction when detect_pii is enabled: 'any', 'low', 'medium', or 'high'.

Available options:

any,

low,

medium,

high

Response

200 - application/json

Successful response

job_id

string

Unique identifier for the extraction job

status

string

Initial job status (typically 'queued')

message

string

Descriptive message about the job creation

quota_remaining

number

Number of Credits remaining in your quota

Parsing

Extraction

Classification

Splitting

Organization

Overview

Request

Response

PII-Blocked Response

Extraction Results Format

Example Extraction Results

Citations

With Citations Enabled

Without Citations (Default)

JSON Schema Definition

Basic Schema Structure

Financial Document Schema Example

Advanced Financial Schema Example

Citation Extraction Schema

Legal Document Schema

JSON Schema Field Types

Job Management Integration

Advanced Schema Patterns

Nested Object Structures

Array of Complex Objects

Error Handling

Authorizations

Body

Response

​Overview

​Request

​Response

​PII-Blocked Response

​Extraction Results Format

​Example Extraction Results

​Citations

​With Citations Enabled

​Without Citations (Default)

​JSON Schema Definition

​Basic Schema Structure

​Financial Document Schema Example

​Advanced Financial Schema Example

​Citation Extraction Schema

​Legal Document Schema

​JSON Schema Field Types

​Job Management Integration

​Advanced Schema Patterns

​Nested Object Structures

​Array of Complex Objects

​Error Handling

Authorizations

Body

Response

Overview

Request

Response

PII-Blocked Response

Extraction Results Format

Example Extraction Results

Citations

With Citations Enabled

Without Citations (Default)

JSON Schema Definition

Basic Schema Structure

Financial Document Schema Example

Advanced Financial Schema Example

Citation Extraction Schema

Legal Document Schema

JSON Schema Field Types

Job Management Integration

Advanced Schema Patterns

Nested Object Structures

Array of Complex Objects

Error Handling