Extraction Quick Start

Quickest way to get started using the client libraries.

Installation Instructions

Requires Python ≥ 3.9. Python ≥ 3.11 is recommended.

Simply install the PyPi package using pip:

pip install -U mindee~=5.3

Requires Node.js ≥ 20.1. Node.js ≥ 22 is recommended.

Simply install the NPM package:

npm install mindee@^5.5.0

Requires PHP ≥ 8.1. PHP ≥ 8.3 is recommended.

Simply install the Packagist package using composer:

php composer.phar require "mindee/mindee:>=3.2"

Requires Ruby ≥ 3.2.

Simply install the gem using:

gem install mindee -v '~> 5.4'

Requires Java ≥ 11. Java ≥ 17 is recommended.

Group ID: com.mindee.sdk Artifact ID: mindee-api-java Version: 5.5.0 or greater

There are various installation methods, Maven, Gradle, etc:

Installation Details

.NET ≥ 8.0 is recommended.

Simply install the NuGet package using dotnet add:

dotnet add package Mindee --version 4.8

Don't see support for your favorite language or framework? Make a feature request!

Send a File and Poll

Make a note of your model's ID for use in the API.

When getting started, we recommend using the polling method which will be quickest (unless you happen to already have access to a public-facing Web server).

Here are basic code examples, these are self-contained and can be run as-is:

Requires Python ≥ 3.10. Python ≥ 3.12 is recommended. Requires the Mindee Python client library version 5.3.1 or greater.

from mindee import PathInput
from mindee.v2 import (
    Client,
    ExtractionParameters,
    ExtractionResponse,
)

input_path = "/path/to/the/file.ext"
api_key = "MY_API_KEY"
model_id = "MY_MODEL_ID"

# Init a new client
mindee_client = Client(api_key)

# Set Extraction parameters
model_params = ExtractionParameters(
    # ID of the model, required.
    model_id=model_id,

    # Options: set to `True` or `False` to override defaults

    # Enhance extraction accuracy with Retrieval-Augmented Generation.
    rag=None,
    # Extract the full text content from the document as strings.
    raw_text=None,
    # Calculate bounding box polygons for all fields.
    polygon=None,
    # Boost the precision and accuracy of all extractions.
    # Calculate confidence scores for all fields.
    confidence=None,
)

# Load a file from disk
input_source = PathInput(input_path)

# Send for processing
response = mindee_client.enqueue_and_get_result(
    ExtractionResponse,
    input_source,
    model_params,
)

# Print a brief summary of the parsed data
print(response.inference)

# Access the result fields
fields: dict = response.inference.result.fields

Also take a look at the Extraction Result documentation.

Requires Node.js ≥ 20.1. Node.js ≥ 22 is recommended. Requires the Mindee Node.js client library version 5.7.1 or greater.

import * as mindee from "mindee";
// If you're on CommonJS:
// const mindee = require("mindee");

const apiKey = "MY_API_KEY";
const filePath = "/path/to/the/file.ext";
const modelId = "MY_MODEL_ID";

// Init a new client
const mindeeClient = new mindee.Client(
  { apiKey: apiKey }
);

// Set Extraction parameters
const modelParams = {
  modelId: modelId,

  // Options: set to `true` or `false` to override defaults

  // Enhance extraction accuracy with Retrieval-Augmented Generation.
  rag: undefined,
  // Extract the full text content from the document as strings.
  rawText: undefined,
  // Calculate bounding box polygons for all fields.
  polygon: undefined,
  // Boost the precision and accuracy of all extractions.
  // Calculate confidence scores for all fields.
  confidence: undefined,
};

// Load a file from disk
const inputSource = new mindee.PathInput({ inputPath: filePath });

// Send for processing
const response = await mindeeClient.enqueueAndGetResult(
  mindee.product.Extraction,
  inputSource,
  modelParams,
);

// print a string summary
console.log(response.inference.toString());

// Access the result fields
const fields = response.inference.result.fields;

Also take a look at the Processing Results documentation.

Requires PHP ≥ 8.1. PHP ≥ 8.3 is recommended. Requires the Mindee PHP client library version 3.2.0 or greater.

<?php

use Mindee\Input\PathInput;
use Mindee\V2\Client;
use Mindee\V2\Product\Extraction\Params\ExtractionParameters;
use Mindee\V2\Product\Extraction\ExtractionResponse;

$apiKey = "MY_API_KEY";
$modelId = "MY_MODEL_ID";
$filePath = "/path/to/the/file.ext";

// Init a new client
$mindeeClient = new Client($apiKey);

// Set Extraction parameters
$modelParams = new ExtractionParameters(
    // ID of the model, required.
    $modelId,

    // Options: set to `true` or `false` to override defaults

    // Enhance extraction accuracy with Retrieval-Augmented Generation.
    rag: null,
    // Extract the full text content from the document as strings.
    rawText: null,
    // Calculate bounding box polygons for all fields.
    polygon: null,
    // Boost the precision and accuracy of all extractions.
    // Calculate confidence scores for all fields.
    confidence: null
);

// Load a file from disk
$inputSource = new PathInput($filePath);

// Send for processing using polling
$response = $mindeeClient->enqueueAndGetResult(
    ExtractionResponse::class,
    $inputSource,
    $modelParams
);

// Print a summary of the response
echo strval($response->inference);

// Access the extracted fields
$fields = $response->inference->result->fields;

Also take a look at the Processing Results documentation.

Requires Ruby ≥ 3.2. Requires the Mindee Ruby client library version 5.4.0 or greater.

require 'mindee'
require 'mindee/v2/product'

input_path = '/path/to/the/file.ext'
api_key = 'MY_API_KEY'
model_id = 'MY_MODEL_ID'

# Init a new client
mindee_client = Mindee::V2::Client.new(api_key: api_key)

# Set Extraction parameters
model_params = {
    # ID of the model, required.
    model_id: model_id,

    # Options: set to `true` or `false` to override defaults

    # Enhance extraction accuracy with Retrieval-Augmented Generation.
    rag: nil,
    # Extract the full text content from the document as strings.
    raw_text: nil,
    # Calculate bounding box polygons for all fields.
    polygon: nil,
    # Boost the precision and accuracy of all extractions.
    # Calculate confidence scores for all fields.
    confidence: nil
}

# Load a file from disk
input_source = Mindee::Input::Source::PathInputSource.new(input_path)

# Send for processing
response = mindee_client.enqueue_and_get_result(
    Mindee::V2::Product::Extraction::Extraction,
    input_source,
    model_params
)

# Print a brief summary of the parsed data
puts response.inference

# Access the result fields
fields = response.inference.result.fields

# fields.get_simple_field('my_simple_field')
# fields.get_list_field('my_list_field')
# fields.get_object_field('my_object_field')

Also take a look at the Processing Results documentation.

Requires Java ≥ 11. Java ≥ 21 is recommended. Requires the Mindee Java SDK version 5.5.0 or greater.

import com.mindee.input.LocalInputSource;
import com.mindee.v2.MindeeClient;
import com.mindee.v2.product.extraction.params.ExtractionParameters;
import com.mindee.v2.product.extraction.ExtractionResponse;
import java.io.IOException;

public class SimpleMindeeClientV2 {

  public static void main(String[] args)
      throws IOException, InterruptedException
  {
    String apiKey = "MY_API_KEY";
    String modelId = "MY_MODEL_ID";
    String filePath = "/path/to/the/file.ext";

    // Init a new client
    var mindeeClient = new MindeeClient(apiKey);

    // Set Extraction parameters
    var modelParams = ExtractionParameters
        // ID of the model, required.
        .builder(modelId)

        // Options: set to `true` or `false` to override defaults

        // Enhance extraction accuracy with Retrieval-Augmented Generation.
        .rag(null)
        // Extract the full text content from the document as strings.
        .rawText(null)
        // Calculate bounding box polygons for all fields.
        .polygon(null)
        // Boost the precision and accuracy of all extractions.
        // Calculate confidence scores for all fields.
        .confidence(null)

        .build();

    // Load a file from disk
    var inputSource = new LocalInputSource(filePath);

    // Send for processing using polling
    ExtractionResponse response = mindeeClient.enqueueAndGetResult(
        ExtractionResponse.class,
        inputSource,
        modelParams
    );

    // Print a summary of the response
    System.out.println(response.getInference().toString());

    // Access the result fields
    var fields = response.getInference().getResult().getFields();
  }
}

Also take a look at the Processing Results documentation.

.NET ≥ 8.0 is recommended. Requires the Mindee .NET client library version 4.8.1 or greater.

using Mindee;
using Mindee.Input;
using Mindee.V2;
using Mindee.V2.Product.Extraction;
using Mindee.V2.Product.Extraction.Params;

string filePath = "/path/to/the/file.ext";
string apiKey = "MY_API_KEY";
string modelId = "MY_MODEL_ID";

// Construct a new client
Client mindeeClient = new Client(apiKey);

// Set Extraction parameters
var modelParams = new ExtractionParameters(
    modelId: modelId

    // Options: set to `true` or `false` to override defaults

    // Enhance extraction accuracy with Retrieval-Augmented Generation.
    , rag: null
    // Extract the full text content from the document as strings.
    , rawText: null
    // Calculate bounding box polygons for all fields.
    , polygon: null
    // Boost the precision and accuracy of all extractions.
    // Calculate confidence scores for all fields.
    , confidence: null
);

// Load a file from disk
var inputSource = new LocalInputSource(filePath);

// Upload the file
var response = await mindeeClient.EnqueueAndGetResultAsync<ExtractionResponse>(
    inputSource, modelParams);

// Print a summary of the response
System.Console.WriteLine(response.Inference.ToString());

// Access the extracted fields
var fields = response.Inference.Result.Fields;

Also take a look at the Processing Results documentation.

Details on Sending

For details on available options and advanced usage, check the following sections:

Process Extraction Results

Once you've sent the file and retrieved the response, you can start accessing the results.

The Extraction model's fields will be in the fields object in the return (the response variable returned from the above step).

Each key in the fields object corresponds to the field's name in your Data Schema.

You'll want to adapt your processing depending on the type of field, for example when looping over lists or accessing sub-fields.

Accessing simple values, using the name of the field in the Data Schema.

You can (should!) specify the type of value, the possible types are str , bool , float . Note that all types may be None.

from mindee.v2 import ExtractionResponse

def handle_response(response: ExtractionResponse):
  fields = response.inference.result.fields

  # texts, dates, classifications ...
  string_field_value: str | None = fields.get_simple_field("string_field").value

  # a JSON float will be a float
  float_field_value: float | None = fields.get_simple_field("float_field").value

  # even if the API always returns an integer, the type will be float
  int_field_value: float | None = fields.get_simple_field("int_field").value

  # booleans
  bool_field_value: bool | None = fields.get_simple_field("bool_field").value

Accessing a list of simple values, where my_list_field is the name of the field in the Model.

from mindee.v2 import ExtractionResponse

def handle_response(response: ExtractionResponse):
    fields = response.inference.result.fields

    simple_list_field = fields.get_list_field("my_simple_list_field")

    # Loop over the list of Simple fields
    for list_item in simple_list_field.items:
        item_value = list_item.value

Accessing an object field and its sub-fields, where my_object_field is the name of the field in the Model. In this hypothetical case, the object has a sub-field named subfield_1 .

from mindee.v2 import ExtractionResponse

def handle_response(response: ExtractionResponse):
    fields = response.inference.result.fields

    object_field = fields.get_object_field("my_object_field")

    sub_fields: dict = object_field.fields

    # grab a single sub-field
    subfield_1 = sub_fields["subfield_1"]

    # loop over sub-fields
    for field_name, sub_field in sub_fields.items():
        sub_field.value

Accessing a list of objects, where my_object_list_field is the name of the field in the Model.

from mindee.v2 import ExtractionResponse

def handle_response(response: ExtractionResponse):
    fields = response.inference.result.fields

    object_list_field = fields.get_list_field("my_object_list_field")

    # Loop over the list of Object fields
    for object_item in object_list_field.items:
        # grab a single sub-field
        sub_field_value = object_item.fields["sub_field"].value
        
        # loop over sub-fields
        for field_name, sub_field in object_item.fields.items():
            sub_field.value

Accessing simple values, using the name of the field in the Data Schema.

Access fields as SimpleField instances when retrieving their value.

handleResponse(response) {
  const fields = response.inference.result.fields;
  
  // texts, dates, classifications ...
  const stringFieldValue = fields.getSimpleField("string_field").stringValue;
  
  // type is 'number', no distinction between floats and integers
  const floatFieldValue = fields.getSimpleField("float_field").numberValue;
  const intFieldValue = fields.getSimpleField("int_field").numberValue;
  
  // booleans
  const boolFieldValue = fields.getSimpleField("bool_field").booleanValue;
}

Accessing a list of values, where my_simple_list_field is the name of the field in the Model.

We need to specify that the field is a ListField in order to access its items.

handleResponse(response) {
  const fields = response.inference.result.fields;

  const simpleListField = fields.getListField("my_simple_list_field");

  const simpleItems = simpleListField.simpleItems;

  // Loop over the list of Simple fields
  for (const itemField of simpleItems) {
    // Choose the appropriate accessor:
    // stringValue, numberValue, booleanValue
    const fieldValue = itemField.stringValue;
  }
}

Accessing an object field and its sub-fields, where my_object_field is the name of the field in the Model. In this hypothetical case, the object has a sub-field named subfield_1 .

handleResponse(response) {
  const fields = response.inference.result.fields;

  const objectField = fields.getObjectField("my_object_field");

  const simpleSubFields = objectField.simpleFields;

  // grab a single sub-field
  const subfield1 = subFields.get("subfield_1");

  // loop over simple sub-fields
  subFields.forEach((simpleSubFields, fieldName) => {
    // Choose the appropriate accessor:
    // stringValue, numberValue, booleanValue
    const fieldValue = subField.stringValue;
  });

  // Object fields can also have lists:
  const listSubFields = objectField.listFields;
}

Accessing a list of objects, where my_object_list_field is the name of the field in the Model.

We need to specify that the field is a ListField in order to access its items.

handleResponse(response) {
  const fields = response.inference.result.fields;

  const fieldObjectList = fields.getListField("my_object_list_field");

  const objectItems = fieldSimpleList.objectItems;

  // Loop over the list of Object fields
  for (const itemField of objectItems) {
    const simpleSubFields = itemField.simpleFields;

    // grab a single sub-field
    const subField1 = subFields.get("subfield_1");

    // Choose the appropriate accessor:
    // stringValue, numberValue, booleanValue
    const subFieldValue = subField1.stringValue;

    // loop over simple sub-fields
    simpleSubFields.forEach((subField, fieldName) => {
      // Choose the appropriate accessor:
      // stringValue, numberValue, booleanValue
      const fieldValue = subField.stringValue;
    });

    // Object fields can also have lists:
    const listSubFields = itemField.listFields;
  }
}

Accessing simple values, using the name of the field in the Data Schema.

Access fields as SimpleField instances when retrieving their value.

use Mindee\V2\Product\Extraction\ExtractionResponse;

public function handleResponse(ExtractionResponse $response)
{
    $fields = $response->inference->result->fields;

    // texts, dates, classifications ...
    $stringFieldValue = $fields->getSimpleField('string_field')->value;

    // a JSON float will be a float
    $floatFieldValue = $fields->getSimpleField('float_field')->value;

    // even if the API always returns an integer, the type will be float
    $intFieldValue = $fields->getSimpleField('int_field')->value;

    // booleans
    $boolFieldValue = $fields->getSimpleField('bool_field')->value;
}

Accessing a list of values, where my_simple_list_field is the name of the field in the Model.

We need to specify that the field is a ListField in order to access its items.

use Mindee\V2\Product\Extraction\ExtractionResponse;

public function handleResponse(ExtractionResponse $response)
{
    $fields = $response->inference->result->fields;

    $simpleListField = $fields->getListField('my_simple_list_field');

    // access a value at a given position
    $fieldFirstValue = $simpleListField->items[0]->value;

    // Loop over the list of Simple fields
    foreach ($simpleListField->items as $listItem) {
        $itemValue = $listItem->value;
    }
}

Accessing an object field and its sub-fields, where my_object_field is the name of the field in the Model. In this hypothetical case, the object has a sub-field named subfield_1 .

use Mindee\V2\Product\Extraction\ExtractionResponse;

public function handleResponse(ExtractionResponse $response)
{
    $fields = $response->inference->result->fields;

    $objectField = $fields->getObjectField('my_object_field');
    $subFields = $objectField->fields;

    // grab a single sub-field
    $subfield1 = $subFields->getSimpleField('subfield_1');

    // loop over sub-fields
    foreach ($subFields as $fieldName => $subField) {
        $fieldValue = $subField->value;
    }
}

Accessing a list of objects, where my_object_list_field is the name of the field in the Model.

We need to specify that the field is a ListField in order to access its items.

use Mindee\V2\Product\Extraction\ExtractionResponse;

public function handleResponse(ExtractionResponse $response)
{
    $fields = $response->inference->result->fields;
    $fieldObjectList = $fields->getObjectField('my_object_list_field');

    // access an object at a given position
    $objectItem0 = $fieldObjectList->items[0];
    $subField0Value = $objectItem0->fields->get('sub_field')->value;

    // Loop over the list of Object fields
    foreach ($myObjectListField->items as $objectItem) {
        $subFieldValue = $objectItem->fields->get('sub_field')->value;
    }
}

Accessing simple values, using the name of the field in the Data Schema.

Access fields as SimpleField instances when retrieving their value.

def handle_response(response)
  fields = response.inference.result.fields

  # texts, dates, classifications ...
  string_field_value = fields.get_simple_field('string_field').string_value

  # a JSON float will be a float
  float_field_value = fields.get_simple_field('float_field').float_value

  # even if the API always returns an integer, the type will be float
  int_field_value = fields.get_simple_field('int_field').float_value

  # booleans
  bool_field_value = fields.get_simple_field('bool_field').boolean_value
end

Accessing a list of values, where my_simple_list_field is the name of the field in the Model.

Access the list as a ListField instance, and the items as SimpleField instances.

def handle_response(response)
  fields = response.inference.result.fields
  
  my_list_field = fields.get_list_field('my_simple_list_field')

  # access a value at a given position
  simple_list_field = my_list_field.simple_items[0].value

  # Loop over the list of Simple fields
  simple_list_field.simple_items.each do |list_item|
    item_value = list_item.value
  end
end

Accessing an object field and its sub-fields, where my_object_field is the name of the field in the Model. In this hypothetical case, the object has a sub-field named subfield_1 .

def handle_response(response)
  fields = response.inference.result.fields

  object_field = fields.get_object_field('my_object_field')
  sub_fields = object_field.fields
  
  # grab a single sub-field
  sub_field_value = sub_fields.get_simple_field('sub_field').value
  
  # loop over sub-fields
  sub_fields.each_value do |sub_field|
    field_value = sub_field.value
  end
end

Accessing a list of objects, where my_object_list_field is the name of the field in the Model.

Access the list as a ListField instance, and the items as ObjectField instances.

def handle_response(response)
  fields = response.inference.result.fields
  
  object_list_field = fields.get_list_field('my_object_list_field')

  # access an object at a given position
  object_item_0 = object_list_field.items[0]
  sub_field_0_value = object_item_0.fields.get('sub_field').value

  # Loop over the list of Object fields
  object_list_field.fields.each do |object_item|
    sub_field_value = object_item.fields.get('sub_field').value
  end
end

You can technically access all field types by their index: fields['field_name']

This is heavily discouraged and unsupported.

Accessing simple values, using the name of the field in the Data Schema.

Access fields as SimpleField instances when retrieving their value.

We also need to specify the type of value, the possible types are String , Boolean , Double . Note that all types may be null.

import com.mindee.v2.product.extraction.ExtractionResponse;

public void handleResponse(ExtractionResponse response) {
  var fields = response.getInference().getResult().getFields();

  // texts, dates, classifications ...
  String stringFieldValue = fields.getSimpleField("string_field")
        .getStringValue();

  // a JSON float will be a Double
  Double floatFieldValue = fields.getSimpleField("float_field")
      .getDoubleValue();

  // even if the API always returns an integer, the type will be Double
  Double intFieldValue = fields.getSimpleField("int_field")
      .getDoubleValue();

  // booleans
  Boolean boolFieldValue = fields.getSimpleField("bool_field")
      .getBooleanValue();
}

Accessing a list of simple values, where my_simple_list_field is the name of the field in the Model.

We need to specify that the field is a ListField in order to access its SimpleItems.

For each item in the list, we also need to specify the correct field and value type, as described above.

import com.mindee.v2.product.extraction.ExtractionResponse;
import com.mindee.parsing.v2.field.ListField;
import com.mindee.parsing.v2.field.SimpleField;
import java.util.List;

public void handleResponse(ExtractionResponse response) {
  var fields = response.getInference().getResult().getFields();

  ListField simpleListField = fields.getListField("my_simple_list_field");

  List<SimpleField> simpleItems = simpleListField.getSimpleItems();

  // Loop over the list of Simple fields
  for (SimpleField itemField : simpleItems) {
    // Choose the appropriate value type accessor method:
    // String, Double, Boolean
    String fieldValue = itemField.getStringValue();
  }
}

Accessing an object field and its sub-fields, where my_object_field is the name of the field in the Model. In this hypothetical case, the object has a sub-field named subfield_1 .

import com.mindee.v2.product.extraction.ExtractionResponse;
import com.mindee.parsing.v2.field.ListField;
import com.mindee.parsing.v2.field.ObjectField;
import com.mindee.parsing.v2.field.SimpleField;
import java.util.HashMap;
import java.util.Map;

public void handleResponse(ExtractionResponse response) {
  var fields = response.getInference().getResult().getFields();

  ObjectField objectField = fields.getObjectField("my_object_field");

  HashMap<String, SimpleField> subFields = objectField.getSimpleFields();

  // grab a single sub-field
  SimpleField subfield1 = subFields.get("subfield_1");

  // loop over sub-fields
  for (Map.Entry<String, SimpleField> entry : subFields.entrySet()) {
    String fieldName = entry.getKey();
    SimpleField subField = entry.getValue();
    
    // Choose the appropriate value type accessor method:
    // String, Double, Boolean
    String fieldValue = subField.getStringValue();
  }
}

Accessing a list of objects, where my_object_list_field is the name of the field in the Model.

import com.mindee.v2.product.extraction.ExtractionResponse;
import com.mindee.parsing.v2.field.ListField;
import com.mindee.parsing.v2.field.ObjectField;
import com.mindee.parsing.v2.field.SimpleField;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

public void handleResponse(ExtractionResponse response) {
  var fields = response.getInference().getResult().getFields();

  ListField fieldObjectList = fields.getListField("my_object_list_field");

  List<ObjectField> objectItems = listField.getObjectItems();

  // Loop over the list of Object fields
  for (ObjectField itemField : objectItems) {

    // Object sub-fields will always be Simple fields
    HashMap<String, SimpleField> subFields = itemField.getSimpleFields();

    // grab a single sub-field
    SimpleField subfield1 = subFields.get("subfield_1");
    
    // Choose the appropriate value type accessor method:
    // String, Double, Boolean
    String subFieldValue = subfield1.getStringValue();

    // loop over sub-fields
    for (Map.Entry<String, SimpleField> entry : subFields.entrySet()) {
      String fieldName = entry.getKey();
      SimpleField subField = entry.getValue();
    }
  }
}

Depending on your requirements, this can be simplified using various custom methods.

Accessing simple values, using the name of the field in the Data Schema.

Access fields as SimpleField instances when retrieving their value.

We also need to specify the type of value, the possible types are string , Boolean , Double . Note that all types may be null.

using Mindee.V2.Parsing.Inference.Field;

public void HandleResponse(ExtractionResponse response)
{
    // texts, dates, classifications ...
    string stringFieldValue = fields["string_field"].SimpleField.Value;

    // a JSON float will be a Double
    Double floatFieldValue = fields["float_field"].SimpleField.Value;

    // even if the API always returns an integer, the type will be Double
    Double intFieldValue = fields["int_field"].SimpleField.Value;

    // booleans
    Boolean boolFieldValue = fields["bool_field"].SimpleField.Value;
}

Accessing a list of simple values, where my_list_field is the name of the field in the Model.

We need to specify that the field is a ListField in order to access its SimpleItems.

using Mindee.V2.Parsing.Inference.Field;

public void HandleResponse(ExtractionResponse response)
{
    InferenceFields fields = response.Inference.Result.Fields;

    ListField simpleListField = fields["my_simple_list_field"].ListField;

    List<SimpleField> simpleItems = simpleListField.SimpleItems;

    // Loop over the list of Simple fields
    foreach (SimpleField itemField in simpleItems)
    {
        // Choose the appropriate value type:
        // string, Double, Boolean
        string fieldValue = itemField.Value;
    }
}

Accessing an object field and its sub-fields, where my_object_field is the name of the field in the Model. In this hypothetical case, the object has a sub-field named subfield_1 .

using Mindee.V2.Parsing.Inference.Field;

public void HandleResponse(ExtractionResponse response)
{
    InferenceFields fields = response.Inference.Result.Fields;

    ObjectField objectField = fields["my_object_field"].ObjectField;

    Dictionary<string, SimpleField> subFields = objectField.SimpleFields;

    // grab a single sub-field
    SimpleField subField1 = subFields["subfield_1"];

    // loop over sub-fields
    // Note: in C#14, 'field' is a reserved keyword, hence use of 'entry'.
    foreach (KeyValuePair<string, SimpleField> entry in subFields)
    {
        string fieldName = entry.Key;
        SimpleField subField = entry.Value;
        
        // process the SimpleField ...
    }
}

Accessing a list of objects, where my_object_list_field is the name of the field in the Model.

using Mindee.V2.Parsing.Inference.Field;

public void HandleResponse(ExtractionResponse response)
{
    InferenceFields fields = response.Inference.Result.Fields;

    ListField fieldObjectList = fields["my_simple_list_field"].ListField;

    List<ObjectField> objectItems = fieldObjectList.ObjectItems;

    // Loop over the list of Object fields
    foreach (ObjectField itemField in objectItems)
    {
        Dictionary<string, SimpleField> subFields = objectField.SimpleFields;
    
        // grab a single sub-field
        SimpleField subField1 = subFields["subfield_1"];
        
        // Choose the appropriate value type:
        // string, Double, Boolean
        string subFieldValue = subField1.Value;
    
        // loop over sub-fields
        // Note: in C#14, 'field' is a reserved keyword, hence use of 'entry'.
        foreach (KeyValuePair<string, SimpleField> entry in subFields)
        {
            string fieldName = entry.Key;
            SimpleField subField = entry.Value;
        }
    }
}

Details on Response Processing

For more details on using the result fields in your application: Extraction Result

For details on response metadata: Response Processing

PreviousSDK Integration

NextExtraction Configuration

Last updated 4 months ago

Was this helpful?