### Install .NET Client Library

Source: https://docs.mindee.com/crop-models/sdk-integration/crop-quick-start

Install the Mindee .NET NuGet package using the .NET CLI.

```sh
dotnet add package Mindee --version 4.0
```

--------------------------------

### Install Node.js Client Library

Source: https://docs.mindee.com/crop-models/sdk-integration/crop-quick-start

Install the Mindee Node.js client library using npm.

```sh
npm install mindee@^5.1.1
```

--------------------------------

### Install PHP Client Library

Source: https://docs.mindee.com/crop-models/sdk-integration/crop-quick-start

Install the Mindee PHP client library using composer.

```sh
php composer.phar require "mindee/mindee:>=2.7"
```

--------------------------------

### PHP OCR Quick Start

Source: https://docs.mindee.com/ocr-models/sdk-integration/ocr-quick-start

Integrate OCR functionality using the Mindee PHP client library. Ensure you are using version 2.7.1 or greater. This example demonstrates initializing the client, setting OCR parameters including the mandatory model ID, loading a file, and processing it.

```php
<?php

use Mindee\ClientV2;
use Mindee\V2\Product\Ocr\Params\OcrParameters;
use Mindee\V2\Product\Ocr\OcrResponse;
use Mindee\Input\PathInput;

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

// Init a new client
$mindeeClient = new ClientV2($apiKey);

// Set ocr parameters
// Note: modelId is mandatory.
$ocrParams = new OcrParameters(
    // ID of the model, required.
    $modelId,
);

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

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

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

// Access the ocr results
$pages = $response->inference->result->pages;
```

--------------------------------

### Install Ruby Client Library

Source: https://docs.mindee.com/crop-models/sdk-integration/crop-quick-start

Install the Mindee Ruby gem.

```shell
gem install mindee -v '~> 5.1'
```

--------------------------------

### Querying Documentation via HTTP GET

Source: https://docs.mindee.com/crop-models/sdk-integration/crop-result

Perform an HTTP GET request to a documentation URL with an 'ask' query parameter to get dynamic information.

```bash
GET https://docs.mindee.com/crop-models/sdk-integration/crop-result.md?ask=<question>
```

--------------------------------

### Install Python Client Library

Source: https://docs.mindee.com/crop-models/sdk-integration/crop-quick-start

Install the Mindee Python client library using pip. Ensure you are using version 4.35.1 or greater.

```sh
pip install -U mindee~=4.35
```

--------------------------------

### Install and Use Mindee CLI in .NET

Source: https://docs.mindee.com/integrations/client-libraries-sdk/command-line-tools-cli

Install the Mindee.Cli NuGet package separately. Use the `Mindee.Cli` command for general help or specific model help. Run extractions by providing your API key, model ID, and the file path.

```bash
# General help
Mindee.Cli --help

# Help for extraction models
Mindee.Cli extraction --help

# Run extraction on a file
#   --api-key: API key, you can instead `export MINDEE_V2_API_KEY=md_XXXXXXXXXXXX`
#   --model-id: Your model ID
#   Positional arg: Absolute path to the file
Mindee.Cli extraction \
  --key md_XXXXXXXXXXXX \
  --model-id abcd1234-aa11-bb22-cc33-abcdef1234567 \
  /path/to/the/file.pdf
```

--------------------------------

### Install and Use Mindee CLI in Python

Source: https://docs.mindee.com/integrations/client-libraries-sdk/command-line-tools-cli

Install the Python library using pip. Use the `mindeeV2` command for general help or specific model help. Run extractions by providing your API key, model ID, and the file path.

```bash
# Install the library
pip install mindee

# General help
mindeeV2 --help

# Help for extraction models
mindeeV2 extraction --help

# Run extraction on a file
#   --key: API key, you can instead `export MINDEE_V2_API_API_KEY=md_XXXXXXXXXXXX`
#   --model: Your model ID
#   Positional arg: Absolute path to the file
mindeeV2 extraction \
  --key md_XXXXXXXXXXXX \
  --model abcd1234-aa11-bb22-cc33-abcdef1234567 \
  /path/to/the/file.pdf
```

--------------------------------

### Query Documentation Dynamically

Source: https://docs.mindee.com/use-cases/extraction-models

Perform an HTTP GET request on the current page URL with the `ask` query parameter to get dynamic answers and relevant excerpts from the documentation.

```http
GET https://docs.mindee.com/use-cases/extraction-models.md?ask=<question>
```

--------------------------------

### Query Documentation via HTTP GET

Source: https://docs.mindee.com/integrations

Perform an HTTP GET request to query the documentation dynamically. Include your question as the 'ask' query parameter.

```http
GET https://docs.mindee.com/integrations.md?ask=<question>
```

--------------------------------

### Install and Use Mindee CLI in Node.js

Source: https://docs.mindee.com/integrations/client-libraries-sdk/command-line-tools-cli

Install the Node.js library using npm. Access the CLI via its path in `node_modules`. Use the `mindeeV2` command for general help or specific model help. Run extractions by providing your API key, model ID, and the file path.

```shellscript
# Install the library
npm install mindee

# General help
./node_modules/.bin/mindeeV2 --help

# Help for extraction models
./node_modules/.bin/mindeeV2 extraction --help

# Run extraction on a file
#   --api-key: API key, you can instead `export MINDEE_V2_API_KEY=md_XXXXXXXXXXXX`
#   --model: Your model ID
#   Positional arg: Absolute path to the file
./node_modules/.bin/mindeeV2 extraction \
  --api-key md_XXXXXXXXXXXX \
  --model abcd1234-aa11-bb22-cc33-abcdef1234567 \
  /path/to/the/file.pdf
```

--------------------------------

### Query Documentation via HTTP GET

Source: https://docs.mindee.com/crop-models/sdk-integration

Perform an HTTP GET request to query the documentation dynamically. Include your question in the `ask` query parameter for a direct answer and relevant excerpts.

```http
GET https://docs.mindee.com/crop-models/sdk-integration.md?ask=<question>
```

--------------------------------

### Querying Documentation via HTTP GET

Source: https://docs.mindee.com/ocr-models/sdk-integration/ocr-result

Perform an HTTP GET request to a documentation URL with an 'ask' query parameter to dynamically query the documentation.

```http
GET https://docs.mindee.com/ocr-models/sdk-integration/ocr-result.md?ask=<question>
```

--------------------------------

### Query Documentation via HTTP GET

Source: https://docs.mindee.com/classification-models/sdk-integration

Perform an HTTP GET request to query the documentation dynamically. Include your question in the 'ask' query parameter for a direct answer and relevant excerpts.

```http
GET https://docs.mindee.com/classification-models/sdk-integration.md?ask=<question>
```

--------------------------------

### Query Documentation Dynamically

Source: https://docs.mindee.com/integrations/api-reference

Perform an HTTP GET request on the current page URL with the `ask` query parameter to get dynamic information from the documentation. The question should be specific and self-contained.

```http
GET https://docs.mindee.com/integrations/api-reference.md?ask=<question>
```

--------------------------------

### Query Documentation via HTTP GET

Source: https://docs.mindee.com/integrations/api-reference/classification-models

Perform an HTTP GET request to the current page URL with the 'ask' query parameter to dynamically query the documentation. The question should be specific and self-contained.

```http
GET https://docs.mindee.com/integrations/api-reference/classification-models.md?ask=<question>
```

--------------------------------

### Query Documentation with GET Request

Source: https://docs.mindee.com/extraction-models/data-schema-best-practices

Perform an HTTP GET request on the current page URL with the `ask` query parameter to dynamically query the documentation. The question should be specific, self-contained, and written in natural language.

```http
GET https://docs.mindee.com/extraction-models/data-schema-best-practices.md?ask=<question>
```

--------------------------------

### Query Documentation Dynamically

Source: https://docs.mindee.com/getting-started

Perform an HTTP GET request to query the documentation. Use the `ask` query parameter with a specific, self-contained question in natural language to get direct answers and relevant excerpts.

```http
GET https://docs.mindee.com/getting-started.md?ask=<question>
```

--------------------------------

### Query Documentation via HTTP GET

Source: https://docs.mindee.com/split-models

Perform an HTTP GET request to query documentation dynamically. Use the 'ask' query parameter with a specific, self-contained question in natural language. The response includes a direct answer and relevant excerpts.

```http
GET https://docs.mindee.com/split-models.md?ask=<question>
```

--------------------------------

### Query Documentation via HTTP GET

Source: https://docs.mindee.com/split-models/sdk-integration/split-result

Perform an HTTP GET request to query the documentation dynamically. Include the 'ask' query parameter with your question in natural language. Use this for information not explicitly present, clarifications, or related documentation.

```http
GET https://docs.mindee.com/split-models/sdk-integration/split-result.md?ask=<question>
```

--------------------------------

### Query Documentation via HTTP GET

Source: https://docs.mindee.com/crop-models

Perform an HTTP GET request to query the documentation dynamically. Use the 'ask' query parameter with a specific, self-contained question in natural language.

```http
GET https://docs.mindee.com/crop-models.md?ask=<question>
```

--------------------------------

### Query Documentation Dynamically

Source: https://docs.mindee.com/models/model-settings

Perform an HTTP GET request on the current page URL with the `ask` query parameter to get answers to specific questions. The question should be specific, self-contained, and written in natural language. Use this when the answer is not explicitly present, you need clarification, or want to retrieve related documentation.

```http
GET https://docs.mindee.com/models/model-settings.md?ask=<question>
```

--------------------------------

### Accessing Object Fields in Node.js

Source: https://docs.mindee.com/extraction-models/sdk-integration/extraction-result

This Node.js example demonstrates how to retrieve object fields and their simple sub-fields. It covers accessing a specific sub-field and iterating through all available simple sub-fields, including how to get their string values.

```JavaScript
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;
```

--------------------------------

### Classify Document (PHP)

Source: https://docs.mindee.com/classification-models/sdk-integration/classification-quick-start

Utilize the Mindee PHP client library to classify a document. Requires version 2.7.1 or greater, an API key, file path, and model ID. This example uses polling to get the result.

```php
<?php

use Mindee\ClientV2;
use Mindee\Input\InferenceParameters;
use Mindee\Input\PathInput;
use Mindee\Error\MindeeException;

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

// Init a new client
$mindeeClient = new ClientV2($apiKey);

// Set inference parameters
$inferenceParams = new InferenceParameters(
    // 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->enqueueAndGetInference(
    $inputSource,
    $inferenceParams
);

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

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

--------------------------------

### Java OCR Quick Start

Source: https://docs.mindee.com/ocr-models/sdk-integration/ocr-quick-start

Use this snippet to process a file with OCR using the Mindee Java client library. Ensure you have version 4.43.0 or greater installed. Replace placeholder values for API key, file path, and model ID.

```java
import com.mindee.MindeeClientV2;
import com.mindee.input.LocalInputSource;
import com.mindee.v2.product.ocr.OcrResponse;
import com.mindee.v2.product.ocr.OcrResult;
import com.mindee.v2.product.ocr.params.OcrParameters;
import java.io.IOException;

public class SimpleMindeeClientV2 {

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

    // Init a new client
    MindeeClientV2 mindeeClient = new MindeeClientV2(apiKey);

    // Set inference parameters
    OcrParameters ocrParams = OcrParameters
        // ID of the model, required.
        .builder(modelId)
        .build();

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

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

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

    // Access the result OCR pages
    OcrResult result = response.getInference().getResult();
  }
}
```

--------------------------------

### Initialize and Process Document with Ruby SDK

Source: https://docs.mindee.com/extraction-models/sdk-integration/quick-start

This Ruby snippet shows how to initialize the Mindee Ruby client, set inference parameters, load a file from disk, and send it for processing. Requires version 5.1.0 or greater.

```ruby
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 inference parameters
extraction_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,
    extraction_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')
```

--------------------------------

### Initialize and Process Document with PHP SDK

Source: https://docs.mindee.com/extraction-models/sdk-integration/quick-start

This PHP snippet demonstrates how to initialize the Mindee PHP client, configure inference parameters, load a file, and send it for processing. Requires version 2.7.1 or greater.

```php
<?php

use Mindee\ClientV2;
use Mindee\Input\InferenceParameters;
use Mindee\Input\PathInput;

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

// Init a new client
$mindeeClient = new ClientV2($apiKey);

// Set inference parameters
$inferenceParams = new InferenceParameters(
    // 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(
    $inputSource,
    $inferenceParams
);

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

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

--------------------------------

### Get Source File Metadata (.NET)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file

Access filename, check if it's a PDF, and get the page count from a loaded source file.

```csharp
string filename = inputSource.Filename;
bool isPdf = inputSource.IsPdf();
int numberOfPages = inputSource.GetPageCount();
```

--------------------------------

### Initialize and Process Document with Node.js SDK

Source: https://docs.mindee.com/extraction-models/sdk-integration/quick-start

Use this snippet to initialize the Mindee Node.js client, set product parameters, load a file, and send it for processing. Ensure you have version 5.1.0 or greater.

```javascript
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 product parameters
const productParams = {
  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,
  productParams,
);

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

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

--------------------------------

### Get Source File Metadata (Java)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file

Access filename, check if it's a PDF, and get the page count from a loaded source file.

```Java
String filename = inputSource.getFilename();
boolean isPdf = inputSource.isPdf();
int numberOfPages = inputSource.getPageCount();
```

--------------------------------

### Get Source File Metadata (Ruby)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file

Access filename, check if it's a PDF, and get the page count from a loaded source file.

```Ruby
filename = input_source.filename
is_pdf = input_source.pdf?
number_of_pages = input_source.page_count
```

--------------------------------

### Load File Instance (Java)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file

Initialize LocalInputSource with a File instance.

```java
var file = new File("/path/to/the/file.ext");

var inputSource = new LocalInputSource(file);
```

--------------------------------

### Load Path Instance (Java)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file

Initialize LocalInputSource with a Path instance.

```java
var filePath = new Path("/path/to/the/file.ext");

var inputSource = new LocalInputSource(filePath);
```

--------------------------------

### Get Source File Metadata (PHP)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file

Access filename, check if it's a PDF, and get the page count from a loaded source file.

```PHP
$filename = $inputSource->fileName;
$isPdf = $inputSource->isPdf();
$numberOfPages = $inputSource->getPageCount();
```

--------------------------------

### Initialize Python Client with API Key

Source: https://docs.mindee.com/integrations/client-libraries-sdk/configure-the-client

Initialize the Mindee client by passing the API key directly. This is suitable for quick testing. Ensure you have imported the necessary classes.

```python
from mindee import (
    ClientV2,
    InferenceParameters,
    InferenceResponse,
    PathInput,  # for loading files from disk
)
```

```python
api_key = "MY_API_KEY"

mindee_client = ClientV2(api_key)
```

--------------------------------

### Get Source File Metadata (Python)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file

Access filename, check if it's a PDF, and get the page count from a loaded source file.

```Python
filename: str = input_source.filename
is_pdf: bool = input_source.is_pdf
number_of_pages: int = input_source.page_count
```

--------------------------------

### Initialize .NET Client using Environment Variable

Source: https://docs.mindee.com/integrations/client-libraries-sdk/configure-the-client

Initialize the Mindee client for .NET without passing the API key directly, by relying on the `MindeeV2__ApiKey` environment variable. This is recommended for production.

--------------------------------

### Load FileInfo Instance (C#)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file

Initialize LocalInputSource with a FileInfo instance.

```csharp
FileInfo fileinfo = new FileInfo("/path/to/the/file.ext");

var inputSource = new LocalInputSource(fileinfo)
```

--------------------------------

### Query Documentation API

Source: https://docs.mindee.com/classification-models/sdk-integration/classification-result

Perform an HTTP GET request to the documentation URL with an 'ask' query parameter to get dynamic answers and relevant excerpts.

```http
GET https://docs.mindee.com/classification-models/sdk-integration/classification-result.md?ask=<question>
```

--------------------------------

### Initialize Python Client using Environment Variable

Source: https://docs.mindee.com/integrations/client-libraries-sdk/configure-the-client

Initialize the Mindee client without passing the API key directly, by relying on the `MINDEE_V2_API_KEY` environment variable. This is the recommended approach for production.

```python
mindee_client = ClientV2()
```

--------------------------------

### Install Node.js Client Library in Supabase Edge Functions

Source: https://docs.mindee.com/integrations/client-libraries-sdk

Install the Mindee Node.js client library in your Supabase edge functions using npm.

```bash
npm install @mindee/mindee-api-nodejs
```

--------------------------------

### Initialize PHP Client with API Key

Source: https://docs.mindee.com/integrations/client-libraries-sdk/configure-the-client

Initialize the Mindee client for PHP by passing the API key directly. This is useful for quick testing. Ensure you have imported the necessary classes.

```php
use Mindee\ClientV2;
use Mindee\Input\InferenceParameters;
use Mindee\Error\MindeeException;
```

```php
$apiKey = "MY_API_KEY";

$mindeeClient = new ClientV2($apiKey);
```

--------------------------------

### Enqueue and Get Inference (Java)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/send-a-file-or-url

Use the `enqueueAndGetInference` method with the Mindee client to send an input source and get the inference results. The inference can be printed to standard output.

```java
InferenceResponse response = mindeeClient.enqueueAndGetInference(
    inputSource, inferenceParams
);

// To easily test which data were extracted,
// simply print an RST representation of the inference
System.out.println(response.getInference().toString());
```

--------------------------------

### Querying Documentation Dynamically

Source: https://docs.mindee.com/crop-models/crop

To get information not explicitly on the page, make a GET request to the current URL with the 'ask' query parameter. The question should be specific and in natural language.

```http
GET https://docs.mindee.com/crop-models/crop.md?ask=<question>
```

--------------------------------

### Initialize .NET Client with API Key

Source: https://docs.mindee.com/integrations/client-libraries-sdk/configure-the-client

Initialize the Mindee client for .NET by passing the API key directly. This is useful for quick testing. Ensure you have added the required namespaces.

```csharp
using Mindee;
using Mindee.Input;
```

```csharp
string apiKey = "MY_API_KEY";

MindeeClientV2 mindeeClient = new MindeeClientV2(apiKey);
```

--------------------------------

### Get Source File Metadata (Node.js)

Source: https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file

Initialize the source, then access filename, check if it's a PDF, and get the page count. Ensure the source is initialized before accessing properties.

```JavaScript
// make sure to initialze the source first
await inputSource.init();

const filename = inputSource.filename;
const isPdf = inputSource.isPdf();
const numberOfPages = await inputSource.getPageCount();
```

--------------------------------

### Initialize PHP Client using Environment Variable

Source: https://docs.mindee.com/integrations/client-libraries-sdk/configure-the-client

Initialize the Mindee client for PHP without passing the API key directly, by relying on the `MINDEE_V2_API_KEY` environment variable. This is recommended for production.

```php
$mindeeClient = new ClientV2($apiKey);
```

--------------------------------

### Query Documentation Dynamically

Source: https://docs.mindee.com/integrations/client-libraries-sdk/basic-model-configuration

To get additional information not directly on the page, make an HTTP GET request to the page URL with the `ask` query parameter. The question should be specific and self-contained.

```HTTP
GET https://docs.mindee.com/integrations/client-libraries-sdk/basic-model-configuration.md?ask=<question>
```

--------------------------------

### Initialize Ruby Client using Environment Variable

Source: https://docs.mindee.com/integrations/client-libraries-sdk/configure-the-client

Initialize the Mindee client for Ruby without passing the API key directly, by relying on the `MINDEE_V2_API_KEY` environment variable. This is recommended for production.

```ruby
mindee_client = Mindee::ClientV2.new()
```

--------------------------------

### Initialize Ruby Client with API Key

Source: https://docs.mindee.com/integrations/client-libraries-sdk/configure-the-client

Initialize the Mindee client for Ruby by passing the API key directly. This is useful for quick testing. Ensure you have required the Mindee package.

```ruby
require 'mindee'
```

```ruby
api_key = 'MY_API_KEY'
mindee_client = Mindee::ClientV2.new(api_key: api_key)
```