curl --request POST \
  --url https://my.orq.ai/v2/knowledge/{knowledge_id}/datasources/preview-chunks \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "file_id": "<string>",
  "chunking_options": {
    "chunking_configuration": {
      "type": "default"
    },
    "chunking_cleanup_options": {
      "delete_emails": true,
      "delete_credit_cards": true,
      "delete_phone_numbers": true,
      "clean_bullet_points": true,
      "clean_numbered_list": true,
      "clean_unicode": true,
      "clean_dashes": true,
      "clean_whitespaces": true
    }
  }
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    file_id: '<string>',
    chunking_options: {
      chunking_configuration: {type: 'default'},
      chunking_cleanup_options: {
        delete_emails: true,
        delete_credit_cards: true,
        delete_phone_numbers: true,
        clean_bullet_points: true,
        clean_numbered_list: true,
        clean_unicode: true,
        clean_dashes: true,
        clean_whitespaces: true
      }
    }
  })
};

fetch('https://my.orq.ai/v2/knowledge/{knowledge_id}/datasources/preview-chunks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://my.orq.ai/v2/knowledge/{knowledge_id}/datasources/preview-chunks"

payload = {
    "file_id": "<string>",
    "chunking_options": {
        "chunking_configuration": { "type": "default" },
        "chunking_cleanup_options": {
            "delete_emails": True,
            "delete_credit_cards": True,
            "delete_phone_numbers": True,
            "clean_bullet_points": True,
            "clean_numbered_list": True,
            "clean_unicode": True,
            "clean_dashes": True,
            "clean_whitespaces": True
        }
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

{
  "chunks": [
    {
      "text": "<string>",
      "page_number": 123
    }
  ],
  "metadata": {
    "words_count": 123,
    "sentences_count": 123,
    "paragraphs_count": 123,
    "tokens_count": 123,
    "characters_count": 123,
    "chunks_count": 123
  }
}