> For the complete documentation index, see [llms.txt](https://docs.extracta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.extracta.ai/data-extraction-api/extraction-details/fields.md).

# Fields

The `fields` parameter plays a crucial role in defining the data you wish to extract using the Extracta LABS API. It allows you to specify the exact structure of the information you're interested in, ensuring tailored and efficient data extraction. There are three primary types of fields you can define: `string`, `object`, and `array`. Understanding the differences and applications of each is key to leveraging the Extracta LABS API effectively.

## String Type

The `string` type is the simplest form and is used to extract text-based information. Each `string` field requires a `key`, `description`, `example`, and a `type`.

**Example:**

```json
{
  "key": "name",
  "description": "Name of the person",
  "example": "Alex Smith",
  "type": "string"
}
```

This defines a single piece of data you wish to extract, such as a name or email address, where the value is expected to be a text string.

## Object Type

The `object` type is used for structured data that includes multiple related properties. An `object` field will have a `key`, `description`, `type`, and a list of `properties`, each of which is itself a field definition that can be a `string`, another `object`, or an `array`.

**Example:**

```json
{
  "key": "personal_info",
  "description": "Personal information of the person",
  "type": "object",
  "properties": [
    {
      "key": "name",
      "description": "Name of the person",
      "example": "Alex Smith",
      "type": "string"
    },
    {
      "key": "email",
      "description": "Email of the person",
      "example": "alex.smith@gmail.com",
      "type": "string"
    }
  ]
}
```

This structure is ideal for extracting grouped data, such as personal information, that contains multiple attributes.

## Array Type

The `array` type is used when the data to be extracted is a list of items, which can be either simple `string` values or structured `object` types. An `array` field will include a `key`, `description`, `type`, and `items` specifying the type of elements in the array.

### Array of Strings Example:

```json
{
  "key": "languages",
  "description": "Languages spoken by the person",
  "type": "array",
  "items": {
    "type": "string",
    "example": "English"
  }
}
```

This format is used for lists where each item is a text string, like languages or skills.

### Array of Objects Example:

```json
{
  "key": "items",
  "description": "The items in the invoice",
  "type": "array",
  "items": {
    "type": "object",
    "properties": [
      {
        "key": "name",
        "description": "The name of the item",
        "example": "Item 1",
        "type": "string"
      },
      {
        "key": "quantity",
        "description": "The quantity of the item",
        "example": "1",
        "type": "string"
      },
      {
        "key": "unit_price",
        "description": "The unit price of the item. Return only the number as a string.",
        "example": "100.00",
        "type": "string"
      }
    ]
  }
}
```

This structure supports extracting a list of complex items, each with its own set of attributes, such as invoice items.

## Conclusion

Understanding the distinction between `string`, `object`, and `array` types is fundamental when defining the `fields` parameter for your data extraction needs with Extracta LABS. By carefully structuring your `fields`, you can customize the API's output to match the specific requirements of your application, ensuring that you capture precisely the data you need.

{% content-ref url="/pages/Kr8TtNYErc3zJQQ68V7K" %}
[1. Create extraction](/data-extraction-api/api-endpoints-data-extraction/1.-create-extraction.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.extracta.ai/data-extraction-api/extraction-details/fields.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.