> For the complete documentation index, see [llms.txt](https://docs.mindee.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mindee.com/extraction-models/optional-features.md).

# Optional Features

## Overview

Models can have optional processing features activated depending on your requirements.

{% hint style="info" %}
Not all features are available on all plans.

Check the [Plans and Credits](/account-management/plans.md#feature-comparison) section for more information.
{% endhint %}

There are two ways of enabling and disabling features: on the Platform, or via API calls.

### Set Default Activation on the Platform

When setting the activation state of a feature on the Platform, this will be the default.\
All API calls will use the default state unless explicitly set otherwise during the API call.

This is useful for project managers, as it allows activating or deactivating a feature across all API calls on that model.

Anyone with write access to the model can set the option's default value.

### Set Activation During API Call

Default activation states may be overridden on a per-call basis via the API.

This is useful for developers for a variety of different scenarios, for example:

* local testing, comparing results on the same files with the feature active and inactive
* conditional activation of a feature based on business rules: document template, file origin, etc
* conditional activation of a feature based on your end-user's configuration
* etc ...

Anyone with access to the API (via an API Key) can enable or disable a feature when making an API call.

Details on setting features in the API: [Client Configuration](/integrations/client-libraries-sdk/configure-the-client.md#optional-features-configuration)

## Available Extraction Features

* [Raw Text (Full OCR)](/extraction-models/optional-features/raw-text-full-ocr.md)\
  Add the full text content of your documents to the API response.
* [Continuous Learning (RAG)](/extraction-models/optional-features/improving-accuracy.md)\
  Enhance extraction accuracy with Retrieval-Augmented Generation using your own documents.
* [Polygons (Bounding Boxes)](/extraction-models/optional-features/polygons-bounding-boxes.md)\
  Add the polygon coordinates of each extracted field to the API response.
* [Confidence Score and Accuracy Boost](/extraction-models/optional-features/automation-confidence-score.md)\
  🚀 Boost the precision and accuracy of all extractions.\
  Add a confidence score to each extracted field.


---

# 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.mindee.com/extraction-models/optional-features.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.