# Zapier Zaps

## Add Mindee Data Extraction to a Zap <a href="#add-mindee-to-a-make.com-scenario" id="add-mindee-to-a-make.com-scenario"></a>

You can use the Mindee App as a step in any zap.

### Setup App

When adding a step, search for "*mindee*" and select **Mindee OCR**:

<figure><img src="/files/VcYpIJzcMaZrKgFO2DV2" alt="Zapier choose Mindee app" width="516"><figcaption></figcaption></figure>

You should now have the Mindee App installed.

Next choose the "Action event" by clicking on "**Document Data Extraction**":

<figure><img src="/files/19tWvy2V10kzlbZlX6vC" alt="Zapier choose Mindee data extraction action" width="563"><figcaption></figcaption></figure>

Next, you'll need to connect the App to one of your [Manage API Keys](/integrations/api-keys.md).

If you already have a Mindee connection configured in Zapier, you'll have the option to "select" a connection in the "Account" section.

Otherwise, click on the "Sign in" button in the "Account" section.

Then, in the connection dialog box, fill in the following information:

* A name for your connection, for example your API key's name
* your [Mindee V2 API key](/integrations/api-keys.md#key-creation)

Finish by clicking on "Yes, Continue to Mindee OCR":

<figure><img src="/files/o8UIw1t6yZv9SETWSNis" alt="Zapier create connection Mindee API key" width="476"><figcaption></figcaption></figure>

{% hint style="info" %}
You'll be able to re-use this connection in other Zaps that include the Mindee App.
{% endhint %}

Your Step should now look something like this:

<figure><img src="/files/4f0NwNKyYpOA6KajdSiE" alt="" width="313"><figcaption></figcaption></figure>

Next, to configure the action, click on "Continue" at the bottom of the screen.

### Configure the Data Extraction Action

First, click on "Model to Use", you'll then be given a list of models available in your organization\
Click the one that you want to use:

<figure><img src="/files/SL1NNxo5ogP7IEwD4NuS" alt="" width="563"><figcaption></figcaption></figure>

For the "File to Send", you'll need to connect to a valid file input.

Normally it will be a field called "**File (Exists but not shown)**".\
As an example, here is what it looks like when connecting to a Drive folder:

<figure><img src="/files/RU4cnWgsE9T1FlFnCG3f" alt="" width="374"><figcaption></figcaption></figure>

You can also set various options:

* [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.
* "Polling Timeout" - The maximum number of seconds to attempt retrieving results, before stopping with an error. Increase this value if you are sending documents with many pages and are consistently getting timeout errors.

Next, to test the step, click on "Continue" at the bottom of the screen.

### Test the Step

If everything in the previous steps was configured correctly, you should now have something that looks like this:

<figure><img src="/files/Cug9WcPb4okXlKnUZqdN" alt="" width="311"><figcaption></figcaption></figure>

After clicking on "Test step", the file will be sent to Mindee for processing.

When complete, it should look like this:

<figure><img src="/files/SToCGNt7Obl8TJAACr9S" alt="" width="308"><figcaption></figcaption></figure>

Congrats, everything works!

After the data is extracted, it will be usable by any Step in your Zap.


---

# Agent Instructions: 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:

```
GET https://docs.mindee.com/extraction-models/no-code-integration/zapier-zaps.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.
