Python Overview

This guide will help you get started with the Mindee Python OCR SDK to easily extract data from your documents.

The Python OCR SDK supports invoice, passport, receipt OCR APIs and custom-built API from the API Builder.

You can view the source code on GitHub, and the package on PyPI.


  • Download and install Python. This library is officially supported on Python 3.7 to 3.11.
  • Download and install pip package manager.


To quickly get started with the Python OCR SDK anywhere, the preferred installation method is via pip.

pip install mindee

Development Installation

If you'll be modifying the source code, you'll need to install the development requirements to get started.

  1. First clone the repo.
git clone [email protected]:mindee/mindee-api-python.git
  1. Then navigate to the cloned directory and install all development requirements.
cd mindee-api-python
pip install -e ".[dev,test]"

Updating the Version

It is important to always check the version of the Mindee OCR SDK you are using, as new and updated features won’t work on old versions.

To check the installed version:

pip show mindee

To get the latest version:

pip install mindee --upgrade

To install a specific version:

pip install mindee==<your_version>


To get started with Mindee's APIs, you need to create a Client and you're ready to go.

Let's take a deep dive into how this works.

Initializing the Client

The Client centralizes document configurations in a single object.

The Client requires your API key.

You can either pass these directly to the constructor or through environment variables.

Pass the API key directly

from mindee import Client
#  Init with your API key
mindee_client = Client(api_key="my-api-key")

Set the API key in the environment

API keys should be set as environment variables, especially for any production deployment.

The following environment variable will set the global API key:


Then in your code:

from mindee import Client
#  Init without an API key
mindee_client = Client()

Setting the Request Timeout

The request timeout can be set using an environment variable:


Loading a Document File

Before being able to send a document to the API, it must first be loaded.

You don't need to worry about different MIME types, the library will take care of handling
all supported types automatically.

Once a document is loaded, interacting with it is done in exactly the same way, regardless
of how it was loaded.

There are a few different ways of loading a document file, depending on your use case:


Load from a file directly from disk. Requires an absolute path, as a string.

input_doc = mindee_client.doc_from_path("/path/to/the/invoice.pdf")

File Object

A normal Python file object with a path. Must be in binary mode.

with open("/path/to/the/receipt.jpg", 'rb') as fo:
     input_doc = mindee_client.doc_from_file(fo)


Requires a base64 encoded string.

Note: The original filename is required when calling the method.

input_doc = mindee_client.doc_from_b64string(b64_string, "receipt.jpg")


Requires raw bytes.

Note: The original filename is required when calling the method.

raw_bytes = b"%PDF-1.3\n%\xbf\xf7\xa2\xfe\n1 0 ob..."
input_doc = mindee_client.doc_from_bytes(raw_bytes, "invoice.pdf")

Loading from bytes is useful when using FastAPI UploadFile objects."/process-file")
async def upload(upload: UploadFile):
    input_doc = mindee_client.doc_from_bytes(,


Allows sending an URL directly.

Note: No local operations can be performed on the input (such as removing pages from a PDF).

input_doc = mindee_client.doc_from_url(url="")

Sending a File

To send a file to the API, we need to specify how to process the document.
This will determine which API endpoint is used and how the API return will be handled internally by the library.

More specifically, we need to set a mindee.documents.TypeDocument type as the first parameter of the parse method.

This is because the parse method's' return type depends on its first argument.

Each document type available in the library has its corresponding class, which inherit from the base mindee.document.Document class.
This is detailed in each document-specific guide.

Off-the-Shelf Documents

Simply setting the correct class is enough:

result = input_doc.parse(documents.TypeInvoiceV4)

Custom Documents

The endpoint to use must also be set, this is done in the endpoint_name argument of the parse method:

result = input_doc.parse(documents.TypeCustomV1, endpoint_name="wnine")

This is because the CustomV1 class is enough to handle the return processing, but the actual endpoint needs to be specified.


Join our Slack