Summarize files with Box AI in Python

Box AI exposes AI capabilities that enable developers to interrogate documents through a single API call. This powerful feature transforms unstructured document content into instant insights without the need to build and maintain complex Retrival Augmented Genration (RAG) pipelines. This quick start demonstrates how to configure the Box Python SDK and use Box AI to summarize files in Box.

Create and configure a Box application

The first step for any Box Platform integration is to create and configure a Box application.

Go to Box Developer Console.
For this quick start, create an App with the Client Credentials Grant application type.
Once the app is created, enable the following scopes:
- Read all files and folders stored in Box
- Manage AI

For more information about creating a new Box application, see Create your first application.

Upload a test file

To use Box AI to get insights from documents, you need a file in Box. For this quick start, use this document containing federal code.

Download the test document, and then drag and drop it into your Box account.
Get the file ID by opening the file in Box and inspecting the URL. The last part of the path is your file ID. For example, the URL might look like this: https://app.box.com/file/2064123286902

In this case, the file ID is 2064123286902.

Configure the environment

Now set up your development environment to run this quickstart. This tutorial uses Python and the latest Box Python SDK to run the code. Make sure you have Python 3.11 or higher installed on your machine.

Create a new directory for your project and navigate into it.
Create a virtual environment:
```
python3 -m venv .venv
source .venv/bin/activate
```
Install the Box Python SDK:
```
pip install "boxsdk~=10"
```
Install the python-dotenv package to load environment variables from the .env file:
```
pip install python-dotenv
```
Create an .env file in the root of your project directory and add the following environment variables, replacing the placeholder values with your actual Box app credentials and the IDs from the previous steps:
```
 BOX_DEVELOPER_TOKEN=your_box_developer_token

 BOX_FILE_ID=your_box_file_id
```

To get your Developer Token, go to the Box Developer Console, open your app, and navigate to the Configuration tab.

Click Generate Developer Token to create a new token.

For simplicity, this quick start uses a short-lived developer token. In production, you should authenticate using your app’s configured method (for example, Client Credentials Grant) instead of a developer token.

Create the summarize.py file

Your development environment is now ready to create the Python script to summarize the document using Box AI.

Create a new file named summarize.py in the root of your project directory and add the following code:

import os

from dotenv import load_dotenv

from box_sdk_gen import (
    AiItemAsk,
    AiItemAskTypeField,
    BoxClient,
    BoxDeveloperTokenAuth,
    CreateAiAskMode
)

load_dotenv()

developer_token = os.getenv("BOX_DEVELOPER_TOKEN")
file_id = os.getenv("BOX_FILE_ID")

def get_box_client(token: str) -> BoxClient:
    
    if not developer_token:
        raise ValueError("BOX_DEVELOPER_TOKEN is not set in environment variables.")
    
    auth = BoxDeveloperTokenAuth(token=token)
    client = BoxClient(auth=auth)

    return client

def main():
    client = get_box_client(token=developer_token)

    me = client.users.get_user_me()
    print(f"My user ID is {me.id}")


if __name__ == "__main__":
    main()

This code loads the environment variables from the .env file, initializes the Box SDK client, and prints the current user’s ID to validate that the client is working correctly.

Run the script using the following command in your terminal:
```
python summarize.py
```
If the Box SDK client is set up correctly, the console displays your user ID. For example:
```
My user ID is 123456789
```

Summarize the file

With a working Box SDK client, you can add the code to summarize the document using Box AI.

Between the get_box_client function and the main function, add the following function:

def summarize_file(client: BoxClient, file_id: str) -> str:
    prompt = """
    Summarize the content of the following file in a few sentences.
    """

    summary = client.ai.create_ai_ask(
        CreateAiAskMode.SINGLE_ITEM_QA,
        prompt,
        [
            AiItemAsk(
                id=file_id,
                type=AiItemAskTypeField.FILE
            )
        ]
    )
    
    return summary.to_dict()['answer']

This function uses the Box AI create_ai_ask method to interrogate the specified file. Your BoxClient and file ID created earlier are sent to the function, which returns the summary of the file as a string.

Add the function call to summarize the file in the main function. Ensure that the new main function contains the following logic:

def main():
    client = get_box_client(token=developer_token)

    # Get the current user and print the ID to validate the client is working
    me = client.users.get_user_me()
    print(f"My user ID is {me.id}")

    summary = summarize_file(client=client, file_id=file_id)

    # Print the extracted metadata
    print(f"\n\nSummary: {summary}")

The SDK handles the API call to Box AI and returns the summary as an AiResponseFull object. In this quick start, the code converts this object to a dictionary and returns the answer field that contains the summary.

Print out the summary to the console to verify that the operation was successful by running the following command in your terminal:

python summarize.py

If the summarization was successful, the console displays your user ID followed by the summary from the test document.

My user ID is 123456789

Summary: **Summary of 28 CFR § 2.20 (Paroling Policy Guidelines)**

- The document sets forth the U.S. Parole Commission’s purpose and framework for national parole policy, emphasizing guidelines to promote consistent, equitable parole decisions while preserving individualized review.
- It provides a matrix of customary total time-to-release ranges by offense severity categories (1–8) and offender parole prognosis (salient factor scores), noting guidelines apply to inmates with good institutional adjustment and are discretionary.
- A comprehensive Offense Behavior Severity Index (Chapters 1–12) assigns categories to specific crimes (homicide, assault, theft, drugs, firearms, national defense, etc.) with detailed rules, exceptions, and examples for grading offenses (including monetary thresholds and drug-quantity bands).
- Chapter Thirteen contains general notes, multiple-offense scoring guidance, definitions of key terms, and the Salient Factor Scoring Manual explaining how to compute parole prognosis points (prior convictions, commitments, age, recent commitment-free period, probation/parole status, and older-offender adjustment).
- The document also references reparole guidelines and authority to revise guidelines; aggravated crimes and Category Eight cases receive special treatment.

​Resources

Resources