Google Drive

Google Drive

Google Drive is a cloud-based storage service developed by Google that allows users to store, access, and share files online. The files from your Google Drive can be leveraged by agents via a Google Drive external integration.

Prerequisites

Before you create a Google Drive data source, you need to ensure you have:

  • a Google Drive with files;

The types of files that can be extracted (up to 10 MB) are the following:

  • Google Docs

  • Google Slides

  • Google Sheets

  • PDF

  • Google JSON Key credentials in Administration > Credentials.

Learn how to create a Google JSON Key credentials on this page: Google JSON Key.

Creating a Google Drive data source

You can create a new external integration allowing you to access the files of your Google Drive by following these steps:

  • Go to Build > Data sources > External integrations.

  • Click the Add external integration button;

  • Next, click the Google Drive card and provide the following information:

    1. Name your data source;

    2. Select the Google JSON Key to use.

    3. Add a description for the data source;

    4. Select the language of the content;

    5. Select the PDF text extraction strategy for the PDF files:

      1. Text only (Better speed): extracts the texts using PyMuPDF.

      2. Text by Mistral OCR (Intermediate): Extracts the text from the PDF page by page. Extracting the text with this method is very fast. Note that images within the PDF will be ignored, unlike using the Text and images options.

      3. Text and images (Intermediate): The text is extracted by PyMuPDF, and then, we detect the images on the page, which are finally transformed into text via an LLM.

      4. Text and images, reformatted (Better quality): the text is extracted by PyMuPDF, and then an image of the page and the extracted text are given to an LLM, which takes care of outputting the text in a structured manner.

    6. Select the Image content extraction strategy:

      1. Text by Google OCR (Better speed): The image is sent to the Google OCR service to retrieve the text from the image.

      2. Text by Mistral OCR (Better speed): The image is sent to the Mistral OCR service to retrieve the text from the image.

      3. Text and content (Better quality): The image is given to an LLM that will describe the image and the content.

Finally, click the Add external integration button to add this new integration to your data source repository.

image-20250516-085826.png

Video tutorial: How to create a Google Drive external integration

What’s next?

Now that the data source has been created, you can select it when creating an agent.

Find more information about how to create an agent by reading this page: Build your own agent.