Google Drive#

Google Drive is a file storage and synchronization service developed by Google.

This notebook covers how to load documents from Google Drive. Currently, only Google Docs are supported.


  1. Create a Google Cloud project or use an existing project

  2. Enable the Google Drive API

  3. Authorize credentials for desktop app

  4. pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib

🧑 Instructions for ingesting your Google Docs data#

By default, the GoogleDriveLoader expects the credentials.json file to be ~/.credentials/credentials.json, but this is configurable using the credentials_path keyword argument. Same thing with token.json - token_path. Note that token.json will be created automatically the first time you use the loader.

GoogleDriveLoader can load from a list of Google Docs document ids or a folder id. You can obtain your folder and document id from the URL:

  • Folder: -> folder id is "1yucgL9WGgWZdM1TOuKkeghlPizuzMYb5"

  • Document: -> document id is "1bfaMQ18_i56204VaQDVeAFpqEijJTgvurupdEDiaUQw"

!pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib
from langchain.document_loaders import GoogleDriveLoader
loader = GoogleDriveLoader(
    # Optional: configure whether to recursively fetch files from subfolders. Defaults to False.
docs = loader.load()

When you pass a folder_id by default all files of type document, sheet and pdf are loaded. You can modify this behaviour by passing a file_types argument

loader = GoogleDriveLoader(
    file_types=["document", "sheet"]