Usage of GoogleDriveLoader on Google Spreadsheet returns "Only files with binary content can be downloaded"

[Defozo]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from langchain_community.document_loaders import GoogleDriveLoader
from langchain_community.document_loaders import UnstructuredFileIOLoader

folder_id = "..."
loader = GoogleDriveLoader(
    folder_id=folder_id,
    file_loader_cls=UnstructuredFileIOLoader,
    file_loader_kwargs={"mode": "elements"},
)

docs = loader.load()

docs[0]

Description

I'm following the documentation here:
https://python.langchain.com/docs/integrations/document_loaders/google_drive

It says:

You can also process a folder with a mix of files and Google Docs/Sheets using the following pattern:

But when I use the code provided:

folder_id = "..."
loader = GoogleDriveLoader(
    folder_id=folder_id,
    file_loader_cls=UnstructuredFileIOLoader,
    file_loader_kwargs={"mode": "elements"},
)

docs = loader.load()

docs[0]

I'm getting error:

Traceback (most recent call last):
  File "c:\Users\defoz\Documents\Projects\crewai\main.py", line 25, in <module>
    docs = loader.load()
           ^^^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\langchain_community\document_loaders\googledrive.py", line 360, in load
    return self._load_file_from_ids()
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\langchain_community\document_loaders\googledrive.py", line 348, in _load_file_from_ids
    docs.extend(self._load_file_from_id(file_id))
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\langchain_community\document_loaders\googledrive.py", line 312, in _load_file_from_id
    status, done = downloader.next_chunk()
                   ^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\googleapiclient\_helpers.py", line 130, in positional_wrapper
    return wrapped(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\googleapiclient\http.py", line 780, in next_chunk
    raise HttpError(resp, content, uri=self._uri)
googleapiclient.errors.HttpError: <HttpError 403 when requesting https://www.googleapis.com/drive/v3/files/...?alt=media returned "Only files with binary content can be downloaded. Use Export with Docs Editors files.". Details: "[{'message': 'Only files with binary content can be downloaded. Use Export with Docs Editors files.', 'domain': 'global', 'reason': 'fileNotDownloadable', 'location': 'alt', 'locationType': 'parameter'}]">

(I removed ids with ...)

I'd expect this to load the Google Spreadsheet I'm trying to load here without any errors.

System Info

System Information

OS: Windows
OS Version: 10.0.19045
Python Version: 3.12.0 (tags/v3.12.0:0fb18b0, Oct 2 2023, 13:03:39) [MSC v.1935 64 bit (AMD64)]

Package Information

langchain_core: 0.1.22
langchain: 0.1.0
langchain_community: 0.0.19
langsmith: 0.0.87
langchain_openai: 0.0.2.post1

Packages not installed (Not Necessarily a Problem)

The following packages were not found:

langgraph
langserve

[dosubot[bot]]

🤖

Hey @Defozo! Nice to see you here again. Hope you're doing well!

Based on the error message you're receiving, it seems like you're trying to download a Google Docs or Sheets file as a binary file, which is not supported by the Google Drive API. Google Docs and Sheets are web-based documents that do not have a binary representation that can be downloaded directly.

In the LangChain's GoogleDriveLoader, the method _load_file_from_id is used to download files from Google Drive. This method uses the get_media method from the Google Drive API to download the file, which only works for binary files.

For Google Docs and Sheets, you need to use the export_media method instead, which converts the document to a downloadable format (like plain text or PDF) before downloading. This is done in the _load_document_from_id and _load_sheet_from_id methods for Google Docs and Sheets respectively.

So, if you are trying to process a folder with a mix of files and Google Docs/Sheets, make sure that the correct method is used for each file type. The _load_documents_from_folder method in the GoogleDriveLoader class should handle this correctly, as it checks the mimeType of each file and calls the appropriate method. If you are still getting the error, there might be a problem with the mimeType of your files, or there might be a bug in the code.

I also found a similar issue in the LangChain repository: Document Loaders: GoogleDriveLoader can't load a google docs file.. The solution suggested there is to split your documents either as Google docs or not based on their mimeType, and then feed your documents ids to file_ids or document_ids based on their type. Here is the example code provided:

GoogleDriveLoader(
        file_ids=non_google_file_to_load,
        document_ids=google_file_to_load,
        credentials_path=credentials_path / "credentials.json",
        token_path=credentials_path / "token.json",
        file_loader_cls=UnstructuredFileIOLoader,
        file_loader_kwargs={"mode": "single"}
)

I hope this helps! If you have any other questions, feel free to ask.

Sources

• Document Loaders: GoogleDriveLoader can't load a google docs file.
• libs/community/langchain_community/document_loaders/googledrive.py

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[Defozo]

But it says in the documentation:

You can also process a folder with a mix of files and Google Docs/Sheets using the following pattern

[dbkinghorn]

I've been fighting with this too and the only way I can get it to work is by using this,

from langchain_googledrive.document_loaders import GoogleDriveLoader

However, that is deprecated.

These do not work,

from langchain_community.document_loaders import GoogleDriveLoader

or

from langchain_google_community import GoogleDriveLoader