[Bug]: ImportError: llama-index-readers-file package not found

[mphipps2]

Bug Description

I'm calling:
image_documents = SimpleDirectoryReader(doc_dir).load_data()

But I get a ModuleNotFoundError for llama_index.readers.file.base (inside llama_index/core/readers/file/base.py) gets called in the readers directory and the :

`=

def _try_loading_included_file_formats() -> Dict[str, Type[BaseReader]]:
try:
from llama_index.readers.file.base import (
DocxReader,
EpubReader,
HWPReader,
ImageReader,
IPYNBReader,
MarkdownReader,
MboxReader,
PandasCSVReader,
PDFReader,
PptxReader,
VideoAudioReader,
) # pants: no-infer-dep
except ImportError:
raise ImportError("llama-index-readers-file package not found")

`=

Version

llama-index: 0.10.12, llama-index-readers-file: 0.1.5

Steps to Reproduce

Call image_documents = SimpleDirectoryReader(doc_dir).load_data() using the newest release

Relevant Logs/Tracbacks

Traceback (most recent call last):
  File "/llama_index/core/readers/file/base.py", line 21, in _try_loading_included_file_formats
    from llama_index.readers.file.base import (
ModuleNotFoundError: No module named 'llama_index.readers.file.base'
  File "/llama_index/core/readers/file/base.py", line 396, in load_data
    SimpleDirectoryReader.load_file(
  File "/llama_index/core/readers/file/base.py", line 303, in load_file
    default_file_reader_cls = SimpleDirectoryReader.supported_suffix_fn()
  File "/llama_index/core/readers/file/base.py", line 35, in _try_loading_included_file_formats
    raise ImportError("`llama-index-readers-file` package not found")
ImportError: `llama-index-readers-file` package not found

[dosubot]

🤖

Hey there, @mphipps2! Great to see you back. Hope you're doing well!

Based on the error message you provided, it seems like the llama_index.readers.file.base module is not found. This could be due to a few reasons:

1. The llama_index.readers.file.base module does not exist in the version of LlamaIndex you're using. However, based on the context provided, this module should be available in LlamaIndex v0.10.12.

2. The llama_index.readers.file.base module is not correctly installed. This could be due to an issue with your Python environment or the way LlamaIndex was installed.

To troubleshoot this issue, you can try the following steps:

1. Create a fresh virtual environment and install LlamaIndex there. This was suggested by multiple users and confirmed to resolve the issue:

   conda deactivate
   conda create --name new_venv
   conda activate new_venv
   pip install -U llama-index
   

   If the issue persists, try force reinstalling the package without using the cache:

   pip3 uninstall llama-index
   pip3 install llama-index --upgrade --no-cache-dir --force-reinstall
   

2. Ensure that all necessary sub-packages are installed, such as llama-index-readers-file:

   pip install -U llama-index-readers-file
   

3. If the error still persists, it might be due to the incorrect import statement. The SimpleDirectoryReader class is located in the llama_index.legacy.readers.file.base module, not llama_index.readers.file.base. Here's how you can correct it:

   from llama_index.legacy.readers.file.base import SimpleDirectoryReader
   
   doc_dir = "/path/to/your/documents"
   image_documents = SimpleDirectoryReader(doc_dir).load_data()

Please try these steps and let me know if the issue persists. You can refer to the similar solved issue for more details.

Sources

• [Bug]: import error generated by SimpleDirectoryReader()
• llama-index-legacy/llama_index/legacy/readers/file/base.py
• llama-index-core/llama_index/core/readers/file/base.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.

[logan-markewich]

@mphipps2 This works fine for me locally and on google colab.

Try with a fresh venv

In a new terminal:

pip uninstall llama-index  # remove any possible global install
python -m venv venv
source venv/bin/activate
pip install llama-index

(or equivalent commands for your package manager of choice)

[mphipps2]

Hi Logan, thanks for the quick response. Starting the new virtual environment worked for me. Not sure where the conflict was, but either way, all good now and will close the ticket. Thanks again