added library for parsing PDFs

[ghost]

pdfminer.six==20221105

[imartinez]

Why is that dependency needed @FluffyDietEngine ?

[Polpetta]

I initialized the project using a virtual environment, and after adding a couple of PDFs I run python ingest.py I got the following error:

python ingest.py               
Traceback (most recent call last):
  File "/home/user/git/privateGPT/venv/lib/python3.11/site-packages/langchain/document_loaders/pdf.py", line 194, in __init__
    from pdfminer.high_level import extract_text  # noqa:F401
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'pdfminer'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/git/privateGPT/ingest.py", line 35, in <module>
    main()
  File "/home/user/git/privateGPT/ingest.py", line 21, in main
    loader = PDFMinerLoader(os.path.join(root, file))
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/git/privateGPT/venv/lib/python3.11/site-packages/langchain/document_loaders/pdf.py", line 196, in __init__
    raise ValueError(
ValueError: pdfminer package not found, please install it with `pip install pdfminer.six`

After adding the dependency suggested in this PR, python ingest.py works without problems

[ghost]

@imartinez When I tried to use PDFMinerLoader to parse a PDF, I got the error which @Polpetta has given. Hence the addition in requirement. Traceback for your reference.

python --version
Python 3.10.9

Traceback (most recent call last):
  File "/Users/santhoshsolomon/Projects/privateGPT/venv/lib/python3.10/site-packages/langchain/document_loaders/pdf.py", line 194, in __init__
    from pdfminer.high_level import extract_text  # noqa:F401
ModuleNotFoundError: No module named 'pdfminer'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/santhoshsolomon/Projects/privateGPT/ingest.py", line 36, in <module>
    main()
  File "/Users/santhoshsolomon/Projects/privateGPT/ingest.py", line 22, in main
    loader = PDFMinerLoader(os.path.join(root, file))
  File "/Users/santhoshsolomon/Projects/privateGPT/venv/lib/python3.10/site-packages/langchain/document_loaders/pdf.py", line 196, in __init__

PDF I am using is available as attachment.
8-Data-Modeling-Patterns-in-Redis.pdf