Add PDF reader to read_file

[jacobtohahn]

Background

Python makes it easy to extract text from PDF files, which allows us to improve the read_file command to support PDF documents. Thanks to andai on Discord for the idea.

Changes

The read_file command was improved to detect if a PDF file is being read and, if so, extract and return the text. Otherwise, the read_file command works as before and treats files as text.

This functionality makes use of the pdfminer.six library, and thus it was added to the requirements.txt file.

Documentation

Test Plan

Tested by using human feedback to instruct AutoGPT to read both a text file and a PDF file. Functionality worked as expected in both cases.

PR Quality Checklist

• My pull request is atomic and focuses on a single change.
• I have thoroughly tested my changes with multiple different prompts.
• I have considered potential risks and mitigations for my changes.
• I have documented my changes clearly and comprehensively.
• I have not snuck in any "extra" small tweaks changes

[jacobtohahn]

Potential improvement: check length of text extracted from the PDF and truncate if it's too long

[hunkim]

Secure way to check if it's a PDF?

def is_pdf(file_path):
    with open(file_path, 'rb') as file:
        file_header = file.read(5)
    return file_header == b'%PDF-'