Using GPT to parse PDF
Project description
gptpdf
Using GPT to parse PDF
Introduction
This package uses OpenAI's GPT-4o to parse PDFs to Markdowns. It perfectly parse text, image, math equations, charts, and tables. It almost cost $0.013 per page.
DEMO
See examples/attention_is_all_you_need/output.md
Installation
pip install gptpdf
Usage
from gptpdf import parse_pdf
pdf_path = '../examples/attention_is_all_you_need.pdf'
output_dir = '../examples/attention_is_all_you_need/'
api_key = os.getenv('OPENAI_API_KEY')
base_url = os.getenv('OPENAI_API_BASE')
# Manually provide OPENAI_API_KEY and OPEN_API_BASE
content, image_paths = parse_pdf(pdf_path, output_dir=output_dir, api_key=api_key, base_url=base_url, model='gpt-4o')
print(content)
print(image_paths)
# also output_dir/output.md is generated
from gptpdf import parse_pdf
pdf_path = '../examples/attention_is_all_you_need.pdf'
output_dir = '../examples/attention_is_all_you_need/'
# Use OPENAI_API_KEY and OPENAI_API_BASE from environment variables
content, image_paths = parse_pdf(pdf_path, output_dir=output_dir, model='gpt-4o', verbose=True)
print(content)
print(image_paths)
# also output_dir/output.md is generated
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
gptpdf-0.0.1.tar.gz
(5.1 kB
view hashes)