- 💡 To use the
o4-miniversion, make sure you have the latestopenaipackage installed. - 📦 Install only what you need:
- For OpenAI API:
openai For open-source models:vllm
- For OpenAI API:
pip install openai - Clone the
s2orc-doc2jsonrepository to convert your PDF file into a structured JSON format.
(For detailed configuration, please refer to the official repository.)
git clone https://github.com/yuekai/s2orc-doc2json.git- Start the PDF processing service.
cd ./s2orc-doc2json/grobid-0.7.3
./gradlew run- Convert your PDF into JSON format.
To convert a single PDF file to JSON, pass the path of the file as the
-iargument toprocess_pdf.py
python ./s2orc-doc2json/doc2json/grobid2json/process_pdf.pyTo convert all the PDF files in a directory to JSON, pass the directory as as the -i argument to process_pdf.py
python ./s2orc-doc2json/doc2json/grobid2json/process_pdf.py -i ${PDF_DIR}Modify SUBMISSIONS_DIR variables in autograder.sh to point to the directory containing the PDF files to grade. Run the autograder.sh script to grade the submissions.
export OPENAI_API_KEY="<OPENAI_API_KEY>"
./autograder.sh