PDF extractor to pull relevant details from CVs in PDF format, and match them against the job descriptions from the Hugging Face dataset.
Please make sure to follow these steps before processing:
- Step 1: Make sure to have all the resume PDFs in one single folder and upload that on Google Drive as a "ZIP" file before processing.
- Step 2: Download/use the "main.ipynb" file from the GitHub repo, and run it on Google Colab to avoid complications.
- Step 3: After mounting GDrive please copy the ZIP file path from Colab runtime storage and paste it into "resume_folder" variable.