This project automates the extraction of company information and product details from PDF quotations (devis). It processes both text-based and scanned PDFs, converting them into structured JSON outputs.
-
Install dependencies (if needed):
pip install -r requirements.txt
-
Open the provided notebook and upload PDFs to the input_path, for example
"./Devis"
. -
Run the notebook; JSON outputs will be saved to the output_path, for example
"./output_json_%s"%model_name
.
- Deepseek-VL