Web application - PDF parsing and interpretation -> JSON output with API

Web based PDF interpreter with API capabilities. We want to be able to take Vendor quotes and invoice PDF's, and intelligently interpret them in a reliable way to extract all relevant company, contact, PO, and line items, as well as totals, tax, discount information, and format it into a standardized JSON object that can be ingested by our database. I've used ChatGPT to help outline the project as I see it with a recommended tech stack, based in Python. The tech stack is as follows: Python for backend development. Flask or Django for the web framework to handle web interface and API endpoints. Integrate PyPDF2 and PDFMiner for PDF parsing. Use Tesseract for OCR capabilities to process image-based PDFs. Employ an NLP library like spaCy for interpreting the document content and suggesting whether it's a quote or an invoice. See attached image for broken down development cycle. Please provide an estimation for price and how long this project would take. Thanks!