Document Parsing Api

Overview

Lightweight FastAPI service converting unstructured PDFs (invoices/contracts) into strict JSON schemas. Uses LLMs (OpenAI/Gemini) with Pydantic validation to ensure high data extraction accuracy. Middleware layer for downstream automation workflows. Open-source project by Idequel Bernabel, published on GitHub.

Highlights

• Open source — view the code and contribute on GitHub

Built with

• Code