InvoicePilot AI — Private, local-first invoice & expense assistant for freelancers
What I Built InvoicePilot AI is a privacy-first, local-first AI assistant that extracts structured data from invoices and receipts in PDFs and images. It validates arithmetic and exports sanitized CSV/XLSX reports. It uses Gemma 2B through Ollama for AI extraction, with a regex-based fallback when the model is unavailable. The application has a React frontend and FastAPI backend. Key Features…
InvoicePilot AI is a privacy-focused, local-first AI tool designed to streamline invoice and expense management for freelancers, small agencies, and organizations prioritizing data privacy. This AI assistant utilizes Gemma 2B through Ollama for AI-powered invoice and receipt extraction, with a regex-based fallback mechanism when the model is unavailable.
The platform supports PDF parsing and OCR, enabling the conversion of scanned documents into structured data. The React frontend, built with TypeScript and Vite, interacts with the FastAPI backend written in Python and FastAPI, providing a seamless user experience. The application leverages PyMuPDF and Tesseract for OCR and parsing tasks, and stores extracted information in SQLite databases using SQLAlchemy.
Users can upload invoices or receipts and review the extracted data, which is then sanitized and exported in CSV or XLSX format. The application is deployed using Docker and Docker Compose, ensuring easy setup and scalability. InvoicePilot AI combines open-weight AI models with deterministic validation, providing users with greater control over their data while automating invoice processing.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
