A newer version of the Gradio SDK is available: 6.13.0
metadata
title: Personal Finance AI agent
emoji: ⚡
colorFrom: indigo
colorTo: green
sdk: gradio
sdk_version: 5.33.0
app_file: app.py
pinned: false
license: mit
tag: agent-demo-track
Personal Financial Transaction AI Agent 🤖
A Python-based application for processing and analyzing financial transactions from PDF, CSV, or Excel files. It categorizes transactions, generates financial insights, and provides a user-friendly Gradio web interface. Designed to run locally or on Hugging Face Spaces, the project uses rule-based local processing, requiring no external API dependencies.
Features
- File Support: Processes transactions from PDF (with table extraction), CSV, or Excel files.
- Transaction Categorization: Automatically categorizes transactions (e.g., Salary Income, Groceries & Food) using robust rule-based logic.
- Financial Insights: Generates summaries including total income, expenses, net balance, and actionable insights.
- Currency Conversion: Supports USD, GBP, JPY, and KES with predefined exchange rates.
- Gradio Interface: Intuitive web UI for uploading files, selecting currency, and downloading results as CSV or Excel.
- Hugging Face Spaces: Optimized for deployment on Hugging Face Spaces with minimal setup.
- Error Handling: Comprehensive logging and user-friendly error messages.
Prerequisites
- Python: 3.8 or higher (3.9+ recommended).
- Dependencies (in
requirements.txt):
Installation
Local Setup
Clone the Repository:
git clone https://huggingface.co/spaces/smainye/Finapp.git
cd Finapp
Project Structure
financial-transaction-processor/
├── app.py # Gradio web interface and main application logic
├── Dockerfile # Defines the environment and instructions to build and run the Python app in a container
├── pdf_processor.py # PDF transaction extraction
├── nebius_backend.py # Transaction categorization and insights generation
├── requirements.txt # Python dependencies
├── data/ # Optional: sample files
│ ├── sample.csv
│ ├── sample.pdf
| ├── sample.xlsx