moe/banking
1
0
Fork 0
Code Issues 10 Pull requests Projects Releases Packages Wiki Activity Actions
No description
18 commits 1 branch 0 tags 2.3 MiB
  • Python 53.3%
  • HTML 46.7%
Find a file
Exact
MoC 0bb5328f52 sadasd
2026-06-15 18:25:39 +02:00
__pycache__ dasd 2026-06-09 17:35:39 +02:00
instance sadasd 2026-06-15 18:25:39 +02:00
templates sadasd 2026-06-15 18:25:39 +02:00
uploads jnn 2026-06-15 16:23:51 +02:00
.DS_Store tret 2026-06-10 14:01:35 +02:00
.env sadasd 2026-06-15 18:25:39 +02:00
.gitignore wdf 2026-06-10 09:48:25 +02:00
app.log sadasd 2026-06-15 18:25:39 +02:00
app.py sadasd 2026-06-15 18:25:39 +02:00
README.md sfsdf 2026-06-14 09:00:17 +02:00
requirements.txt Stop tracking .venv 2026-06-10 09:48:13 +02:00

README.md

Invest.AI

A Flask-based web application for aggregating and analyzing investment portfolios using AI-powered file parsing and agentic analysis.

Features

  • Add and manage multiple bank accounts
  • Upload banking statements (PDF, CSV, or screenshots)
  • AI-powered data extraction using OpenRouter LLM models
  • Track asset history over time
  • View current balances for each account
  • Modern, responsive web interface

Setup

  1. Install system dependencies for OCR:

    • Windows: Download and install Tesseract OCR from UB-Mannheim/tesseract
    • macOS: brew install tesseract
    • Linux: sudo apt-get install tesseract-ocr

  2. Install Python dependencies:

pip install -r requirements.txt
  1. Configure environment variables:
cp .env.example .env

Edit .env and add your OpenRouter API key:

OPENROUTER_API_KEY=your_api_key_here
OPENROUTER_MODEL=anthropic/claude-3-haiku:beta
FLASK_SECRET_KEY=your_secret_key_here

Optional: For better PDF parsing of printed webpages, use a vision-capable model:

OPENROUTER_MODEL=claude-3.5-sonnet
  1. Run the application:
python app.py
  1. Open your browser to http://localhost:5000

Usage

  1. Click "Add Bank Account" to create a new account
  2. Enter account name and description
  3. Click on an account to view details
  4. Upload banking statements (PDF, CSV, or images)
  5. The AI will automatically parse the file and extract asset data
  6. View current balance and asset history for each account

Supported File Types

  • PDF files (bank statements)
  • CSV files (transaction exports)
  • Images (screenshots of banking apps)

API Endpoints

  • GET / - Main web interface
  • GET /api/accounts - List all accounts
  • POST /api/accounts - Create new account
  • DELETE /api/accounts/<id> - Delete account
  • POST /api/accounts/<id>/files - Upload file for account
  • GET /api/accounts/<id>/files - List account files
  • GET /api/accounts/<id>/history - Get asset history

Technology Stack

  • Backend: Flask, SQLAlchemy
  • Database: SQLite
  • AI: OpenRouter API (configurable LLM models)
  • Frontend: HTML, Tailwind CSS, JavaScript
  • File Processing: PyPDF2, Pandas, Pillow