Skip to content

AI-powered financial analysis platform built with Django and AWS Bedrock, designed for accountants to gain insights from CSV data with multi-agent support (MCP).

License

Notifications You must be signed in to change notification settings

oVitorio-ac/ContAI-Finance

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

9 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

ContAI Finance

Project developed for TDC 2025 - Q Developer Quest

A Django application designed for accountants to upload CSV files and interact with an AI-powered assistant for financial analysis.

πŸ“Š Project Status

Python Version Django Version License Build Status Coverage Tests

🏷️ Tags

  • q-developer-quest-tdc-2025
  • django
  • aws
  • amazon-q-developer
  • financial-analysis
  • mcp-server

πŸ“Έ Screenshots

Upload Screen

Upload Screen

Chat Interface

Chat Screen

πŸš€ Getting Started

Prerequisites

  • Python 3.12 or superior
  • Poetry
  • Git

Installation Steps

  1. Clone the repository:

    git clone https://github.com/oVitorio-ac/ContAI-Finance.git
    cd ContAI-Finance
  2. Setup with Poetry:

    # Install dependencies
    poetry install
    
    # Activate virtual environment
    poetry shell
  3. Database Setup:

    python manage.py makemigrations
    python manage.py migrate
  4. Run the Server:

    python manage.py runserver
  5. Access the App:

πŸ› οΈ Tech Stack

  • Backend: Django 5.2.6
  • Frontend: Bootstrap 5, HTML5
  • Database: SQLite (Development) / S3 integration for files
  • Cloud Infrastructure: AWS (S3, ECS, Lambda, Bedrock)
  • Development Tools: Amazon Q Developer, Terraform, Docker
  • Package Manager: Poetry

πŸ“ Project Structure

ContAI-Finance/
β”œβ”€β”€ src/                          # πŸ“ Source code
β”‚   β”œβ”€β”€ contai_finance/          # πŸ—οΈ Django project settings
β”‚   β”œβ”€β”€ financeiro/              # πŸ“¦ Main application module
β”‚   β”œβ”€β”€ mcp_server/             # πŸ”§ MCP Services (CSV Analyzer, Bedrock)
β”‚   β”œβ”€β”€ static/                  # 🎨 Static assets
β”‚   β”œβ”€β”€ templates/               # πŸ“„ HTML templates
β”‚   └── manage.py                # 🎯 Django entry point
β”œβ”€β”€ tests/                        # πŸ§ͺ Test suite
β”œβ”€β”€ infrastructure/               # ☁️ Infrastructure as Code
β”‚   β”œβ”€β”€ terraform/               # πŸ—οΈ AWS IaC
β”‚   β”œβ”€β”€ docker/                  # 🐳 Containerization
β”‚   └── scripts/                 # πŸ“œ Deployment & Helper scripts
β”œβ”€β”€ docs/                         # πŸ“š Comprehensive documentation
β”œβ”€β”€ .env.example                  # πŸ” Environment variables template
└── pyproject.toml                # πŸ“¦ Poetry configuration

🎯 Key Features

  • βœ… CSV File Upload: Secure handling and storage.
  • βœ… AI Chat Interface: Interactive financial insights.
  • βœ… MCP Servers: Specialized tools for precise CSV analysis and Bedrock automation.
  • βœ… AWS Integration: Bedrock for advanced AI, S3 for storage, and Lambda for triggers.
  • βœ… Automated Testing: Comprehensive suite with >90% coverage.
  • βœ… IaC Ready: Full infrastructure definition with Terraform for AWS deployment.

πŸ“Š Architecture

The project leverages a hybrid architecture combining a Django monolith with serverless AWS components for specialized tasks.

graph TD
    User["User"] -->|Upload CSV/Chat| Django["Django (ECS Fargate)"]
    Django -->|Store File| S3["AWS S3"]
    S3 -->|Trigger| Lambda["AWS Lambda (Processor)"]
    Lambda -->|Store Analysis| S3
    Django -->|Precise Query| MCP["CSV Analyzer (MCP)"]
    Django -->|Complex Insights| Bedrock["AWS Bedrock (Claude 3)"]
    MCP -->|Read| LocalCSV["Local/S3 CSV"]
Loading

For more details, see our Architecture Documentation.

πŸ§ͺ Testing

Run tests using Pytest or the custom runner script:

# All tests
python run_tests.py

# Using Pytest directly
pytest

# With coverage report
pytest --cov=src --cov-report=html

πŸ† TDC 2025 - Q Developer Quest Progress

  • βœ… Tier 1: Project generated with Amazon Q Developer, Public Repo, Screenshots, and Prompt List.
  • βœ… Tier 2: Architecture Diagrams (Mermaid), Automated Tests (19), Technical Documentation.
  • βœ… Tier 3: Three MCP Servers integrated, AWS Bedrock integration, IaC (Terraform), ECS/Fargate Deployment.

🀝 Contributing

Contributions are welcome! Please check our Contributing Guidelines and Development Guide for more information.

πŸ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

About

AI-powered financial analysis platform built with Django and AWS Bedrock, designed for accountants to gain insights from CSV data with multi-agent support (MCP).

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Packages

No packages published

Contributors 2

  •  
  •