FinanceFlowAI is an open-source project designed to train, evaluate, and deploy small language models (SLMs) for personal finance question-answering tasks. It empowers users with tailored financial advice to better manage their spending, savings, and investments.
- Interactive Financial Advisor: Engage with the AI to receive personalized financial advice.
- Training and Fine-Tuning: Use preloaded datasets or customize your own for fine-tuning the model.
- Performance Evaluation: Assess model accuracy with metrics like Precision, Recall, and F1-score.
- Docker Integration: Seamlessly deploy using containerized environments.
- Python 3.10+
- Docker (optional for containerized environments)
-
Clone the repository:
git clone https://github.com/your-username/finance-flow-ai.git cd finance-flow-ai -
Install dependencies:
pip install -r requirements.txt
-
Set up pre-commit hooks:
pre-commit install
-
(Optional) Build the Docker image:
docker build -t finance-flow-ai .
python src/main.pypython src/train.py --config configs/training_config.yamlpython src/evaluate.py --data datasets/sample_data.csvfinance-flow-ai/
├── datasets/ # Data for training and evaluation
├── docs/ # Documentation files
├── notebooks/ # Jupyter Notebooks for prototyping
├── src/ # Source code for the project
├── tests/ # Unit and integration tests
├── .pre-commit-config.yaml # Pre-commit hook configuration
├── .gitignore # Git ignore rules
├── Dockerfile # Docker image setup
├── Makefile # Automation tasks
├── README.md # Project overview and instructions
└── pyproject.toml # Project dependencies and configuration
We welcome contributions! Please read our Contributing Guide and Code of Conduct before getting started.
This project is licensed under the MIT License.