Expense Analytics App with AI (Llama 3.2 + Ollama)

This is a Flask web app that lets you upload an expense CSV and ask questions about your data using a locally running Llama 3.2 model via Ollama.

Features

• Upload CSV files of your expenses
• Ask natural language questions about your data
• Answers powered by Llama 3.2 (via Ollama)

---

Getting Started

1. Clone the repository

git clone <your-repo-url>
cd expense-analytics-app

2. Set up Python virtual environment

python3 -m venv .venv
source .venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Set up environment variables

Create a .env file in the project root:

SECRET_KEY=<your-random-secret-key>

Generate a random secret key:

python3 -c "import secrets; print(secrets.token_urlsafe(32))"

5. Run the Flask app

python app.py

The app will be available at http://localhost:5000

---

Running Llama 3.2 with Ollama

1. Install Ollama

Follow instructions at: https://ollama.com/download

2. Pull the Llama 3.2 model

ollama pull llama3.2

3. Start the Ollama server (if not already running)

ollama serve

Ollama will run at http://localhost:11434 by default.

---

Usage

1. Upload your CSV file on the web interface.
2. Ask questions about your expenses in natural language.
3. The AI will analyze your data and provide answers.

---

Notes

• Uploaded CSV files are stored in the uploads/ directory (and are gitignored).
• The app only sends a sample of your data to the LLM for context.
• For best results, use clear and specific questions.

---

License

MIT