InProSSA - Industrial Problem Solving using Symbolic and Subsymblic AI

Setup

Install uv

Linux/macOS:

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows (PowerShell):

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Set up Python environment

After installing uv and cloning the repository:

cd inprossa
uv sync

This will create a virtual environment and install all dependencies.

Structure

Every work packages has a specific directory.

Directory tree overview:

├───wp1
├───wp2
│   ├───formulation
│   ├───instances
│   └───source
│       ├───problemdatagenerator
|       └───simulator
|       └───optimiser
|       └───NL2DSL (semi-NL problem description to OptDSL translation using LLMs, continuous in-context learning and Trees of Thoughts)
├───wp3
│   └───examples
├───wp4
└───wp5