DC2025

Prototype for en AI-assistent som hjelper kundeservice med å svare på henvendelser basert på dokumentasjon fra Digdir og interne rutiner.

🚀 Project Setup – Dev Container Enabled

Welcome to the project! This repository is set up for fast onboarding using Visual Studio Code Remote - Containers (Dev Containers). Follow the steps below to get started.

---

📦 Requirements

Make sure you have the following installed:

• Docker Desktop (and it's running)
• Visual Studio Code
• Dev Containers Extension

---

⚙️ Getting Started

1. Clone the repository:

   git clone https://github.com/your-org/your-project.git
   cd your-project
   
   

🧑‍💻 Open in Dev Container

4. Open the folder in VS Code

   • Launch Visual Studio Code
   • Open the project folder (File → Open Folder...)

5. Reopen in Container

   VS Code should prompt you:

   "This folder contains a Dev Container configuration. Reopen in container?"

   👉 Click “Reopen in Container”

   If you don’t get the prompt:

   • Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux)
   • Search: Dev Containers: Reopen in Container and run it

6. Done! 🎉
   The container will automatically:

   • ✅ Copy .env.template → .env (if not already present)
   • ✅ Install dependencies from requirements.txt
   • ✅ Set up a fully configured Python environment ready to use

🌐 Open the API Docs

Once the dev container is running and the app has started (automatically or manually), you can open your browser and go to:

http://localhost:8000/docs

This opens the interactive API documentation powered by FastAPI (Swagger UI), where you can explore and test all available endpoints.

To use the local finetuned model through AIvar API, do the following:

1. set USE_AZURE = False in /app/config.py
2. run "uvicorn model_server:app --host 0.0.0.0 --port 8001" from the terminal in jupyter notebook: https://notebook.sandkasse.ai/lab/tree/digdir-camp-2025-desKI/finetuning/use_model
3. Use http://localhost:8000/docs

---

Developer info

All services has a Minimal Usage documentation within the class documentation. Please read this and use as intended.

Config.py includes all standard variables. Change them to change the behaviour of the program. Example: USE_AZURE: TRUE -> The program will use an Azure model, FALSE -> The program will use AIvar model.

🧹 Ruff

Ruff is a fast, all-in-one Python linter, formatter, and import sorter.

Basic Commands

ruff check . # Lint the codebase
ruff check . --fix # Auto-fix lint issues
ruff format . # Format the code
ruff format --check . # Check formatting