Would you send your innovative research ideas to a commercial search provider⁉️🧐
I definitely don't want that, but that's exactly what many tools for searching for funding programs do. 😬
👉 That's why I started the Semantic Funding Search (SeFuSe) project. With SeFuSe, you can run the entire setup locally, keeping your data on your own server. 🔒
🔍 What is SeFuSe?
SeFuSe helps you find relevant funding programs in the German Federal Funding Database (Förderdatenbank des Bundes) - simply by describing your project idea.
No keyword guessing, no endless scrolling - SeFuSe uses semantic search powered by modern embedding models to identify programs that best fit your needs, providing short summaries and direct links to official entries.
Watch the demo
⚙️ How it runs
SeFuSe is built as a modular, open-source stack using:
- 🧱 FastAPI for the backend
- 🧠 Ollama for local embedding model inference
- 📦 Qdrant as the vector database
- 💻 Streamlit for the user interface
It's all managed through Docker Compose, which makes deployment and updates easy and gives you full control over your data.