Si'aa (سعة) – A smart community-driven storage marketplace built for Saudi Arabia. This platform connects users needing storage with nearby available spaces.
This platform now includes AI Matching using the sentence-transformers/all-MiniLM-L6-v2 model. The system converts text descriptions to embeddings (vectors) and finds the best matching storage spaces based on semantic similarity
-
Install Backend Dependencies
cd backend pip install -r requirements.txt -
Start the Backend Server
python app.py
The server will run on
http://localhost:5000 -
Initialize Sample Data (mock data)
python init_sample_data.py
-
Open the Frontend
- Open
HTML/search.html - Fill the search filters
- Click "Search & Get Recommendations"
- Results will be ranked by AI match score!
- Open
- Text Embeddings: Storage descriptions are converted to 384-dimensional vectors
- Semantic Matching: User queries are matched against all spaces using cosine similarity
- Smart Ranking: Results are sorted by match percentage (highest similarity first)
- Filter Integration: Combines AI matching with traditional filters (location, price, size)