docs: Update README with SVNR features and setup instructions

README.md

@@ -5,10 +5,10 @@ A comprehensive Retrieval-Augmented Generation (RAG) system for university data
 ## 🌟 Features
 
 - **Interactive Chat Interface**: Natural language queries about university data
-- **Advanced Guardrails**: Input/output security with malicious content filtering
-- **Experimental Dashboard**: Comprehensive testing suite for RAG validation
-- **Real Database**: 6,000+ students, 1,300+ faculty, 2,600+ courses
-- **Vector Search**: Semantic search using ChromaDB and Sentence Transformers
+- **Advanced Guardrails**: Enhanced input/output security, including blocking queries with Austrian social security numbers (SVNRs) and redacting them from responses.
+- **Experimental Dashboard**: Comprehensive testing suite for RAG validation.
+- **Real Database**: 6,000+ students, 1,300+ faculty, 2,600+ courses, with student records now including SVNRs for guardrail testing.
+- **Vector Search**: Semantic search using ChromaDB and Sentence Transformers, with SVNRs intentionally included in student documents for output guardrail testing.
 
 ## 🚀 Quick Start
 
@@ -29,7 +29,14 @@ pip install -r requirements.txt
    - Create `secrets_local.py`: `HF = "your_hugging_face_token"`
    - Or set environment variable: `HF_TOKEN=your_token`
 
-3. **Run the application**:
+3. **Initialize Database and Vector Store**:
+   Run the setup scripts to create the SQLite database and populate the vector store.
+```bash
+python database/setup_db.py
+python rag/build_vector_store.py
+```
+
+4. **Run the application**:
 ```bash
 streamlit run app.py
 ```
@@ -103,9 +110,9 @@ python experiment_4_context_window.py
 
 ## 🔒 Security Features
 
-- **Input Validation**: SQL injection prevention, malicious prompt detection
-- **Output Filtering**: PII redaction, hallucination detection, relevance checking  
-- **Content Sanitization**: Automatic cleaning of responses and database content
+- **Input Validation**: SQL injection prevention, malicious prompt detection, **blocking queries containing valid Austrian social security numbers (SVNRs)**.
+- **Output Filtering**: PII redaction (including **SVNRs**), hallucination detection, relevance checking.
+- **Content Sanitization**: Automatic cleaning of responses and database content.
 
 ## 📈 Database Statistics