feat: add Gradio web UI

- app.py: Gradio Interface wrapping BoschProductRAG.query()
- Index built once at startup (not per-request)
- Markdown output: answer + linked sources + latency
- Example prompts included for quick demo
- Verified: launches on :7860, returns correct answers

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

README.md

@@ -1,6 +1,6 @@
 # Bosch HVAC Product Knowledge Bot
 
-A CLI-based **Retrieval-Augmented Generation (RAG)** system that answers sales and specification questions about Bosch HVAC products.
+A **Retrieval-Augmented Generation (RAG)** system that answers sales and specification questions about Bosch HVAC products. Available as both a **web UI (Gradio)** and a **CLI**.
 
 ## What It Does
 
@@ -26,7 +26,16 @@ cp .env.example .env
 uv sync
 ```
 
-### 2. Query the Knowledge Bot
+### 2. Launch the Web UI
+
+```bash
+source .venv/bin/activate
+python app.py
+```
+
+Opens at `http://127.0.0.1:7860` — type a question, get an answer with sources and latency. Includes example prompts.
+
+### 3. Or Use the CLI
 
 ```bash
 # Activate the uv environment
@@ -66,7 +75,7 @@ LATENCY: 1234.5ms
 ============================================================
 ```
 
-### 3. Evaluate Metrics
+### 4. Evaluate Metrics
 
 ```bash
 # Run full evaluation (latency + accuracy)
@@ -85,7 +94,9 @@ src/products_catalog.json  ← Product specs (6 Bosch HVAC systems)
          ↓
     src/rag.py            ← RAG pipeline (embeddings + retrieval)
          ↓
-    src/cli.py            ← CLI interface (Click)
+    ┌────┴────┐
+ app.py     src/cli.py     ← Gradio web UI / CLI interface
+  (Web)        (CLI)
          ↓
   User questions
 ```