Refactor README and tests, add new screenshots, and update setup script

- Cleaned up README.md by removing unnecessary blank lines.
- Updated test_llm_service.py to mock OpenAI API key for better error handling.
- Added multiple new screenshot files for documentation and demo purposes.
- Minor formatting adjustments in setup.sh to remove extra blank lines.
- Changed app.spec.js to wait for the full page load instead of DOM content loaded for more reliable test execution.

Signed-off-by: Andre Bossard <anbossar@microsoft.com>

Author: abossard

CSV/data.csv

@@ -43,10 +43,6 @@ All deep-dive guides now live under `docs/` for easier discovery:
 - **[Publishing Guide](docs/KBA_PUBLISHING.md)** – How to publish KBAs to different KB systems
 
 
-
-
-
-
 ### DSPy Prompt Tuning Playground
 
 > **NEW:** Interactive Jupyter notebook series teaching prompt optimization with DSPy
@@ -72,7 +68,6 @@ Open `00_introduction.ipynb` and follow the 8-notebook learning path. The notebo
 - Uses the same `LITELLM_MODEL` / `LITELLM_FALLBACK_MODELS` env vars as the backend
 
 
-
 ## 5-minute quick start (TL;DR)
 1. Clone the repo: `git clone <your-fork-url> && cd python-quart-vite-react`
 2. Run the automated bootstrap: `./setup.sh` (creates the repo-level `.venv`, installs frontend deps, installs Playwright)

README.md

@@ -66,8 +66,9 @@ def test_service_defaults_to_litellm(self):
 
     def test_service_forced_openai_without_key_raises(self):
         """Test that forcing openai backend without key raises error"""
-        with pytest.raises(LLMAuthenticationError, match="OpenAI API key not set"):
-            LLMService(backend="openai")  # No api_key, env cleared won't help since module-level loaded
+        with patch('llm_service.OPENAI_API_KEY', ''):
+            with pytest.raises(LLMAuthenticationError, match="OpenAI API key not set"):
+                LLMService(backend="openai")
 
     def test_service_forced_litellm_backend(self):
         """Test forcing LiteLLM backend even with API key"""