feat(app): improve UI and backend robustness per user feedback

app.py

@@ -19,7 +19,7 @@ def main_interface():
     with gr.Blocks(
         theme=tibetan_theme,
         title="Tibetan Text Metrics Web App",
-        css=tibetan_theme.get_css_string(),
+        css=tibetan_theme.get_css_string() + ".metric-description { padding: 1.5rem !important; }"
     ) as demo:
         gr.Markdown(
             """# Tibetan Text Metrics Web App
@@ -59,7 +59,7 @@ def main_interface():
                     semantic_toggle_radio = gr.Radio(
                         label="Compute semantic similarity? (Experimental)",
                         choices=["Yes", "No"],
-                        value="Yes",
+                        value="No",
                         info="Semantic similarity will be time-consuming. Choose 'No' to speed up analysis if these metrics are not required.",
                         elem_id="semantic-radio-group",
                     )
@@ -122,7 +122,7 @@ def main_interface():
         with gr.Row():
             with gr.Column():
                 output_analysis = gr.Markdown(
-                    "## AI Analysis\n*The AI will analyze your text similarities and provide insights into patterns and relationships. Make sure to set up your OpenRouter API key for this feature.*",
+                    "## AI Analysis\n*The AI will analyze your text similarities and provide insights into patterns and relationships.*",
                     elem_classes="gr-markdown"
                 )
                 
@@ -239,7 +239,7 @@ Each segment is represented as a vector of these TF-IDF scores, and the cosine s
                             This chart displays the number of words in each segment of your texts after tokenization.
                             """)
                         elif metric_key in metric_tooltips:
-                            gr.Markdown(value=metric_tooltips[metric_key])
+                            gr.Markdown(value=metric_tooltips[metric_key], elem_classes="metric-description")
                         else:
                             gr.Markdown(value=f"### {metric_key}\nDescription not found.")
                     

pipeline/llm_service.py

@@ -552,10 +552,9 @@ Your analysis will be performed using the `{model_name}` model. Provide a concis
         # Count how many expected content markers we find
         content_matches = sum(1 for term in expected_content if term.lower() in response.lower())
         
-        # If we find fewer than 3 expected content markers, it's likely not a good analysis
+        # If we find fewer than 3 expected content markers, log a warning
         if content_matches < 3:
             logger.warning(f"LLM response missing expected content sections (found {content_matches}/6)")
-            raise ValueError("Response does not contain expected analysis sections")
         
         # Check for text names from the dataset
         # Extract text names from the Text Pair column
@@ -580,7 +579,7 @@ Your analysis will be performed using the `{model_name}` model. Provide a concis
         response = f"<div class='llm-analysis'>\n{response}\n</div>"
         
         # Format the response into a markdown block
-        formatted_response = f"""## AI-Powered Analysis (Model: {model_name})"""
+        formatted_response = f"""## AI-Powered Analysis (Model: {model_name})\n\n{response}"""
     
         return formatted_response