Update app.py

app.py

@@ -528,27 +528,34 @@ def generate_enhanced_analytics(date_range=None):
         else:
             most_used_model = "N/A"
         
+        # Create summary without nested f-strings to avoid the backslash issue
         summary = f"""
-        ## Analytics Summary
-        
-        ### Overview
-        - **Total API Requests**: {total_requests:,}
-        - **Total Tokens Used**: {total_tokens:,}
-        - **Estimated Cost**: ${total_estimated_cost:.2f}
-        - **Average Response Time**: {avg_response_time:.2f} seconds
-        - **Most Used Model**: {most_used_model}
-        - **Date Range**: {df["timestamp"].min().date()} to {df["timestamp"].max().date()}
-        
-        ### Model Costs Breakdown
-        {''.join([f"- **{cost['model']}**: {cost['tokens']:,} tokens / ${cost['cost']:.2f}\n" for cost in model_costs])}
-        
-        ### Usage Patterns
-        - **Busiest Day**: {df.groupby("date")["tokens_used"].sum().idxmax()} ({df[df["date"] == df.groupby("date")["tokens_used"].sum().idxmax()]["tokens_used"].sum():,} tokens)
-        - **Most Efficient Model**: {df.groupby("model")["response_time_sec"].mean().idxmin()} ({df.groupby("model")["response_time_sec"].mean().min():.2f}s avg response)
-        
-        ### Forecast
-        - **Projected Usage (Next 7 Days)**: {prediction_data["predicted_tokens"].sum():,.0f} tokens (estimated)
-        """
+## Analytics Summary
+
+### Overview
+- **Total API Requests**: {total_requests:,}
+- **Total Tokens Used**: {total_tokens:,}
+- **Estimated Cost**: ${total_estimated_cost:.2f}
+- **Average Response Time**: {avg_response_time:.2f} seconds
+- **Most Used Model**: {most_used_model}
+- **Date Range**: {df["timestamp"].min().date()} to {df["timestamp"].max().date()}
+
+### Model Costs Breakdown
+"""
+
+        # Add each model cost as a separate string concatenation
+        for cost in model_costs:
+            summary += f"- **{cost['model']}**: {cost['tokens']:,} tokens / ${cost['cost']:.2f}\n"
+
+        # Continue with the rest of the summary
+        summary += f"""
+### Usage Patterns
+- **Busiest Day**: {df.groupby("date")["tokens_used"].sum().idxmax()} ({df[df["date"] == df.groupby("date")["tokens_used"].sum().idxmax()]["tokens_used"].sum():,} tokens)
+- **Most Efficient Model**: {df.groupby("model")["response_time_sec"].mean().idxmin()} ({df.groupby("model")["response_time_sec"].mean().min():.2f}s avg response)
+
+### Forecast
+- **Projected Usage (Next 7 Days)**: {prediction_data["predicted_tokens"].sum():,.0f} tokens (estimated)
+"""
         
         return summary, model_usage_img, daily_usage_img, response_time_img, time_pattern_img, intent_analysis_img, model_comparison_img, forecast_chart, export_analytics_csv(df), df.to_dict("records")