Update evaluate.py

evaluate.py

@@ -581,6 +581,7 @@ def run_comprehensive_evaluation(
 - **Behaviour F1 (avg)**: {bf1_mean:.2f}%
 - **Emotion F1 (avg)**: {ef1_mean:.2f}%
 - **Topic F1 (avg)**: {tf1_mean:.2f}%
+- **Context F1 (avg)**: {cf1_mean:.2f}%
 """
 # END of summary_text
 
@@ -607,7 +608,6 @@ def run_comprehensive_evaluation(
             recall_at_5_mean = to_f(df["recall_at_5"]).mean() * 100
             
             rag_summary = f"""
-- **Context F1 (avg)**: {cf1_mean:.2f}%
 - **RAG: Context Precision**: {context_precision_mean * 100:.1f}%
 - **RAG: Context Recall**: {context_recall_mean * 100:.1f}%
 - **RAG: Recall@5**: {recall_at_5_mean:.1f}%