Update app.py

app.py

@@ -80,11 +80,11 @@ def run_agent(_):
        - Insightful relationships between key columns.
        - At least 3 visualizations showing important trends.
     4. Derive at least 3 actionable real-world insights.
-       5. Save all visualizations to ./figures/ directory.
-       6. "Ensure that all visualizations have figure size at least 8x6 and saved at 150+ dpi."
-       Return a JSON object with keys:
-         - 'insights': clean bullet-point insights.
-         - 'figures': list of file paths of generated visualizations.
+    5. Save all visualizations to ./figures/ directory.
+    6. Ensure all visualizations are at least 8x6 and saved at 150+ dpi.
+    Return a JSON object with keys:
+        - 'insights': clean bullet-point insights.
+        - 'figures': list of file paths of generated visualizations.
     """
 
     result = agent.run(
@@ -96,15 +96,13 @@ def run_agent(_):
         try:
             result = json.loads(result)
         except json.JSONDecodeError:
-            insights = "Failed to parse result from agent."
-            return insights, []
+            return "Failed to parse result from agent.", []
 
     if isinstance(result, dict):
         insights = result.get("insights", "No insights generated.")
         image_paths = result.get("figures", [])
     else:
-        insights = "Error: Unexpected result format from agent."
-        image_paths = []
+        return "Error: Unexpected result format from agent.", []
 
     images = []
     for path in image_paths:
@@ -112,7 +110,8 @@ def run_agent(_):
             images.append(Image.open(path))
         except Exception as e:
             print(f"Error loading image {path}: {e}")
-    return insights, images
+    return insights, images  # ⚠️ This must be a 2-element tuple
+
 
 
     
@@ -264,7 +263,6 @@ with gr.Blocks() as demo:
         lime_img = gr.Image(label="LIME Explanation")
 
 
-    #agent_btn.click(fn=run_agent, inputs=df_output, outputs=insights_output)
     agent_btn.click(fn=run_agent, inputs=df_output, outputs=[insights_output, visual_output])
     train_btn.click(fn=train_model, inputs=df_output, outputs=[metrics_output, trials_output])
     explain_btn.click(fn=explainability, inputs=df_output, outputs=[shap_img, lime_img])