Update app.py

app.py

@@ -13,6 +13,7 @@ from sklearn.ensemble import RandomForestClassifier
 from sklearn.model_selection import train_test_split, cross_val_score
 from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
 from sklearn.preprocessing import LabelEncoder
+from smolagent.types import AgentText
 
 # Authenticate with Hugging Face
 hf_token = os.getenv("HF_TOKEN")
@@ -53,6 +54,8 @@ agent = CodeAgent(
     additional_authorized_imports=["numpy", "pandas", "matplotlib.pyplot", "seaborn"]
 )
 
+
+
 def run_agent(_):
     if df_global is None:
         return "Please upload a file first.", []
@@ -73,7 +76,7 @@ def run_agent(_):
        - At least 3 visualizations showing important trends.
     4. Derive at least 3 actionable real-world insights.
     5. Save all visualizations to ./figures/ directory.
-    Return a dictionary with keys:
+    Return a JSON object with keys:
       - 'insights': clean bullet-point insights.
       - 'figures': list of file paths of generated visualizations.
     """
@@ -83,11 +86,22 @@ def run_agent(_):
         additional_args={"source_file": temp_file.name}
     )
 
-    # Now, result is expected to be a dictionary
-    insights = result.get("insights", "No insights generated.")
-    image_paths = result.get("figures", [])
+    # Convert AgentText object to string and parse it
+    if isinstance(result, AgentText):
+        import json
+        result_str = result.text.strip()
+
+        try:
+            result_dict = json.loads(result_str)
+        except json.JSONDecodeError:
+            return f"Error decoding agent response: {result_str}", []
+
+        insights = result_dict.get("insights", "No insights generated.")
+        image_paths = result_dict.get("figures", [])
+        return insights, image_paths
+    else:
+        return "Unexpected result type from agent", []
 
-    return insights, image_paths