Update app.py

app.py

@@ -19,9 +19,12 @@ def process_csv(file):
     df["Sentiment"] = df["Feedback"].apply(lambda x: pipe(x)[0]["label"])
     return {"df": df}, "✅ CSV processed!"
 
-def predict_attrition_risk(employee_name: str, sentiment: str):
+def predict_attrition_risk(employee_name: str, sentiment: str, explanation: str):
     risk_mapping = {"positive": "Low Risk", "neutral": "Medium Risk", "negative": "High Risk"}
-    return f"{employee_name}: {risk_mapping.get(sentiment.lower(), 'Unknown Sentiment')}"
+    risk_level = risk_mapping.get(sentiment.lower(), "Unknown Sentiment")
+
+    return f"**{employee_name}**: {risk_level} risk\n\n📝 {explanation}"
+
 
 def analyze_attrition_with_llm(df_dict, hr_query):
     if df_dict is None or "df" not in df_dict:
@@ -29,38 +32,47 @@ def analyze_attrition_with_llm(df_dict, hr_query):
     
     df = df_dict["df"]
     employees_data = {row["Employee"].strip(): row["Sentiment"] for _, row in df.iterrows()}
+
+    # LLM function calling with enhanced prompt
+    prompt = f"""
+    HR Query: {hr_query}
+    Employees Data: {json.dumps(employees_data, indent=2)}
+
+    Based on the sentiment of employee feedback, predict their attrition risk as High, Medium, or Low.
+    Additionally, provide a **short summary (~50 words)** explaining why this risk level was assigned.
+    """
     
-    # LLM function calling
-    prompt = f"HR Query: {hr_query}\nEmployees Data: {json.dumps(employees_data, indent=2)}"
     response = client.chat.completions.create(
         model="gpt-4-turbo",
         messages=[{"role": "user", "content": prompt}],
         functions=[
             {
                 "name": "predict_attrition_risk",
-                "description": "Predicts attrition risk based on sentiment.",
+                "description": "Predicts attrition risk based on sentiment and explains the reasoning.",
                 "parameters": {
                     "type": "object",
                     "properties": {
                         "employee_name": {"type": "string", "description": "Employee's name"},
-                        "sentiment": {"type": "string", "description": "Extracted sentiment"}
+                        "sentiment": {"type": "string", "description": "Extracted sentiment"},
+                        "explanation": {"type": "string", "description": "Short reasoning for the risk level (50 words)."}
                     },
-                    "required": ["employee_name", "sentiment"]
+                    "required": ["employee_name", "sentiment", "explanation"]
                 }
             }
         ],
         function_call="auto"
     )
-    
+
     message = response.choices[0].message
     if message.function_call:
         try:
             function_call = json.loads(message.function_call.arguments)
             employee_name = function_call.get("employee_name")
             sentiment = function_call.get("sentiment")
-            
+            explanation = function_call.get("explanation")
+
             if employee_name and sentiment:
-                return predict_attrition_risk(employee_name, sentiment)
+                return f"**{employee_name}**: {sentiment} risk\n\n📝 {explanation}"
         except Exception as e:
             return f"❌ Error processing LLM function call: {str(e)}"