Add application file 10

app.py

@@ -174,18 +174,35 @@ def process_po(po_df, sku_df):
 async def predict_batch(request: POBatchRequest):
     try:
         po_df = pd.DataFrame([item.dict() for item in request.items])
+
+        # 🔧 Rename fields to match what process_po() expects
+        po_df.rename(columns={
+            "product_name": "Product_Name",
+            "quantity": "Quantity",
+            "delivery_date": "Delivery_Date",
+            "filename": "Filename",
+            "company_name": "Company_Name"
+        }, inplace=True)
+
         processed_df = process_po(po_df, sku_df)
+
+        # 🔁 Prepare response using updated column names
         response = processed_df[[
             "Product_Name", "predicted_risk_label", "missing_field_score_v2",
             "semantic_signal", "delivery_lag_flag", "description_token_rarity_score",
             "filename_type_encoded"
         ]].copy()
         response["poid"] = processed_df.get("POID", "")
+
+        # 🔁 Convert to JSON format with camelCase keys
         data = response.rename(columns={"Product_Name": "product_name"}).to_dict(orient="records")
+
         return {"data": data}
+
     except Exception as e:
         logger.error(f"Prediction failed: {e}")
         raise HTTPException(status_code=500, detail=str(e))
 
+
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=7860)