Update app.py

app.py

@@ -18,29 +18,82 @@ INTERNAL_MODEL_MAP = {
     "Gemini 2.5 Pro": "gemini-2.5-pro",
 }
 EXTERNAL_MODEL_NAME = "prithivMLmods/Camel-Doc-OCR-062825 (External)"
-
 PROMPT_FREIGHT_JSON = """
 Please analyze the freight rate table in the file I provide and convert it into JSON in the following structure:
 {
   "shipping_line": "...",
   "shipping_line_code": "...",
+  "shipping_line_reason": "Why this carrier is chosen?",
   "fee_type": "Air Freight",
   "valid_from": ...,
   "valid_to": ...,
-  "charges": [...],
-  "local_charges": [...]
+  "charges": [
+    {
+      "frequency": "...",
+      "package_type": "...",
+      "aircraft_type": "...",
+      "direction": "Export or Import or null",
+      "origin": "...",
+      "destination": "...",
+      "charge_name": "...",
+      "charge_code": "...",
+      "charge_code_reason": "...",
+      "cargo_type": "...",
+      "currency": "...",
+      "transit": "...",
+      "transit_time": "...",
+      "weight_breaks": {
+        "M": ...,
+        "N": ...,
+        "+45kg": ...,
+        "+100kg": ...,
+        "+300kg": ...,
+        "+500kg": ...,
+        "+1000kg": ...,
+        "other": {
+          key: value
+        },
+        "weight_breaks_reason":"Why chosen weight_breaks?"
+      },
+      "remark": "..."
+    }
+  ],
+  "local_charges": [
+    {
+      "charge_name": "...",
+      "charge_code": "...",
+      "unit": "...",
+      "amount": ...,
+      "remark": "..."
+    }
+  ]
 }
 ### Date rules
-- valid_from: DD/MM/YYYY, 01/MM/YYYY, 01/01/YYYY or 'UFN'
-- valid_to: DD/MM/YYYY or 'UFN'
+- valid_from format:
+  - `DD/MM/YYYY` (if full date)
+  - `01/MM/YYYY` (if month+year only)
+  - `01/01/YYYY` (if year only)
+  - `UFN` if missing
+- valid_to:
+  - exact `DD/MM/YYYY` if present
+  - else `UFN`
 STRICT RULES:
-- Only return JSON, no explanation.
-- All rates must match the weight break columns (M,N,45kg,100kg,...).
-- Use IATA code for origin/destination.
-- Direction: Export if origin in Vietnam, else Import.
-- Combine with “notes” at bottom of PDF if relevant.
+- ONLY return a single JSON object as specified above.
+- All rates must exactly match the corresponding weight break columns (M,N,45kg, 100kg, 300kg, 500kg, 1000kg, etc.). set null if N/A. No assumptions or interpolations.
+- If the table shows "RQ" or similar, set value as "RQST".
+- Group same-price destinations into one record separated by "/".
+- Always use IATA code for origin and destination.
+- Flight number (e.g. ZH118) is not charge code.
+- Frequency: D[1-7]; 'Daily' = D1234567. Join multiple (e.g. D3,D4→D34).
+- If local charges exist, list them.
+- If validity missing, set null.
+- Direction: Export if origin is Vietnam (SGN, HAN, DAD...), else Import.
+- Provide short plain English reasons for "shipping_line_reason" & "charge_code_reason".
+- Replace commas in remarks with semicolons.
+- Only return JSON.
 """
 
+
 # ================== HELPERS ==================
 def _read_file_bytes(upload: Union[str, os.PathLike, dict, object] | None) -> bytes:
     if upload is None: