Update app.py

app.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# app.py — Logistics OCR Extractor (PDF + Images) with strict ship_from rules
 
 import base64
 import json
@@ -13,7 +12,6 @@ MODEL = "gpt-5.1"
 client = OpenAI(api_key=API_KEY)
 
 
-# ----------------------- PDF Upload -----------------------
 def upload_pdf(path):
     f = client.files.create(
         file=open(path, "rb"),
@@ -22,12 +20,10 @@ def upload_pdf(path):
     return f.id
 
 
-# ----------------------- Prompt Builder -----------------------
 def build_prompt():
     return (
         "Extract structured JSON from this logistics shipping document. "
-        "Use only what appears in the PDF/image, never hallucinate. "
-        "Return strictly valid JSON in this schema:\n\n"
+        "Return ONLY valid JSON.\n\n"
         "{\n"
         "  \"po_number\": string|null,\n"
         "  \"ship_from\": string|null,\n"
@@ -58,29 +54,26 @@ def build_prompt():
 
         "SHIP_FROM EXTRACTION RULES (MANDATORY):\n"
         "1. If document contains explicit Origin/Ship From labels, extract that value.\n"
-        "2. If document is an email-based inbound notice and no explicit origin exists, "
-        "set ship_from = the email 'From:' field.\n"
+        "2. If it is an email-based inbound notice and no explicit origin exists, use the email 'From:' field.\n"
         "3. If both Origin and Mill exist, use Origin.\n"
-        "4. If only Mill exists AND it is clearly the shipping location, use Mill.\n"
-        "5. Priority order: Origin → Email From → Mill → Sender company block.\n"
-        "6. If none apply, ship_from = null.\n\n"
-
-        "Rules for inventories:\n"
-        "- Do NOT merge different lengths; create a separate variant per length.\n"
-        "- Extract EXACT numbers shown: packages, pcs_per_pkg, pieces, fbm.\n"
-        "- total_pcs = sum of all variant pieces.\n"
-        "- total_fbm = sum of all variant fbm.\n\n"
-
-        "Rules for total_quantity:\n"
-        "- If the document shows a total PCS value explicitly, use it.\n"
-        "- If only variants exist, do not compute total_quantity unless the document explicitly states it.\n\n"
-
-        "Parse tables carefully. If a dimension group (like 2x6) appears, use that.\n"
-        "Return only JSON. No explanations."
+        "4. If only Mill exists and is clearly the shipping point, use Mill.\n"
+        "5. Priority: Origin → Email From → Mill → Sender block.\n"
+        "6. If nothing matches, ship_from = null.\n\n"
+
+        "Inventory rules:\n"
+        "- Never merge different lengths.\n"
+        "- Extract packages, pcs_per_pkg, pieces, fbm EXACTLY.\n"
+        "- total_pcs = sum of variant pieces.\n"
+        "- total_fbm = sum of variant fbm.\n\n"
+
+        "total_quantity rules:\n"
+        "- Use the explicit total if shown.\n"
+        "- If not explicitly shown, do not infer.\n\n"
+
+        "Return ONLY the JSON."
     )
 
 
-# ----------------------- Extraction Logic -----------------------
 def extract(file):
     path = Path(file.name)
     suffix = path.suffix.lower()
@@ -112,15 +105,15 @@ def extract(file):
     return txt[s:e+1]
 
 
-# ----------------------- Gradio UI -----------------------
 def ui(file):
     return extract(file)
 
 
-# Sample images (optional)
-sample_files = [
-    ("IMG_0001.jpg", "/IMG_0001.jpg"),
-    ("IMG_0002.jpg", "/IMG_0002.jpg")
+# EXAMPLES must be ONLY filenames,
+# and these files must exist in the root directory of the Space.
+examples = [
+    "IMG_0001.jpg",
+    "IMG_0002.jpg"
 ]
 
 gr.Interface(
@@ -128,5 +121,5 @@ gr.Interface(
     inputs=gr.File(label="Upload PDF or Image"),
     outputs=gr.JSON(label="Extracted JSON"),
     title="Logistics OCR Data Extractor (GPT-5.1)",
-    examples=sample_files
+    examples=examples
 ).launch()