Update app.py

app.py

@@ -11,9 +11,13 @@ MODEL = "gpt-5.1"
 
 client = OpenAI(api_key=API_KEY)
 
+
+# ---------------- PDF Upload ----------------
 def upload_pdf(path):
     return client.files.create(file=open(path, "rb"), purpose="assistants").id
 
+
+# ---------------- Prompt ----------------
 def prompt():
     return (
         "Extract structured JSON from the attached logistics document. Return ONLY valid JSON.\n"
@@ -45,34 +49,37 @@ def prompt():
         "  ],\n"
         "  \"custom_fields\": {}\n"
         "}\n\n"
+
         "SHIP FROM RULES:\n"
         "- If explicit fields like 'Origin', 'Ship From' exist, extract that value.\n"
-        "- If the document is an email-style inbound notice (header block) and shows:\n"
-        "    From: Name <email>\n"
+        "- If email header block exists:\n"
+        "      From: Name <email>\n"
         "  then ship_from_name = Name, ship_from_email = email.\n"
-        "- If only an email exists and no human name, set both fields to that email.\n"
-        "- If both Origin and an email sender exist, use Origin for ship_from_name and still capture the email under ship_from_email.\n"
+        "- If only email exists, set both fields to email.\n"
+        "- If both Origin and email sender exist, name = Origin and email under custom_fields.\n"
         "- Priority: Origin → Email Name → Mill → Sender block → null.\n\n"
+
         "CARRIER / EQUIPMENT RULE:\n"
-        "- If the table contains:\n"
-        "      Equipment id = <value>\n"
-        "      Mark = <value>\n"
-        "  then ALWAYS treat 'Equipment id' as the railcar number.\n"
-        "- NEVER use 'Mark' as railcar number.\n"
-        "- Carrier type must match the carrier text exactly (e.g., CHICAGO RAIL LINK).\n\n"
+        "- If table shows 'Equipment id = X' and 'Mark = Y', then X = rail_car_number.\n"
+        "- 'Mark' must never be used as the railcar number.\n\n"
+
         "INVENTORY RULES:\n"
-        "- Do not merge length groups. Each unique length or dimension is its own variant.\n"
-        "- Extract pcs_per_pkg, packages, pieces, fbm exactly as written.\n"
+        "- Each dimension group must remain separate.\n"
+        "- pieces_per_pkg, packages, pieces, fbm must be exact.\n"
         "- total_pcs = sum of pieces.\n"
         "- total_fbm = sum of fbm.\n\n"
+
         "TOTAL QUANTITY RULE:\n"
-        "- Use explicit totals if they appear.\n"
-        "- If no explicit total quantity appears, leave null.\n\n"
+        "- Use explicit totals. If no total, leave null.\n\n"
+
         "CUSTOM FIELDS RULE:\n"
-        "- Capture all meaningful leftover fields not part of main schema.\n\n"
+        "- Capture leftover meaningful text.\n\n"
+
         "Return ONLY the JSON."
     )
 
+
+# ---------------- Extraction ----------------
 def extract(file):
     path = Path(file.name)
     suffix = path.suffix.lower()
@@ -87,7 +94,10 @@ def extract(file):
         b64 = base64.b64encode(path.read_bytes()).decode()
         content = [
             {"type": "text", "text": prompt()},
-            {"type": "image_url", "image_url": {"url": f"data:image/{suffix[1:]};base64,{b64}"}}
+            {
+                "type": "image_url",
+                "image_url": {"url": f"data:image/{suffix[1:]};base64,{b64}"}
+            }
         ]
 
     r = client.chat.completions.create(
@@ -100,18 +110,24 @@ def extract(file):
     e = text.rfind("}")
     return text[s:e+1]
 
+
 def ui(file):
     return extract(file)
 
+
+# ---------------- Sample Images (Preview Enabled) ----------------
 examples = [
-    "IMG_0001.jpg",
-    "IMG_0002.jpg"
+    ["IMG_0001.jpg"],
+    ["IMG_0002.jpg"]
 ]
 
+
+# ---------------- Gradio App ----------------
 gr.Interface(
     fn=ui,
     inputs=gr.File(label="Upload PDF or Image"),
     outputs=gr.JSON(label="Extracted JSON"),
     title="Logistics OCR Data Extractor (GPT-5.1)",
-    examples=examples
+    examples=examples,
+    examples_per_page=2
 ).launch(share=True)