Upload 4 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+IMG_0001.jpg filter=lfs diff=lfs merge=lfs -text
+IMG_0002.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,87 @@
+import base64
+import json
+from pathlib import Path
+import gradio as gr
+from openai import OpenAI
+
+API_KEY = "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"
+MODEL = "gpt-5.1"
+
+client = OpenAI(api_key=API_KEY)
+
+SAMPLE_DIR = Path("samples")
+SAMPLES = {
+    "Sample 1 (IMG_0001.jpg)": SAMPLE_DIR / "IMG_0001.jpg",
+    "Sample 2 (IMG_0002.jpg)": SAMPLE_DIR / "IMG_0002.jpg",
+    "None": None
+}
+
+def upload_pdf(p):
+    f = client.files.create(file=open(p, "rb"), purpose="assistants")
+    return f.id
+
+def prompt():
+    return (
+        "Extract structured JSON:\n"
+        "{"
+        "\"po_number\":string|null,"
+        "\"ship_from\":string|null,"
+        "\"carrier_type\":string|null,"
+        "\"rail_car_number\":string|null,"
+        "\"total_quantity\":number|null,"
+        "\"inventories\":[{\"productName\":string,\"productCode\":string|null,"
+        "\"pcs\":number|null,\"dimensions\":string|null}],"
+        "\"custom_fields\":{}"
+        "}\n"
+        "Use only PDF/image content."
+    )
+
+def extract_from_path(path: Path):
+    suffix = path.suffix.lower()
+
+    if suffix == ".pdf":
+        fid = upload_pdf(path)
+        msg = [
+            {"type": "text", "text": prompt()},
+            {"type": "file", "file": {"file_id": fid}}
+        ]
+    else:
+        b64 = base64.b64encode(path.read_bytes()).decode()
+        msg = [
+            {"type": "text", "text": prompt()},
+            {
+                "type": "image_url",
+                "image_url": {"url": f"data:image/{suffix[1:]};base64,{b64}"}
+            }
+        ]
+
+    response = client.chat.completions.create(
+        model=MODEL,
+        messages=[{"role": "user", "content": msg}]
+    )
+
+    raw = response.choices[0].message.content
+    start = raw.find("{")
+    end = raw.rfind("}")
+    return raw[start:end+1]
+
+def run_extraction(uploaded_file, sample_name):
+    if uploaded_file is not None:
+        return extract_from_path(Path(uploaded_file.name))
+
+    if sample_name != "None":
+        sample_path = SAMPLES[sample_name]
+        return extract_from_path(sample_path)
+
+    return "Upload a file or select a sample."
+
+gr.Interface(
+    fn=run_extraction,
+    inputs=[
+        gr.File(label="Upload PDF or Image (optional)"),
+        gr.Dropdown(list(SAMPLES.keys()), value="None", label="Or choose a sample image")
+    ],
+    outputs=gr.JSON(label="Extracted JSON"),
+    title="Logistics OCR Text Extraction (OpenAI GPT-5.1)",
+    description="Upload your own PDF/image or choose a sample to test the extraction."
+).launch()

requirements.txt

@@ -0,0 +1,2 @@
+openai>=1.0.0
+gradio