Create app.py

app.py

@@ -0,0 +1,105 @@
+import base64
+import json
+import os
+from glob import glob
+
+import gradio as gr
+from openai import OpenAI
+from transformers import pipeline
+
+CLASS_LABELS = ["Egyptian Mau", "leonberger", "samoyed"]
+
+MODEL_REPO = "vasanthi8134/oxford-pets-3class-vit"
+CLIP_MODEL = "openai/clip-vit-base-patch32"
+OPENAI_MODEL = os.getenv("OPENAI_MODEL", "gpt-4.1-mini")
+
+openai_api_key = os.getenv("OPENAI_API_KEY")
+openai_client = OpenAI(api_key=openai_api_key) if openai_api_key else None
+
+vit_classifier = pipeline(
+    "image-classification",
+    model=MODEL_REPO,
+)
+
+clip_classifier = pipeline(
+    "zero-shot-image-classification",
+    model=CLIP_MODEL,
+)
+
+def encode_image(image_path):
+    with open(image_path, "rb") as f:
+        return base64.b64encode(f.read()).decode("utf-8")
+
+def classify_with_openai(image_path):
+    if openai_client is None:
+        return {
+            "error": "Missing OPENAI_API_KEY in Hugging Face Space Secrets."
+        }
+
+    prompt = (
+        "Classify the pet in this image. "
+        f"Choose exactly one label from this list: {CLASS_LABELS}. "
+        'Return valid JSON with keys: "label", "confidence", "reasoning". '
+        "Confidence must be a number between 0 and 1."
+    )
+
+    base64_image = encode_image(image_path)
+
+    response = openai_client.responses.create(
+        model=OPENAI_MODEL,
+        input=[
+            {
+                "role": "user",
+                "content": [
+                    {"type": "input_text", "text": prompt},
+                    {
+                        "type": "input_image",
+                        "image_url": f"data:image/jpeg;base64,{base64_image}",
+                    },
+                ],
+            }
+        ],
+    )
+
+    try:
+        return json.loads(response.output_text)
+    except Exception:
+        return {"raw_response": response.output_text}
+
+def classify_pet(image_path):
+    vit_results = vit_classifier(image_path)
+    vit_output = {item["label"]: round(float(item["score"]), 4) for item in vit_results}
+
+    clip_results = clip_classifier(image_path, candidate_labels=CLASS_LABELS)
+    clip_output = {item["label"]: round(float(item["score"]), 4) for item in clip_results}
+
+    openai_output = classify_with_openai(image_path)
+
+    return {
+        "your_model_vit": vit_output,
+        "open_source_clip": clip_output,
+        "closed_source_openai": openai_output,
+    }
+
+example_files = []
+for ext in ["jpg", "jpeg", "png", "webp"]:
+    example_files.extend(glob(f"example_images/*.{ext}"))
+    example_files.extend(glob(f"example_images/*.{ext.upper()}"))
+
+example_files = [[path] for path in sorted(example_files)]
+
+iface = gr.Interface(
+    fn=classify_pet,
+    inputs=gr.Image(type="filepath", label="Upload pet image"),
+    outputs=gr.JSON(label="Model comparison"),
+    title="Pet Classification Comparison",
+    description=(
+        "Compare a fine-tuned ViT model, a zero-shot CLIP model, "
+        "and an OpenAI vision model on 3 pet classes: "
+        "Egyptian Mau, leonberger, samoyed."
+    ),
+    examples=example_files if example_files else None,
+    allow_flagging="never",
+)
+
+iface.launch()