Create app.py

app.py

@@ -0,0 +1,81 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from fastapi.middleware.cors import CORSMiddleware
+from transformers import pipeline
+from PIL import Image
+import base64
+import io
+import requests
+
+app = FastAPI(title="STOA Deepfake Detector API")
+
+# --- CORS ---
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# --- MODEL LOADING ---
+print("Booting Security Node. Loading Deepfake ViT model into memory...")
+pipe = pipeline("image-classification", model="dima806/deepfake_vs_real_image_detection")
+print("Agent Ready!")
+
+# --- REQUEST SCHEMA ---
+class PredictRequest(BaseModel):
+    image: str | None = None
+    image_url: str | None = None
+
+# --- ENDPOINTS ---
+@app.get("/health")
+def health_check():
+    return {"status": "ok"}
+
+@app.post("/predict")
+def predict(req: PredictRequest):
+    try:
+        img = None
+        
+        # 1. Handle URL Input (with the Wikipedia bypass fix from Task 24!)
+        if req.image_url:
+            headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"}
+            response = requests.get(req.image_url, stream=True, headers=headers)
+            if response.status_code != 200:
+                raise Exception(f"Could not download image. Server returned: {response.status_code}")
+            img = Image.open(response.raw).convert("RGB")
+            
+        # 2. Handle Base64 Input
+        elif req.image:
+            b64_data = req.image
+            if "," in b64_data:
+                b64_data = b64_data.split(",")[1]
+            image_bytes = base64.b64decode(b64_data)
+            img = Image.open(io.BytesIO(image_bytes)).convert("RGB")
+            
+        # 3. Handle Empty Request
+        else:
+            raise HTTPException(status_code=400, detail="Must provide 'image' (base64) or 'image_url'.")
+
+        # 4. Execute AI Math
+        results = pipe(img)
+        
+        # 5. Format to exact Task 25 specifications
+        scores_dict = {}
+        for res in results:
+            raw_label = res['label'].upper()
+            # Map standard model output to strict spec requirements
+            final_label = "DEEPFAKE" if "FAKE" in raw_label else "REAL"
+            scores_dict[final_label] = round(res['score'], 4)
+            
+        top_pred = max(scores_dict, key=scores_dict.get)
+        
+        return {
+            "prediction": top_pred,
+            "confidence": scores_dict[top_pred],
+            "scores": scores_dict
+        }
+        
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Failed to process face: {str(e)}")