Update app.py

app.py

@@ -8,6 +8,10 @@ import json
 import base64
 from PIL import Image
 import tempfile
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.responses import JSONResponse, HTMLResponse
+from fastapi.middleware.cors import CORSMiddleware
+import uvicorn
 
 warnings.filterwarnings("ignore")
 
@@ -66,7 +70,25 @@ DR_CLASSES = ["No DR", "Mild", "Moderate", "Severe", "Proliferative DR"]
 DME_CLASSES = ["No DME", "Low Risk", "High Risk"]
 
 # ============================================================
-# 3. PREPROCESSING FUNCTIONS
+# 3. CREATE FASTAPI APP
+# ============================================================
+app = FastAPI(
+    title="DR & DME Detection API",
+    description="API untuk mendeteksi Diabetic Retinopathy dan Diabetic Macular Edema dari citra retina",
+    version="1.0.0"
+)
+
+# Enable CORS for mobile access
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# ============================================================
+# 4. PREPROCESSING FUNCTIONS
 # ============================================================
 def preprocess_pil_image(img):
     """Preprocess PIL Image for prediction"""
@@ -84,7 +106,7 @@ def preprocess_pil_image(img):
     return np.expand_dims(arr, 0)
 
 # ============================================================
-# 4. SOFTMAX SAFETY
+# 5. SOFTMAX SAFETY
 # ============================================================
 def ensure_probability(x):
     x = np.asarray(x, dtype=np.float32)
@@ -94,7 +116,7 @@ def ensure_probability(x):
     return x
 
 # ============================================================
-# 5. CORE PREDICTION FUNCTION
+# 6. CORE PREDICTION FUNCTION
 # ============================================================
 def predict_image(image):
     """Core prediction function that returns structured data"""
@@ -182,7 +204,6 @@ def predict_image(image):
         else:  # High Risk
             rec_dme = "Disarankan segera mendapatkan evaluasi klinis dan terapi oleh dokter spesialis mata."
 
-        # Return both structured data and HTML
         return {
             "success": True,
             "predictions": {
@@ -210,38 +231,50 @@ def predict_image(image):
         }
 
 # ============================================================
-# 6. API PREDICT FUNCTION UNTUK /run/predict
+# 7. FASTAPI ENDPOINTS
 # ============================================================
-def api_predict(image):
+@app.get("/")
+async def root():
+    """Root endpoint"""
+    return {
+        "message": "DR & DME Detection API",
+        "version": "1.0.0",
+        "endpoints": {
+            "docs": "/docs",
+            "health": "/health",
+            "predict": "/predict",
+            "predict_form": "/predict_form",
+            "gradio_ui": "/gradio"
+        }
+    }
+
+@app.get("/health")
+async def health_check():
+    """Health check endpoint"""
+    return {
+        "status": "healthy",
+        "model_loaded": best_model is not None,
+        "timestamp": tf.timestamp().numpy().astype(float)
+    }
+
+@app.post("/predict")
+async def predict_endpoint(file: UploadFile = File(...)):
     """
-    Function untuk API endpoint /run/predict
-    Gradio akan secara otomatis mengkonversi input ke format yang tepat
+    Predict endpoint for JSON base64 input
+    Accepts: JSON with base64 image
     """
     try:
-        if image is None:
-            return {"error": "No image provided"}
-        
-        # Jika input adalah dictionary (dari JSON API call)
-        if isinstance(image, dict):
-            if "data" in image:
-                # Handle base64 dari JSON API
-                return handle_api_json_input(image)
+        # Read and parse JSON
+        content = await file.read()
+        try:
+            data = json.loads(content)
+        except:
+            raise HTTPException(status_code=400, detail="Invalid JSON format")
         
-        # Jika input adalah file/bytes (dari form-data)
-        # Gradio sudah otomatis konversi ke PIL Image
-        result = predict_image(image)
-        return result
+        if "data" not in data:
+            raise HTTPException(status_code=400, detail="Missing 'data' field in JSON")
         
-    except Exception as e:
-        return {
-            "success": False,
-            "error": f"API processing error: {str(e)}"
-        }
-
-def handle_api_json_input(image_data):
-    """Handle JSON input dengan base64"""
-    try:
-        img_data = image_data["data"]
+        img_data = data["data"]
         if isinstance(img_data, list):
             img_data = img_data[0]
         
@@ -254,16 +287,48 @@ def handle_api_json_input(image_data):
         img = Image.open(io.BytesIO(img_bytes)).convert("RGB")
         
         # Get prediction
-        return predict_image(img)
+        result = predict_image(img)
+        
+        if not result["success"]:
+            raise HTTPException(status_code=500, detail=result["error"])
         
+        return JSONResponse(content=result)
+        
+    except HTTPException:
+        raise
     except Exception as e:
-        return {
-            "success": False,
-            "error": f"Base64 processing error: {str(e)}"
-        }
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/predict_form")
+async def predict_form_endpoint(file: UploadFile = File(...)):
+    """
+    Predict endpoint for form-data file upload
+    Accepts: image file (jpg, png, jpeg)
+    """
+    try:
+        # Check file type
+        if not file.content_type.startswith('image/'):
+            raise HTTPException(status_code=400, detail="File must be an image")
+        
+        # Read image
+        contents = await file.read()
+        img = Image.open(io.BytesIO(contents)).convert("RGB")
+        
+        # Get prediction
+        result = predict_image(img)
+        
+        if not result["success"]:
+            raise HTTPException(status_code=500, detail=result["error"])
+        
+        return JSONResponse(content=result)
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
 
 # ============================================================
-# 7. FORMAT OUTPUT FOR GRADIO UI
+# 8. GRADIO UI FUNCTIONS (for Web Interface)
 # ============================================================
 def format_prediction_html(result):
     """Format prediction result as HTML for Gradio"""
@@ -374,9 +439,6 @@ def format_prediction_html(result):
     
     return html
 
-# ============================================================
-# 8. GRADIO UI FUNCTION
-# ============================================================
 def gradio_predict(image):
     """Main function for Gradio UI"""
     if image is None:
@@ -389,54 +451,30 @@ def gradio_predict(image):
     return format_prediction_html(result)
 
 # ============================================================
-# 9. CREATE GRADIO INTERFACES
-# ============================================================
-
-# Interface untuk Web UI
-web_interface = gr.Interface(
-    fn=gradio_predict,
-    inputs=gr.Image(type="pil", label="📤 Upload Gambar Retina"),
-    outputs=gr.HTML(label="📊 Hasil Analisis"),
-    title="🩺 DETEKSI DIABETIC RETINOPATHY & DME",
-    description="Sistem AI untuk Analisis Citra Fundus Retina",
-    allow_flagging="never"
-)
-
-# Interface untuk API (akan digunakan oleh /run/predict)
-api_interface = gr.Interface(
-    fn=api_predict,
-    inputs=gr.Image(type="pil"),
-    outputs=gr.JSON(),
-    title="API Endpoint",
-    description="Use this endpoint for API calls",
-    allow_flagging="never"
-)
-
-# ============================================================
-# 10. MULTI TEST IMAGES
+# 9. PREPARE EXAMPLE IMAGES
 # ============================================================
-TEST_IMAGES = [
-    "IDRiD_001test.jpg",
-    "IDRiD_004test.jpg",
-    "IDRiD_005test.jpg",
-    "IDRiD_006test.jpg",
-    "IDRiD_007test.jpg",
-    "IDRiD_008test.jpg",
-    "IDRiD_009test.jpg",
-    "IDRiD_010test.jpg",
-    "IDRiD_011test.jpg",
-    "IDRiD_012test.jpg",
-]
-
-TEST_IMAGES = [[p] for p in TEST_IMAGES if os.path.exists(p)]
-
+def get_example_images():
+    """Get example images for demo"""
+    example_images = []
+    
+    # Check current directory and subdirectories
+    for root, dirs, files in os.walk("."):
+        for file in files:
+            if file.lower().endswith(('.jpg', '.jpeg', '.png')):
+                # Skip very large files
+                filepath = os.path.join(root, file)
+                if os.path.getsize(filepath) < 5 * 1024 * 1024:  # 5MB limit
+                    example_images.append([filepath])
+                    if len(example_images) >= 8:  # Max 8 examples
+                        break
+    
+    return example_images[:8]  # Return max 8 examples
 
 # ============================================================
-# 11. CREATE GRADIO APP WITH BLOCKS
+# 10. CREATE GRADIO APP
 # ============================================================
 with gr.Blocks(
     title="DR & DME Detection",
-    # css=CUSTOM_CSS,
     theme=gr.themes.Soft()
 ) as demo:
     
@@ -450,123 +488,112 @@ with gr.Blocks(
     - **Diabetic Macular Edema (DME)**: Pembengkakan di makula
     """)
     
-    # Create tabs for Web UI and API
-    with gr.Tabs():
-        # Tab 1: Web UI
-        with gr.TabItem("🌐 Web Interface"):
-            with gr.Row():
-                with gr.Column(scale=1):
-                    # Upload section
-                    image_input = gr.Image(
-                        type="pil",
-                        label="📤 Upload Gambar Retina",
-                        height=300
-                    )
-                    
-                    upload_btn = gr.Button(
-                        "🔍 Analisis Gambar",
-                        variant="primary",
-                        size="lg"
-                    )
-                    
-                    gr.Markdown("""
-                    **Format yang didukung:** JPG, PNG, JPEG  
-                    **Ukuran rekomendasi:** 224×224 piksel  
-                    **Warna:** RGB (akan dikonversi otomatis)
-                    """)
-                
-                with gr.Column(scale=2):
-                    # Results section
-                    output_html = gr.HTML(
-                        label="📊 Hasil Analisis",
-                        value="<div style='text-align: center; padding: 50px; color: #666;'>Hasil analisis akan muncul di sini setelah mengupload gambar.</div>"
-                    )
-
-
-            gr.Markdown("### 🧪 Data Testing")
-            gr.Examples(
-                examples=TEST_IMAGES,
-                inputs=image_input
+    with gr.Row():
+        with gr.Column(scale=1):
+            # Upload section
+            image_input = gr.Image(
+                type="pil",
+                label="📤 Upload Gambar Retina",
+                height=300
             )
             
-            # Connect button to function
-            upload_btn.click(
-                fn=gradio_predict,
-                inputs=image_input,
-                outputs=output_html
+            upload_btn = gr.Button(
+                "🔍 Analisis Gambar",
+                variant="primary",
+                size="lg"
             )
             
-            # Also trigger on image upload
-            image_input.change(
-                fn=gradio_predict,
-                inputs=image_input,
-                outputs=output_html
-            )
-        
-        # Tab 2: API Interface
-        with gr.TabItem("🔧 API Endpoint"):
             gr.Markdown("""
-            ### API Endpoint untuk Mobile App
-            
-            **URL:** `/run/predict`
-            
-            **Method:** POST
-            
-            **Content-Type:** `multipart/form-data` atau `application/json`
+            **Format yang didukung:** JPG, PNG, JPEG  
+            **Ukuran rekomendasi:** 224×224 piksel  
+            **Warna:** RGB (akan dikonversi otomatis)
             """)
-            
-            with gr.Row():
-                with gr.Column():
-                    api_image_input = gr.Image(
-                        type="pil",
-                        label="Test API dengan gambar"
-                    )
-                    api_test_btn = gr.Button("Test API", variant="secondary")
-                
-                with gr.Column():
-                    api_output = gr.JSON(
-                        label="API Response",
-                        value={"info": "API response akan muncul di sini"}
-                    )
-            
-            # Connect API test button
-            api_test_btn.click(
-                fn=api_predict,
-                inputs=api_image_input,
-                outputs=api_output
+        
+        with gr.Column(scale=2):
+            # Results section
+            output_html = gr.HTML(
+                label="📊 Hasil Analisis",
+                value="<div style='text-align: center; padding: 50px; color: #666;'>Hasil analisis akan muncul di sini setelah mengupload gambar.</div>"
             )
-            
-            gr.Markdown("""
-            ### 📋 Contoh Penggunaan API
-            
-            **cURL dengan file:**
-            ```bash
-            curl -X POST "https://[your-space].hf.space/run/predict" \\
-              -F "data=@retina_image.jpg"
-            ```
-            
-            **Python:**
-            ```python
-            import requests
-            
-            with open("retina_image.jpg", "rb") as f:
-                response = requests.post(
-                    "https://[your-space].hf.space/run/predict",
-                    files={"data": f}
-                )
-            print(response.json())
-            ```
-            """)
     
+    # Examples section
+    example_images = get_example_images()
+    if example_images:
+        gr.Markdown("### 🧪 Contoh Gambar (Klik untuk mencoba)")
+        gr.Examples(
+            examples=example_images,
+            inputs=image_input,
+            outputs=output_html,
+            fn=gradio_predict,
+            cache_examples=False
+        )
+    
+    # API Info section
+    gr.Markdown("---")
+    with gr.Accordion("📱 Akses API dari Mobile App", open=False):
+        gr.Markdown("""
+        ### API Endpoints:
+        
+        1. **POST /predict_form** - Upload file gambar
+           ```bash
+           curl -X POST "https://kodetr-idrid.hf.space/predict_form" \\
+             -F "file=@retina_image.jpg"
+           ```
+        
+        2. **POST /predict** - JSON dengan base64
+           ```json
+           {
+             "data": "data:image/jpeg;base64,/9j/4AAQSkZJRg..."
+           }
+           ```
+        
+        3. **GET /health** - Health check
+        4. **GET /** - API info
+        """)
+    
+    # Connect button to function
+    upload_btn.click(
+        fn=gradio_predict,
+        inputs=image_input,
+        outputs=output_html
+    )
+
+# ============================================================
+# 11. MOUNT GRADIO TO FASTAPI
+# ============================================================
+@app.get("/gradio")
+async def gradio_interface():
+    """Redirect to Gradio interface"""
+    return HTMLResponse("""
+    <html>
+        <head>
+            <meta http-equiv="refresh" content="0; url=/gradio/" />
+        </head>
+        <body>
+            <p>Redirecting to Gradio interface...</p>
+        </body>
+    </html>
+    """)
+
+# Mount Gradio app to FastAPI
+app = gr.mount_gradio_app(app, demo, path="/gradio")
 
 # ============================================================
-# 11. LAUNCH FOR HUGGING FACE
+# 12. MAIN ENTRY POINT
 # ============================================================
 if __name__ == "__main__":
-    # Launch untuk Hugging Face Spaces
-    demo.launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-        share=False,
-        debug=False
+    print("\n" + "="*60)
+    print("🚀 SERVER STARTING")
+    print("="*60)
+    print(f"📱 FastAPI: http://0.0.0.0:7860")
+    print(f"📊 API Docs: http://0.0.0.0:7860/docs")
+    print(f"🖥️  Gradio UI: http://0.0.0.0:7860/gradio")
+    print(f"🏥 Health Check: http://0.0.0.0:7860/health")
+    print("="*60)
+    
+    uvicorn.run(
+        app,
+        host="0.0.0.0",
+        port=7860,
+        log_level="info"
     )