update 1.0

Dockerfile

@@ -1,6 +1,11 @@
 # Use official Python slim image
 FROM python:3.11-slim
 
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
 # Create a non-root user
 RUN useradd -m -u 1000 user
 USER user
@@ -9,16 +14,25 @@ ENV PATH="/home/user/.local/bin:$PATH"
 # Set working directory
 WORKDIR /app
 
-# Copy and install dependencies
-COPY --chown=user ./requirements.txt requirements.txt
-RUN pip install --no-cache-dir --upgrade pip \
-    && pip install --no-cache-dir -r requirements.txt
+# Copy requirements first (for better caching)
+COPY --chown=user requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
 
-# Copy app files
-COPY --chown=user . /app
+# Copy application files
+COPY --chown=user . .
 
-# Expose default HF Spaces port
+# Make sure the model file exists (you'll need to add this)
+# COPY --chown=user best_model.pth .
+
+# Expose port (Hugging Face Spaces typically uses 7860)
 EXPOSE 7860
 
-# Run FastAPI app
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+  CMD curl -f http://localhost:7860/health || exit 1
+
+# Run the application
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1", "--log-level", "info"]

app.py

@@ -1,42 +1,117 @@
+# app.py
 import os
 import tempfile
-from fastapi import FastAPI, File, Form, UploadFile
+from fastapi import FastAPI, File, Form, UploadFile, HTTPException
 from fastapi.responses import JSONResponse
-from predictor import SimilarityPredictor  # <-- move your model code to predictor.py
+import logging
 
-# Load model once at startup
-MODEL_PATH = os.getenv("MODEL_PATH", "best_model.pth")
-THRESHOLD = float(os.getenv("THRESHOLD", 0.5))
-predictor = SimilarityPredictor(MODEL_PATH, threshold=THRESHOLD)
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
 app = FastAPI()
 
+# Global predictor variable
+predictor = None
+
+@app.on_event("startup")
+async def startup_event():
+    """Initialize predictor on startup"""
+    global predictor
+    try:
+        from predictor import SimilarityPredictor
+        MODEL_PATH = os.getenv("MODEL_PATH", "best_model.pth")
+        THRESHOLD = float(os.getenv("THRESHOLD", "0.5"))
+        
+        logger.info(f"Loading model from: {MODEL_PATH}")
+        logger.info(f"Using threshold: {THRESHOLD}")
+        
+        predictor = SimilarityPredictor(MODEL_PATH, threshold=THRESHOLD)
+        logger.info("✅ Model loaded successfully!")
+        
+    except Exception as e:
+        logger.error(f"❌ Failed to load model: {e}")
+        # Don't raise here - let the app start but handle in endpoints
+
+@app.get("/")
+async def root():
+    """Root endpoint"""
+    return {
+        "message": "Image-Text Similarity API is running",
+        "endpoints": {
+            "GET /": "This endpoint",
+            "GET /health": "Health check",
+            "POST /predict": "Predict similarity between image and text"
+        }
+    }
+
+@app.get("/health")
+async def health_check():
+    """Health check endpoint"""
+    global predictor
+    return {
+        "status": "healthy" if predictor is not None else "model_not_loaded",
+        "model_loaded": predictor is not None
+    }
+
 @app.post("/predict")
-async def predict(
+async def predict_similarity(
     file: UploadFile = File(...),
     text: str = Form(...)
 ):
+    """Predict similarity between uploaded image and text"""
+    global predictor
+    
+    if predictor is None:
+        raise HTTPException(
+            status_code=503, 
+            detail="Model not loaded. Check logs for initialization errors."
+        )
+    
+    tmp_path = None
     try:
-        # Save uploaded image temporarily
+        # Validate file type
+        if not file.content_type.startswith('image/'):
+            raise HTTPException(
+                status_code=400, 
+                detail=f"Invalid file type: {file.content_type}. Please upload an image."
+            )
+        
+        # Create temporary file
         with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tmp:
             tmp_path = tmp.name
             content = await file.read()
             tmp.write(content)
-
+        
+        logger.info(f"Processing image: {file.filename}, text: {text[:50]}...")
+        
         # Run prediction
         result = predictor.predict_similarity(tmp_path, text, verbose=False)
-
-        # Cleanup temp file
-        os.remove(tmp_path)
-
+        
         if result is None:
-            return JSONResponse({"error": "Prediction failed"}, status_code=500)
-
-        return JSONResponse(result)
+            raise HTTPException(status_code=500, detail="Prediction failed")
+        
+        logger.info(f"Prediction completed: {result['prediction']}")
+        return result
 
+    except HTTPException:
+        raise
     except Exception as e:
-        return JSONResponse({"error": str(e)}, status_code=500)
+        logger.error(f"Prediction error: {e}")
+        raise HTTPException(status_code=500, detail=f"Prediction failed: {str(e)}")
+    
+    finally:
+        # Cleanup temp file
+        if tmp_path and os.path.exists(tmp_path):
+            try:
+                os.remove(tmp_path)
+            except Exception as e:
+                logger.warning(f"Failed to cleanup temp file: {e}")
 
-@app.get("/")
-def home():
-    return {"message": "Image-Text Similarity API is running"}
+# Add middleware for better error handling
+@app.middleware("http")
+async def log_requests(request, call_next):
+    logger.info(f"{request.method} {request.url}")
+    response = await call_next(request)
+    logger.info(f"Response status: {response.status_code}")
+    return response