Update app.py

app.py

@@ -1,32 +1,48 @@
-from transformers import BlipProcessor, BlipForConditionalGeneration
-from PIL import Image
 import gradio as gr
 import torch
+import time
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from utils import create_pdf
 
-# Load BLIP model and processor
+# Load model and processor
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
-model.eval()
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
 
-# Inference function
 def generate_caption(image):
+    start_time = time.time()
+    
     if image.mode != "RGB":
         image = image.convert("RGB")
     
-    inputs = processor(image, return_tensors="pt").to(device, torch.float16)
+    inputs = processor(images=image, return_tensors="pt").to(device)
     output = model.generate(**inputs, max_new_tokens=50)
     caption = processor.decode(output[0], skip_special_tokens=True)
+
+    duration = time.time() - start_time
+    if duration > 5:
+        caption = f"⚠️ Took {round(duration, 2)}s: {caption}"
+    
     return caption
 
-# Gradio interface
+def process_images(images):
+    results = []
+    for i, img in enumerate(images[:10]):  # Limit to 10 images
+        caption = generate_caption(img)
+        results.append(f"Image {i+1}: {caption}")
+    pdf_file = create_pdf(results)
+    return "\n\n".join(results), pdf_file
+
 iface = gr.Interface(
-    fn=generate_caption,
-    inputs=gr.Image(type="pil"),
-    outputs="text",
-    title="Construction Site Image-to-Text Generator",
-    description="Upload a site photo. The model will detect and describe construction activities."
+    fn=process_images,
+    inputs=gr.File(label="Upload up to 10 Site Images", type="file", file_types=[".jpg", ".png"], multiple=True),
+    outputs=["text", "file"],
+    title="Auto-DPR Generator from Site Images",
+    description="Upload construction site images. AI will auto-generate a progress summary and downloadable PDF.",
+    allow_flagging="never"
 )
 
-iface.launch()
+if __name__ == "__main__":
+    iface.launch()