Update app.py

app.py

@@ -1,48 +1,38 @@
 import gradio as gr
-import torch
-import time
-from PIL import Image
 from transformers import BlipProcessor, BlipForConditionalGeneration
-from utils import create_pdf
+from PIL import Image
+from fpdf import FPDF
+import os
+from datetime import datetime
 
-# Load model and processor
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model.to(device)
 
-def generate_caption(image):
-    start_time = time.time()
-    
-    if image.mode != "RGB":
-        image = image.convert("RGB")
-    
-    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)
+def analyze_image(image):
+    raw_image = Image.fromarray(image)
+    text = "Describe the construction site"
+    inputs = processor(raw_image, text, return_tensors="pt")
+    out = model.generate(**inputs)
+    caption = processor.decode(out[0], skip_special_tokens=True)
 
-    duration = time.time() - start_time
-    if duration > 5:
-        caption = f"⚠️ Took {round(duration, 2)}s: {caption}"
+    date_str = datetime.now().strftime("%Y-%m-%d")
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_font("Arial", size=12)
+    pdf.multi_cell(0, 10, f"Daily Progress Report - {date_str}\n\nCaption: {caption}")
     
-    return caption
-
-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
+    os.makedirs("reports", exist_ok=True)
+    file_path = f"reports/DPR_{date_str}.pdf"
+    pdf.output(file_path)
+    return caption, file_path
 
-iface = gr.Interface(
-    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"
+demo = gr.Interface(
+    fn=analyze_image,
+    inputs=gr.Image(type="numpy", label="Upload Site Photo"),
+    outputs=[gr.Textbox(label="Generated Caption"), gr.File(label="Download DPR PDF")],
+    title="Auto DPR Generator",
+    description="Upload a construction site image to generate a Daily Progress Report."
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    demo.launch()