Update app.py

app.py

@@ -1,6 +1,10 @@
-from transformers import BlipProcessor, BlipForConditionalGeneration
+import os
+import shutil
+import base64
+import time
+import concurrent.futures
 from PIL import Image
-import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
 import torch
 from datetime import datetime
 from reportlab.lib.pagesizes import letter
@@ -8,12 +12,8 @@ from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Image as PD
 from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
 from reportlab.lib import colors
 from simple_salesforce import Salesforce
-import os
 from dotenv import load_dotenv
-import base64
-import io
-import shutil
-import concurrent.futures
+import gradio as gr
 
 # Load environment variables from .env file
 load_dotenv()
@@ -31,23 +31,22 @@ except Exception as e:
     print(f"Failed to connect to Salesforce: {str(e)}")
 
 # Load BLIP model and processor
+device = "cuda" if torch.cuda.is_available() else "cpu"
 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)
+model.eval().to(device)
 
 # Inference function to generate captions dynamically based on image content
 def generate_captions_from_image(image):
     if image.mode != "RGB":
         image = image.convert("RGB")
-    
-    # Resize image for faster processing (use smaller resolution to speed up inference)
-    image = image.resize((320, 320))  # Reduced size for faster processing
+
+    # Resize for faster processing
+    image = image.resize((224, 224))  # Adjust to smaller resolution for faster inference
     
     # Preprocess the image and generate a caption
     inputs = processor(image, return_tensors="pt").to(device, torch.float16)
-    output = model.generate(**inputs, max_new_tokens=50)
+    output = model.generate(**inputs, max_length=50)
     caption = processor.decode(output[0], skip_special_tokens=True)
     
     return caption
@@ -258,7 +257,6 @@ iface = gr.Interface(
     description="Upload up to 10 site photos. The AI model will generate a text-based Daily Progress Report (DPR), save it as a PDF, and upload the PDF and images to Salesforce under Daily_Progress_Reports__c in the Files related list. Download the PDF locally if needed.",
     allow_flagging="never",
     css="#gradio-share-link-button-0 { display: none !important; }"
-
 )
 
 if __name__ == "__main__":