Update app.py

app.py

@@ -10,7 +10,7 @@ from PIL import Image
 from transformers import pipeline
 import gradio as gr
 from fastapi.responses import RedirectResponse
-import numpy as np
+
 # Initialize FastAPI
 app = FastAPI()
 
@@ -62,14 +62,19 @@ def extract_text_from_excel(excel_file):
 
 # Function to perform object detection using Torchvision
 def extract_text_from_image(image_file):
-    if isinstance(image_file, np.ndarray):  # Check if input is a NumPy array
-        image = Image.fromarray(image_file)  # Convert NumPy array to PIL image
-    else:
-        image = Image.open(image_file).convert("RGB")  # Handle file input
+    image = Image.open(image_file).convert("RGB")
+    image_tensor = transform(image).unsqueeze(0)
+
+    with torch.no_grad():
+        predictions = model(image_tensor)
+    
+    detected_objects = []
+    for label, score in zip(predictions[0]['labels'], predictions[0]['scores']):
+        if score > 0.7:
+            detected_objects.append(f"Object {label.item()} detected with confidence {score.item():.2f}")
+    
+    return "\n".join(detected_objects) if detected_objects else "No objects detected."
 
-    reader = easyocr.Reader(["en"])
-    result = reader.readtext(np.array(image))  # Convert PIL image back to NumPy array
-    return " ".join([res[1] for res in result])
 # Function to answer questions based on document content
 def answer_question_from_document(file, question):
     file_ext = file.name.split(".")[-1].lower()