Update app.py

app.py

@@ -1,21 +1,25 @@
 import gradio as gr
-from transformers import CLIPModel, CLIPProcessor
+from transformers import CLIPModel, CLIPFeatureExtractor, BertTokenizer
 from PIL import Image
 import torch
 
-# Load model and processor
+# Load model and appropriate processors separately
 model_name = "jinaai/jina-clip-v1"
 model = CLIPModel.from_pretrained(model_name)
-processor = CLIPProcessor.from_pretrained(model_name)
+feature_extractor = CLIPFeatureExtractor.from_pretrained(model_name)
+tokenizer = BertTokenizer.from_pretrained(model_name)
 
 def compute_similarity(image, text):
-    image = Image.fromarray(image)  # Convert NumPy array to PIL image
+    image = Image.fromarray(image)  # Convert NumPy array to PIL Image
+    
+    # Process image
+    image_inputs = feature_extractor(images=image, return_tensors="pt")
 
-    # Process inputs
-    inputs = processor(text=[text], images=image, return_tensors="pt", padding=True, truncation=True)
+    # Process text
+    text_inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
 
     with torch.no_grad():
-        outputs = model(**inputs)
+        outputs = model(**image_inputs, **text_inputs)
         logits_per_image = outputs.logits_per_image  # Image-to-text similarity
         similarity_score = logits_per_image.item()
     
@@ -26,7 +30,7 @@ demo = gr.Interface(
     fn=compute_similarity,
     inputs=[gr.Image(type="numpy"), gr.Textbox(label="Enter text")],
     outputs=gr.Number(label="Similarity Score"),
-    title="CLIP Image-Text Similarity",
+    title="JinaAI CLIP Image-Text Similarity",
     description="Upload an image and enter a text prompt to get the similarity score."
 )