Update app.py

app.py

@@ -9,13 +9,17 @@ model = AutoModel.from_pretrained("jinaai/jina-clip-v1", trust_remote_code=True)
 # Function to compute similarity
 def compute_similarity(input1, input2, input1_type, input2_type):
     # Check if inputs are empty
-    if (input1_type == "Text" and not input1.strip()) or (input1_type == "Image" and input1 is None):
+    if input1_type == "Text" and not input1.strip():
         return "Error: Input 1 is empty!"
-    if (input2_type == "Text" and not input2.strip()) or (input2_type == "Image" and input2 is None):
+    if input2_type == "Text" and not input2.strip():
         return "Error: Input 2 is empty!"
-    
+    if input1_type == "Image" and input1 is None:
+        return "Error: Image 1 is missing!"
+    if input2_type == "Image" and input2 is None:
+        return "Error: Image 2 is missing!"
+
     inputs = []
-    
+
     # Process first input
     if input1_type == "Text":
         text1_embedding = model.encode_text([input1])
@@ -23,7 +27,7 @@ def compute_similarity(input1, input2, input1_type, input2_type):
     elif input1_type == "Image":
         image1_embedding = model.encode_image([Image.fromarray(input1)])
         inputs.append(image1_embedding)
-    
+
     # Process second input
     if input2_type == "Text":
         text2_embedding = model.encode_text([input2])
@@ -31,12 +35,21 @@ def compute_similarity(input1, input2, input1_type, input2_type):
     elif input2_type == "Image":
         image2_embedding = model.encode_image([Image.fromarray(input2)])
         inputs.append(image2_embedding)
-    
+
     # Compute cosine similarity
     similarity_score = (inputs[0] @ inputs[1].T).item()
-    
+
     return similarity_score
 
+# Function to update UI based on selected input types
+def update_visibility(input1_type, input2_type):
+    return (
+        gr.update(visible=input1_type == "Text", value="" if input1_type == "Text" else None),
+        gr.update(visible=input1_type == "Image", value=None if input1_type == "Image" else None),
+        gr.update(visible=input2_type == "Text", value="" if input2_type == "Text" else None),
+        gr.update(visible=input2_type == "Image", value=None if input2_type == "Image" else None),
+    )
+
 # Gradio UI
 with gr.Blocks() as demo:
     gr.Markdown("## Multimodal Similarity: Text-Text, Text-Image, Image-Image")
@@ -55,15 +68,6 @@ with gr.Blocks() as demo:
 
     output = gr.Textbox(label="Similarity Score / Error", interactive=False)
 
-    # Function to toggle visibility based on selected types
-    def update_visibility(input1_type, input2_type):
-        return (
-            input1_type == "Text",
-            input1_type == "Image",
-            input2_type == "Text",
-            input2_type == "Image"
-        )
-
     input1_type.change(update_visibility, inputs=[input1_type, input2_type], outputs=[input1, image1, input2, image2])
     input2_type.change(update_visibility, inputs=[input1_type, input2_type], outputs=[input1, image1, input2, image2])