Update app.py

app.py

@@ -11,18 +11,35 @@ from typing import Dict, List, Any, Optional
 from transformers.pipelines import pipeline
 
 # Initialize the model
-model = pipeline("image-feature-extraction", model="nomic-ai/nomic-embed-vision-v1.5", trust_remote_code=True)
+try:
+    model = pipeline("image-feature-extraction", model="nomic-ai/nomic-embed-vision-v1.5", trust_remote_code=True)
+    model_loaded = True
+except Exception as e:
+    print(f"Error loading model: {str(e)}")
+    model = None
+    model_loaded = False
 
 # Function to generate embeddings from an image
 def generate_embedding(image):
     if image is None:
-        return None, "No image provided"
+        return {"error": "No image provided"}, "No image provided"
+    
+    if not model_loaded:
+        return {"error": "Model not loaded properly"}, "Error: Model not loaded properly"
     
     # Convert to PIL Image if needed
     if not isinstance(image, Image.Image):
-        image = Image.fromarray(image)
+        try:
+            image = Image.fromarray(image)
+        except Exception as e:
+            print(f"Error converting image: {str(e)}")
+            return {"error": f"Invalid image format: {str(e)}"}, f"Error: Invalid image format"
     
     try:
+        # Check if model is loaded before calling it
+        if model is None:
+            return {"error": "Model not loaded properly"}, "Error: Model not loaded properly"
+            
         # Generate embedding using the transformers pipeline
         result = model(image)
         
@@ -47,14 +64,14 @@ def generate_embedding(image):
                     embedding_list = list(result)
                 else:
                     print("Result is None")
-                    return None, "Failed to generate embedding"
+                    return {"error": "Failed to generate embedding"}, "Failed to generate embedding"
             except:
                 print(f"Couldn't convert result of type {type(result)} to list")
-                return None, "Failed to process embedding"
+                return {"error": "Failed to process embedding"}, "Failed to process embedding"
         
         # Ensure we have a valid embedding list
         if embedding_list is None:
-            return None, "Failed to generate embedding"
+            return {"error": "Failed to generate embedding"}, "Failed to generate embedding"
             
         # Calculate embedding dimension
         embedding_dim = len(embedding_list)
@@ -65,7 +82,7 @@ def generate_embedding(image):
         }, f"Dimension: {embedding_dim}"
     except Exception as e:
         print(f"Error generating embedding: {str(e)}")
-        return None, f"Error: {str(e)}"
+        return {"error": f"Error generating embedding: {str(e)}"}, f"Error: {str(e)}"
 
 # Function to generate embeddings from an image URL
 def embed_image_from_url(image_url):
@@ -101,7 +118,10 @@ app = gr.Interface(
     ],
     title="Nomic Vision Embedding Model (nomic-ai/nomic-embed-vision-v1.5)",
     description="Upload an image to generate embeddings using the Nomic Vision model.",
-    examples=[["examples/example1.jpg"], ["examples/example2.jpg"]],
+    examples=[
+        ["nomic/examples/example1.jpg"],
+        ["nomic/examples/example2.jpg"]
+    ],
     allow_flagging="never"
 )