Update app.py

app.py

@@ -10,7 +10,6 @@ from transformers import CLIPProcessor, CLIPModel
 from PIL import Image
 import torch
 import numpy as np
-from typing import Tuple
 import spaces
 
 # Load model/processor
@@ -19,7 +18,7 @@ processor: CLIPProcessor = CLIPProcessor.from_pretrained("openai/clip-vit-large-
 model.eval()
 
 @spaces.GPU
-def get_embedding(image: Image.Image) -> Tuple[str, str]:
+def get_embedding(image: Image.Image) -> str:
     """
     Generate CLIP embedding for an image.
     
@@ -27,7 +26,7 @@ def get_embedding(image: Image.Image) -> Tuple[str, str]:
         image (Image.Image): PIL Image object to process
     
     Returns:
-        Tuple[str, str]: A tuple containing (embedding_info, embedding_values)
+        str: The full embedding array as a string
     """
     device: str = "cuda" if torch.cuda.is_available() else "cpu"
     
@@ -41,36 +40,19 @@ def get_embedding(image: Image.Image) -> Tuple[str, str]:
     # L2 normalize the embeddings
     emb = emb / emb.norm(p=2, dim=-1, keepdim=True)
     
-    # Convert to numpy for easier handling
+    # Convert to numpy and return as string
     emb_numpy = emb.cpu().numpy().squeeze()
     
-    # Create formatted output
-    embedding_info = f"Embedding Shape: {emb_numpy.shape}\nDevice Used: {device}\nNormalized: Yes (L2)"
-    
-    # Format embedding values (show first 10 and last 10 values for readability)
-    if len(emb_numpy) > 20:
-        embedding_preview = (
-            f"First 10 values: {emb_numpy[:10].tolist()}\n"
-            f"...\n"
-            f"Last 10 values: {emb_numpy[-10:].tolist()}\n\n"
-            f"Full embedding array:\n{emb_numpy.tolist()}"
-        )
-    else:
-        embedding_preview = f"Full embedding array:\n{emb_numpy.tolist()}"
-    
-    return embedding_info, embedding_preview
+    return str(emb_numpy.tolist())
 
 # Create Gradio interface
 demo: gr.Interface = gr.Interface(
     fn=get_embedding,
     inputs=gr.Image(type="pil", label="Upload Image"),
-    outputs=[
-        gr.Textbox(label="Embedding Info", lines=3),
-        gr.Textbox(label="Embedding Values", lines=20, max_lines=30)
-    ],
+    outputs=gr.Textbox(label="Embedding", lines=20, max_lines=30),
     allow_flagging="never",
     title="CLIP Image Embedding Generator",
-    description="Upload an image to generate its CLIP embedding vector. The embedding is L2-normalized and ready for similarity computations.",
+    description="Upload an image to generate its CLIP embedding vector.",
     theme=gr.themes.Soft()
 )