Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from transformers import AutoModel, AutoTokenizer
-import torch
+import numpy as np
 
 # Load a small CPU model for text to vector processing
 model_name = "sentence-transformers/all-mpnet-base-v2"
@@ -8,42 +8,18 @@ model = AutoModel.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 def text_to_vector(texts):
-    results = []
-
-    # Process each sentence individually to catch errors
-    for sentence in texts:
-        try:
-            # Tokenize the sentence
-            inputs = tokenizer(sentence, return_tensors="pt", padding=True, truncation=True)
-
-            # Check if tokenization results in valid tokens
-            if inputs['input_ids'].shape[1] == 0:
-                raise ValueError(f"Tokenization failed for sentence: '{sentence}'")
-
-            # Pass through the model
-            with torch.no_grad():
-                outputs = model(**inputs)
-
-            # Get the vector from pooler_output or handle errors
-            if outputs.pooler_output is None:
-                raise ValueError(f"No vector generated for sentence: '{sentence}'")
-            
-            # Convert the vector to a list of floats
-            vector = outputs.pooler_output.squeeze().numpy().tolist()
-
-            # Append result as sentence and vector pair
-            results.append({
-                "sentence": sentence,
-                "vector": vector
-            })
-        except Exception as e:
-            # Handle any errors for individual sentences
-            results.append({
-                "sentence": sentence,
-                "vector": f"Error: {str(e)}"
-            })
+    # Tokenize the input array of sentences
+    inputs = tokenizer(texts, return_tensors="pt", padding=True, truncation=True)
+    outputs = model(**inputs)
+    vectors = outputs.pooler_output.detach().numpy()
+    
+    # Convert each vector to a string representation and create an object
+    result = [
+        {"sentence": sentence, "vector": ", ".join(map(str, vector))}
+        for sentence, vector in zip(texts, vectors)
+    ]
     
-    return results
+    return result
 
 demo = gr.Interface(
     fn=text_to_vector,