Update app.py

app.py

@@ -234,27 +234,30 @@ def classify_emotion(text, classifier):
     return final_emotion
         
 def get_embedding_for_text(text, tokenizer, model):
-    """Get embedding for complete text while preserving all content."""
-    # Split into optimal chunks of 512 tokens
-    chunks = split_text(text, max_length=512)
+    """Get embedding for complete text."""
+    chunks = split_text(text)
     chunk_embeddings = []
     
     for chunk in chunks:
-        inputs = tokenizer(
-            chunk,
-            return_tensors="pt",
-            padding=True,
-            max_length=512
-        )
-        inputs = {k: v.to(model.device) for k, v in inputs.items()}
-        
-        with torch.no_grad():
-            outputs = model(**inputs)[0]
-        
-        embedding = outputs[:, 0, :].cpu().numpy()
-        chunk_embeddings.append(embedding[0])
+        try:
+            inputs = tokenizer(
+                chunk,
+                return_tensors="pt",
+                padding=True,
+                truncation=True,
+                max_length=512
+            )
+            inputs = {k: v.to(model.device) for k, v in inputs.items()}
+            
+            with torch.no_grad():
+                outputs = model(**inputs)
+            
+            embedding = outputs.last_hidden_state[:, 0, :].cpu().numpy()
+            chunk_embeddings.append(embedding[0])
+        except Exception as e:
+            st.warning(f"Error processing chunk: {str(e)}")
+            continue
     
-    # Weight each chunk based on its content
     if chunk_embeddings:
         weights = np.array([len(chunk.split()) for chunk in chunks])
         weights = weights / weights.sum()