Update app.py

app.py

@@ -239,24 +239,20 @@ def get_embedding_for_text(text, tokenizer, model):
     chunk_embeddings = []
     
     for chunk in chunks:
-        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()
+        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():
+            # Access the first element of the tuple which contains the hidden states
+            outputs = model(**inputs)[0]
+            embedding = outputs[:, 0, :].cpu().numpy()
             chunk_embeddings.append(embedding[0])
-        except Exception as e:
-            st.warning(f"Error processing chunk: {str(e)}")
-            continue
     
     if chunk_embeddings:
         weights = np.array([len(chunk.split()) for chunk in chunks])