Update app.py

app.py

@@ -36,8 +36,15 @@ def extract_embeddings(batch):
 embeddings_dataset = tokenized_datasets.map(extract_embeddings, batched=True, batch_size=batch_size)
 
 # Access the embeddings
-embeddings = np.vstack(embeddings_dataset["embeddings"])
+# Debugging code to print dataset keys
+st.write("Dataset Keys:", embeddings_dataset.column_names)
 
+# Access the embeddings
+if "embeddings" in embeddings_dataset.column_names:
+    embeddings = np.vstack(embeddings_dataset["embeddings"])
+else:
+    st.error("The 'embeddings' key is not present in the dataset.")
+    
 # Perform unsupervised clustering (K-Means)
 num_clusters = 5  # You can adjust this based on your data
 kmeans = KMeans(n_clusters=num_clusters)