Update app.py

app.py

@@ -46,7 +46,14 @@ embedding_model = SentenceTransformer("mixedbread-ai/mxbai-embed-large-v1")
 
 #doc_func = lambda x: x.text
 #dataset = list(map(doc_func, dataset))
-embeddings = embedding_model.encode(dataset)
+
+def embedder(dataset[i]):
+    return embedding_model.encode(dataset[i])
+    
+dataset = dataset.map(embedder, batched=True)
+print(dataset[1])
+print(dataset[2])
+#embeddings = embedding_model.encode(dataset)
 
 #embeddings = embedding_model.embed_documents(docs)
 dataset = dataset.add_column('embeddings', embeddings)