Update app.py

app.py

@@ -16,7 +16,7 @@ from sklearn.metrics.pairwise import cosine_similarity
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-model = BGEM3FlagModel('BAAI/bge-m3',  
+embedding_model = BGEM3FlagModel('BAAI/bge-m3',  
                        use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
 
 embeddings = np.load("embeddings_tchap.npy")
@@ -40,7 +40,7 @@ system_prompt = "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n
 #Vector search over the database
 def vector_search(sentence_query):
 
-    query_embedding = model.encode(sentence_query, 
+    query_embedding = embedding_model.encode(sentence_query, 
                             batch_size=12, 
                             max_length=256, # If you don't need such a long length, you can set a smaller value to speed up the encoding process.
                             )['dense_vecs']