Update app.py

app.py

@@ -10,7 +10,7 @@ import numpy as np
 model = SentenceTransformer("moka-ai/m3e-base")
 
 # Encode the documents into embeddings
-documents = ["Document 1", "Document 2", "Document 3"]
+documents = ["班车线路", "兴趣小组", "财务报销"]
 document_embeddings = model.encode(documents)
 
 # Store the embeddings to FAISS
@@ -18,7 +18,7 @@ index = faiss.IndexFlatIP(document_embeddings.shape[1])
 index.add(document_embeddings)
 
 # Encode the query into an embedding
-query = "2"
+query = "报销餐费"
 query_embedding = model.encode([query])[0]
 
 # Search the FAISS index for the most similar document