Upload app.py

app.py

@@ -54,7 +54,15 @@ sources = [
     "TaxQADataSet_ntpc1.txt",
     "TaxQADataSet_ntpc2.txt",
     "TaxQADataSet_kctax.txt",
-    "TaxQADataSet_chutax.txt"
+    "TaxQADataSet_chutax.txt",
+    "HouseTaxAct1130103.txt",
+    "VehicleLicenseTaxAct1101230.txt",
+    "TaxCollectionAct1101217.txt",
+    "LandTaxAct1100623.txt",
+    "AmusementTaxAct960523.txt",
+    "StampTaxAct910515.txt",
+    "DeedTaxAct990505.txt",
+    "ProgressiveHouseTaxRates1130701.txt"
 ]
 
 documents = load_documents(sources)
@@ -70,7 +78,7 @@ text_splitter = RecursiveCharacterTextSplitter(
 split_docs = text_splitter.split_documents(documents)
 print(f"分割後的文件數量：{len(split_docs)}")
 
-embeddings = HuggingFaceEmbeddings(model_name="BAAI/bge-m3")
+embeddings = HuggingFaceEmbeddings(model_name="BAAI/bge-large-zh-v1.5")
 print(f"\n成功初始化嵌入模型")
 
 print(f"開始建立向量資料庫")