diff --git a/AI/WxMini/Milvus/T2_create_index.py b/AI/WxMini/Milvus/T2_create_index.py
new file mode 100644
index 00000000..57417ec9
--- /dev/null
+++ b/AI/WxMini/Milvus/T2_create_index.py
@@ -0,0 +1,29 @@
+# create_index.py
+from WxMini.Milvus.Utils.MilvusCollectionManager import MilvusCollectionManager
+from WxMini.Milvus.Utils.MilvusConnectionPool import *
+from WxMini.Milvus.Config.MulvusConfig import *
+
+# 1. 使用连接池管理 Milvus 连接
+milvus_pool = MilvusConnectionPool(host=MS_HOST, port=MS_PORT, max_connections=MS_MAX_CONNECTIONS)
+
+# 2. 从连接池中获取一个连接
+connection = milvus_pool.get_connection()
+
+# 3. 初始化集合管理器
+collection_name = MS_COLLECTION_NAME
+collection_manager = MilvusCollectionManager(collection_name)
+
+# 4. 创建索引
+index_params = {
+    "index_type": "IVF_FLAT",  # 使用 IVF_FLAT 索引类型
+    "metric_type": "L2",       # 使用 L2 距离度量方式
+    "params": {"nlist": 128}   # 设置 IVF_FLAT 的 nlist 参数
+}
+collection_manager.create_index("embedding", index_params)
+print("索引创建成功。")
+
+# 5. 释放连接
+milvus_pool.release_connection(connection)
+
+# 6. 关闭连接池
+milvus_pool.close()
\ No newline at end of file
diff --git a/AI/WxMini/Milvus/T2_insert_data.py b/AI/WxMini/Milvus/T3_insert_data.py
similarity index 72%
rename from AI/WxMini/Milvus/T2_insert_data.py
rename to AI/WxMini/Milvus/T3_insert_data.py
index 2afea069..0ba3ed9c 100644
--- a/AI/WxMini/Milvus/T2_insert_data.py
+++ b/AI/WxMini/Milvus/T3_insert_data.py
@@ -1,11 +1,8 @@
-# insert_data.py
 import random
 
-from pymilvus import FieldSchema, DataType
-
+from WxMini.Milvus.Config.MulvusConfig import *
 from WxMini.Milvus.Utils.MilvusCollectionManager import MilvusCollectionManager
 from WxMini.Milvus.Utils.MilvusConnectionPool import *
-from WxMini.Milvus.Config.MulvusConfig import *
 
 # 1. 使用连接池管理 Milvus 连接
 milvus_pool = MilvusConnectionPool(host=MS_HOST, port=MS_PORT, max_connections=MS_MAX_CONNECTIONS)
@@ -25,19 +22,12 @@ data = [
 ]
 entities = [data]  # 插入的数据
 collection_manager.insert_data(entities)
+print("数据插入成功。")
 
-# 5. 创建索引
-index_params = {
-    "index_type": "IVF_FLAT",  # 使用 IVF_FLAT 索引类型
-    "metric_type": "L2",       # 使用 L2 距离度量方式
-    "params": {"nlist": 128}   # 设置 IVF_FLAT 的 nlist 参数
-}
-collection_manager.create_index("embedding", index_params)
-
-# 6. 加载集合到内存
+# 5. 加载集合到内存
 collection_manager.load_collection()
 
-# 7. 查询数据，验证插入是否成功
+# 6. 查询数据，验证插入是否成功
 query_vector = [random.random() for _ in range(128)]  # 随机生成一个查询向量
 search_params = {
     "metric_type": "L2",       # 使用 L2 距离度量方式
@@ -49,8 +39,8 @@ for hits in results:
     for hit in hits:
         print(f"ID: {hit.id}, Distance: {hit.distance}")
 
-# 8. 释放连接
+# 7. 释放连接
 milvus_pool.release_connection(connection)
 
-# 9. 关闭连接池
+# 8. 关闭连接池
 milvus_pool.close()
\ No newline at end of file
diff --git a/AI/WxMini/Milvus/T3_search_data.py b/AI/WxMini/Milvus/T4_search_data.py
similarity index 94%
rename from AI/WxMini/Milvus/T3_search_data.py
rename to AI/WxMini/Milvus/T4_search_data.py
index 08a10984..23fd744e 100644
--- a/AI/WxMini/Milvus/T3_search_data.py
+++ b/AI/WxMini/Milvus/T4_search_data.py
@@ -24,7 +24,7 @@ search_params = {
     "metric_type": "L2",       # 使用 L2 距离度量方式
     "params": {"nprobe": 10}   # 设置 IVF_FLAT 的 nprobe 参数
 }
-results = collection_manager.search(query_vector, search_params, limit=2)
+results = collection_manager.search(query_vector, search_params, limit=20)
 print("查询结果：")
 for hits in results:
     for hit in hits: