'commit'

dsRag/Milvus/X1_create_collection.py

@@ -27,13 +27,12 @@ if utility.has_collection(collection_name):
 # 5. 定义集合的字段和模式
 fields = [
     FieldSchema(name="id", dtype=DataType.INT64, is_primary=True, auto_id=True),  # 主键字段，自动生成 ID
-    FieldSchema(name="person_id", dtype=DataType.VARCHAR, max_length=64),  # 会话 ID
+    FieldSchema(name="document_id", dtype=DataType.VARCHAR, max_length=64),  # 文档 ID
     FieldSchema(name="user_input", dtype=DataType.VARCHAR, max_length=65535),  # 用户问题
-    FieldSchema(name="model_response", dtype=DataType.VARCHAR, max_length=65535),  # 大模型反馈结果
     FieldSchema(name="timestamp", dtype=DataType.VARCHAR, max_length=32),  # 时间
     FieldSchema(name="embedding", dtype=DataType.FLOAT_VECTOR, dim=MS_DIMENSION)  # 向量字段，维度为 200
 ]
-schema_description = "Chat records collection with person_id , user input, model response, and timestamp"
+schema_description = "Chat records collection with document_id , user_input, and timestamp"
 
 # 6. 创建集合
 print(f"正在创建集合 '{collection_name}'...")

dsRag/Milvus/X4_InsertMathData.py

@@ -46,16 +46,15 @@ for filename in os.listdir(txt_dir):
 
             # 5. 获取当前时间和会话ID
             timestamp = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
-            person_id = "MATH_DATA_" + str(hash(filename))
+            document_id = "MATH_DATA_1" # 史校长的这本书定义为 MATH_DATA_1
 
             # 6. 将文本转换为嵌入向量
             embedding = text_to_embedding(content)
 
             # 7. 插入数据
             entities = [
-                [person_id],  # person_id
+                [document_id],  # document_id
                 [content],  # user_input
-                [""],  # model_response (留空)
                 [timestamp],  # timestamp
                 [embedding]  # embedding
             ]