Repository navigation
Expand file tree
/
Copy pathsql_storage.py
More file actions
285 lines (245 loc) · 8.65 KB
/
Copy pathsql_storage.py
File metadata and controls
285 lines (245 loc) · 8.65 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
# -*- coding: utf-8 -*-
import uuid
import pymysql
import json
import numpy as np
from typing import List
from modelcache.manager.scalar_data.base import CacheStorage, CacheData
from DBUtils.PooledDB import PooledDB
class SQLStorage(CacheStorage):
def __init__(
self,
db_type: str = "mysql",
config=None
):
self.host = config.get('mysql', 'host')
self.port = int(config.get('mysql', 'port'))
self.username = config.get('mysql', 'username')
self.password = config.get('mysql', 'password')
self.database = config.get('mysql', 'database')
self.pool = PooledDB(
creator=pymysql,
host=self.host,
user=self.username,
password=self.password,
port=self.port,
database=self.database
)
def create(self):
pass
def _insert(self, data: List):
answer = data[0]
question = data[1]
embedding_data = data[2]
model = data[3]
answer_type = 0
embedding_data = embedding_data.tobytes()
is_deleted = 0
_id = str(uuid.uuid4())
table_name = "modelcache_llm_answer"
insert_sql = f"""
INSERT INTO {table_name}
(id, question, answer, answer_type, model, embedding_data, is_deleted)
VALUES (%s, %s, %s, %s, %s, _binary%s, %s)
"""
conn = self.pool.connection()
try:
with conn.cursor() as cursor:
# 执行插入数据操作
values = (_id, question, answer, answer_type, model, embedding_data, is_deleted)
cursor.execute(insert_sql, values)
conn.commit()
finally:
# 关闭连接,将连接返回给连接池
conn.close()
return _id
def batch_insert(self, all_data: List[List]):
table_name = "modelcache_llm_answer"
insert_sql = f"""
INSERT INTO {table_name}
(id, question, answer, answer_type, model, embedding_data, is_deleted)
VALUES (%s, %s, %s, %s, %s, %s, %s)
"""
values_list = []
ids = []
for data in all_data:
answer = data[0]
question = data[1]
embedding_data = data[2].tobytes()
model = data[3]
answer_type = 0
is_deleted = 0
_id = str(uuid.uuid4())
ids.append(_id)
values_list.append((
_id, question, answer, answer_type, model, embedding_data, is_deleted
))
conn = self.pool.connection()
try:
with conn.cursor() as cursor:
cursor.executemany(insert_sql, values_list)
conn.commit()
finally:
conn.close()
return ids
def insert_query_resp(self, query_resp, **kwargs):
error_code = query_resp.get('errorCode')
error_desc = query_resp.get('errorDesc')
cache_hit = query_resp.get('cacheHit')
model = kwargs.get('model')
query = kwargs.get('query')
delta_time = kwargs.get('delta_time')
hit_query = query_resp.get('hit_query')
answer = query_resp.get('answer')
if isinstance(hit_query, list):
hit_query = json.dumps(hit_query, ensure_ascii=False)
table_name = "modelcache_query_log"
insert_sql = f"""
INSERT INTO {table_name}
(error_code, error_desc, cache_hit, model, query, delta_time, hit_query, answer)
VALUES (%s, %s, %s, %s, %s, %s, %s, %s)
"""
conn = self.pool.connection()
try:
with conn.cursor() as cursor:
# 执行插入数据操作
values = (error_code, error_desc, cache_hit, model, query, delta_time, hit_query, answer)
cursor.execute(insert_sql, values)
conn.commit()
finally:
# 关闭连接,将连接返回给连接池
conn.close()
def get_data_by_id(self, key: int):
table_name = "modelcache_llm_answer"
query_sql = f"""
SELECT answer, question, embedding_data, model
FROM {table_name}
WHERE id = %s
"""
conn = self.pool.connection()
try:
with conn.cursor() as cursor:
# 执行数据库操作
cursor.execute(query_sql, (key,))
resp = cursor.fetchone()
finally:
# 关闭连接,将连接返回给连接池
conn.close()
if resp is not None and len(resp) == 4:
# parse the numpy array from bytes and return the data
return resp[0], resp[1], np.frombuffer(resp[2], dtype=np.float32), resp[3]
else:
return None
def update_hit_count_by_id(self, primary_id: int):
table_name = "modelcache_llm_answer"
update_sql = f"""
UPDATE {table_name}
SET hit_count = hit_count+1
WHERE id = %s
"""
conn = self.pool.connection()
# 使用连接执行更新数据操作
try:
with conn.cursor() as cursor:
# 执行更新数据操作
cursor.execute(update_sql,(primary_id,))
conn.commit()
finally:
# 关闭连接,将连接返回给连接池
conn.close()
def get_ids(self, deleted=True):
table_name = "modelcache_llm_answer"
state = 1 if deleted else 0
query_sql = f"""
SELECT id
FROM {table_name}
WHERE is_deleted = %s
"""
conn = self.pool.connection()
try:
with conn.cursor() as cursor:
cursor.execute(query_sql, (state,))
ids = [row[0] for row in cursor.fetchall()]
finally:
conn.close()
return ids
def mark_deleted(self, keys):
table_name = "modelcache_llm_answer"
placeholders = ",".join(["%s"] * len(keys))
mark_sql = f"""
UPDATE {table_name}
SET is_deleted=1
WHERE id in ({placeholders})
"""
conn = self.pool.connection()
try:
with conn.cursor() as cursor:
cursor.execute(mark_sql, keys)
delete_count = cursor.rowcount
conn.commit()
finally:
conn.close()
return delete_count
def model_deleted(self, model_name):
table_name = "modelcache_llm_answer"
delete_sql = f"""
Delete from {table_name}
WHERE model = %s
"""
table_log_name = "modelcache_query_log"
delete_log_sql = f"""
Delete from {table_log_name}
WHERE model = %s
"""
conn = self.pool.connection()
# 使用连接执行删除数据操作
try:
with conn.cursor() as cursor:
# 执行删除数据操作
resp = cursor.execute(delete_sql, (model_name,))
conn.commit()
# 执行删除该模型对应日志操作 resp_log行数不返回
resp_log = cursor.execute(delete_log_sql, (model_name,))
conn.commit() # 分别提交事务
finally:
# 关闭连接,将连接返回给连接池
conn.close()
return resp
def clear_deleted_data(self):
table_name = "modelcache_llm_answer"
delete_sql = f"""
DELETE FROM {table_name}
WHERE is_deleted = 1
"""
conn = self.pool.connection()
try:
with conn.cursor() as cursor:
cursor.execute(delete_sql)
delete_count = cursor.rowcount
conn.commit()
finally:
conn.close()
return delete_count
def count(self, state: int = 0, is_all: bool = False):
table_name = "modelcache_llm_answer"
# we're not using prepared statements here, so we need to ensure state is an integer
if not isinstance(state, int):
raise ValueError("'state' must be an integer.")
if is_all:
count_sql = f"SELECT COUNT(*) FROM {table_name}"
else:
count_sql = f"SELECT COUNT(*) FROM {table_name} WHERE is_deleted = {state}"
conn = self.pool.connection()
try:
with conn.cursor() as cursor:
cursor.execute(count_sql)
num = cursor.fetchone()[0]
finally:
conn.close()
return num
def close(self):
pass
def count_answers(self):
pass
def flush(self):
pass