a73a751f
 tangwang
enrich
|
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
|
from __future__ import annotations
import importlib.util
import io
import json
import logging
import sys
import types
from pathlib import Path
from unittest import mock
def _load_product_enrich_module():
if "dotenv" not in sys.modules:
fake_dotenv = types.ModuleType("dotenv")
fake_dotenv.load_dotenv = lambda *args, **kwargs: None
sys.modules["dotenv"] = fake_dotenv
if "redis" not in sys.modules:
fake_redis = types.ModuleType("redis")
class _FakeRedisClient:
def __init__(self, *args, **kwargs):
pass
def ping(self):
return True
fake_redis.Redis = _FakeRedisClient
sys.modules["redis"] = fake_redis
repo_root = Path(__file__).resolve().parents[1]
if str(repo_root) not in sys.path:
sys.path.insert(0, str(repo_root))
module_path = repo_root / "indexer" / "product_enrich.py"
spec = importlib.util.spec_from_file_location("product_enrich_under_test", module_path)
module = importlib.util.module_from_spec(spec)
assert spec and spec.loader
spec.loader.exec_module(module)
return module
product_enrich = _load_product_enrich_module()
def _attach_stream(logger_obj: logging.Logger):
stream = io.StringIO()
handler = logging.StreamHandler(stream)
handler.setFormatter(logging.Formatter("%(message)s"))
logger_obj.addHandler(handler)
return stream, handler
def test_create_prompt_splits_shared_context_and_localized_tail():
products = [
{"id": "1", "title": "dress"},
{"id": "2", "title": "linen shirt"},
]
shared_zh, user_zh, prefix_zh = product_enrich.create_prompt(products, target_lang="zh")
shared_en, user_en, prefix_en = product_enrich.create_prompt(products, target_lang="en")
assert shared_zh == shared_en
assert "Analyze each input product title" in shared_zh
assert "1. dress" in shared_zh
assert "2. linen shirt" in shared_zh
assert "Product list" not in user_zh
assert "Product list" not in user_en
assert "specified language" in user_zh
assert "Language: Chinese" in user_zh
assert "Language: English" in user_en
assert prefix_zh.startswith("| 序号 | 商品标题 | 品类路径 |")
assert prefix_en.startswith("| No. | Product title | Category path |")
def test_call_llm_logs_shared_context_once_and_verbose_contains_full_requests():
payloads = []
response_bodies = [
{
"choices": [
{
"message": {
"content": (
"| 1 | 连衣裙 | 女装>连衣裙 | 法式,收腰 | 年轻女性 | "
"通勤,约会 | 春季,夏季 | 中长款 | 聚酯纤维 | 透气 | "
"修身显瘦 | 法式收腰连衣裙 |\n"
)
}
}
],
"usage": {"prompt_tokens": 120, "completion_tokens": 45, "total_tokens": 165},
},
{
"choices": [
{
"message": {
"content": (
"| 1 | Dress | Women>Dress | French,Waisted | Young women | "
"Commute,Date | Spring,Summer | Midi | Polyester | Breathable | "
"Slim fit | French waisted dress |\n"
)
}
}
],
"usage": {"prompt_tokens": 118, "completion_tokens": 43, "total_tokens": 161},
},
]
class _FakeResponse:
def __init__(self, body):
self.body = body
def raise_for_status(self):
return None
def json(self):
return self.body
class _FakeSession:
trust_env = True
def post(self, url, headers=None, json=None, timeout=None, proxies=None):
del url, headers, timeout, proxies
payloads.append(json)
return _FakeResponse(response_bodies[len(payloads) - 1])
def close(self):
return None
product_enrich.reset_logged_shared_context_keys()
main_stream, main_handler = _attach_stream(product_enrich.logger)
verbose_stream, verbose_handler = _attach_stream(product_enrich.verbose_logger)
try:
with mock.patch.object(product_enrich, "API_KEY", "fake-key"), mock.patch.object(
product_enrich.requests,
"Session",
lambda: _FakeSession(),
):
zh_shared, zh_user, zh_prefix = product_enrich.create_prompt(
[{"id": "1", "title": "dress"}],
target_lang="zh",
)
en_shared, en_user, en_prefix = product_enrich.create_prompt(
[{"id": "1", "title": "dress"}],
target_lang="en",
)
zh_markdown, zh_raw = product_enrich.call_llm(
zh_shared,
zh_user,
zh_prefix,
target_lang="zh",
)
en_markdown, en_raw = product_enrich.call_llm(
en_shared,
en_user,
en_prefix,
target_lang="en",
)
finally:
product_enrich.logger.removeHandler(main_handler)
product_enrich.verbose_logger.removeHandler(verbose_handler)
assert zh_shared == en_shared
assert len(payloads) == 2
assert len(payloads[0]["messages"]) == 3
assert payloads[0]["messages"][1]["role"] == "user"
assert "1. dress" in payloads[0]["messages"][1]["content"]
assert "Language: Chinese" in payloads[0]["messages"][1]["content"]
assert "Language: English" in payloads[1]["messages"][1]["content"]
assert payloads[0]["messages"][-1]["partial"] is True
assert payloads[1]["messages"][-1]["partial"] is True
main_log = main_stream.getvalue()
verbose_log = verbose_stream.getvalue()
assert main_log.count("LLM Shared Context") == 1
assert main_log.count("LLM Request Variant") == 2
assert "Localized Requirement" in main_log
assert "Shared Context" in main_log
assert verbose_log.count("LLM Request [model=") == 2
assert verbose_log.count("LLM Response [model=") == 2
assert '"partial": true' in verbose_log
assert "Combined User Prompt" in verbose_log
assert "French waisted dress" in verbose_log
assert "法式收腰连衣裙" in verbose_log
assert zh_markdown.startswith(zh_prefix)
assert en_markdown.startswith(en_prefix)
assert json.loads(zh_raw)["usage"]["total_tokens"] == 165
assert json.loads(en_raw)["usage"]["total_tokens"] == 161
def test_process_batch_reads_result_and_validates_expected_fields():
|
|
a73a751f
tangwang
enrich
|
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
|
"""
with mock.patch.object(
product_enrich,
"call_llm",
return_value=(merged_markdown, json.dumps({"choices": [{"message": {"content": "stub"}}]})),
):
results = product_enrich.process_batch(
[{"id": "sku-1", "title": "dress"}],
batch_num=1,
target_lang="zh",
)
assert len(results) == 1
row = results[0]
assert row["id"] == "sku-1"
assert row["lang"] == "zh"
assert row["title_input"] == "dress"
assert row["title"] == "法式连衣裙"
assert row["category_path"] == "女装>连衣裙"
assert row["tags"] == "法式,收腰"
assert row["target_audience"] == "年轻女性"
assert row["usage_scene"] == "通勤,约会"
assert row["season"] == "春季,夏季"
assert row["key_attributes"] == "中长款"
assert row["material"] == "聚酯纤维"
assert row["features"] == "透气"
|
|
76e1f088
tangwang
1. 减少一列sell point...
|
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
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
|
def test_analyze_products_uses_product_level_cache_across_batch_requests():
cache_store = {}
process_calls = []
def fake_get_cached_anchor_result(title, target_lang, tenant_id=None):
return cache_store.get((tenant_id, target_lang, title))
def fake_set_cached_anchor_result(title, target_lang, result, tenant_id=None):
cache_store[(tenant_id, target_lang, title)] = result
def fake_process_batch(batch_data, batch_num, target_lang="zh"):
process_calls.append(
{
"batch_num": batch_num,
"target_lang": target_lang,
"titles": [item["title"] for item in batch_data],
}
)
return [
{
"id": item["id"],
"lang": target_lang,
"title_input": item["title"],
"title": f"normalized:{item['title']}",
"category_path": "cat",
"tags": "tags",
"target_audience": "audience",
"usage_scene": "scene",
"season": "season",
"key_attributes": "attrs",
"material": "material",
"features": "features",
"anchor_text": f"anchor:{item['title']}",
}
for item in batch_data
]
products = [
{"id": "1", "title": "dress"},
{"id": "2", "title": "shirt"},
]
with mock.patch.object(product_enrich, "API_KEY", "fake-key"), mock.patch.object(
product_enrich,
"_get_cached_anchor_result",
side_effect=fake_get_cached_anchor_result,
), mock.patch.object(
product_enrich,
"_set_cached_anchor_result",
side_effect=fake_set_cached_anchor_result,
), mock.patch.object(
product_enrich,
"process_batch",
side_effect=fake_process_batch,
):
first = product_enrich.analyze_products(
[products[0]],
target_lang="zh",
tenant_id="170",
)
second = product_enrich.analyze_products(
products,
target_lang="zh",
tenant_id="170",
)
third = product_enrich.analyze_products(
products,
target_lang="zh",
tenant_id="170",
)
assert [row["title_input"] for row in first] == ["dress"]
assert [row["title_input"] for row in second] == ["dress", "shirt"]
assert [row["title_input"] for row in third] == ["dress", "shirt"]
assert process_calls == [
{"batch_num": 1, "target_lang": "zh", "titles": ["dress"]},
{"batch_num": 1, "target_lang": "zh", "titles": ["shirt"]},
]
assert second[0]["anchor_text"] == "anchor:dress"
assert second[1]["anchor_text"] == "anchor:shirt"
assert third[0]["anchor_text"] == "anchor:dress"
assert third[1]["anchor_text"] == "anchor:shirt"
|