cd4ce66d
 tangwang
trans logs
|
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
|
self.available = True
self.storage = {}
self.get_calls = []
self.set_calls = []
def get(self, *, model, target_lang, source_text):
self.get_calls.append((model, target_lang, source_text))
return self.storage.get((model, target_lang, source_text))
def set(self, *, model, target_lang, source_text, translated_text):
self.set_calls.append((model, target_lang, source_text, translated_text))
self.storage[(model, target_lang, source_text)] = translated_text
def test_translation_cache_key_format(monkeypatch):
monkeypatch.setattr(TranslationCache, "_init_redis_client", staticmethod(lambda: None))
cache = TranslationCache({"ttl_seconds": 60, "sliding_expiration": True})
key = cache.build_key(model="llm", target_lang="en", source_text="商品标题")
assert key.startswith("trans:llm:en:商品标题")
assert len(key) == len("trans:llm:en:商品标题") + 64
def test_service_caches_all_capabilities(monkeypatch):
monkeypatch.setattr(TranslationCache, "_init_redis_client", staticmethod(lambda: None))
created = {}
def _fake_create_backend(self, *, name, backend_type, cfg):
del self, backend_type, cfg
class _Backend:
model = name
@property
def supports_batch(self):
return True
def translate(self, text, target_lang, source_lang=None, scene=None):
del target_lang, source_lang, scene
if isinstance(text, list):
return [f"{name}:{item}" for item in text]
return f"{name}:{text}"
backend = _Backend()
created[name] = backend
return backend
monkeypatch.setattr(TranslationService, "_create_backend", _fake_create_backend)
config = {
"service_url": "http://127.0.0.1:6006",
"timeout_sec": 10.0,
"default_model": "llm",
"default_scene": "general",
"capabilities": {
"llm": {
"enabled": True,
"backend": "llm",
"model": "dummy-llm",
"base_url": "https://example.com",
"timeout_sec": 10.0,
"use_cache": True,
},
"opus-mt-zh-en": {
"enabled": True,
"backend": "local_marian",
"model_id": "dummy",
"model_dir": "dummy",
"device": "cpu",
"torch_dtype": "float32",
"batch_size": 8,
"max_input_length": 16,
"max_new_tokens": 16,
"num_beams": 1,
"use_cache": True,
},
},
"cache": {
"ttl_seconds": 60,
"sliding_expiration": True,
},
}
service = TranslationService(config)
fake_cache = _FakeCache()
service._translation_cache = fake_cache
first = service.translate("商品标题", target_lang="en", source_lang="zh", model="llm")
second = service.translate("商品标题", target_lang="en", source_lang="zh", model="llm")
batch = service.translate(["连衣裙", "衬衫"], target_lang="en", source_lang="zh", model="opus-mt-zh-en")
assert first == "llm:商品标题"
assert second == "llm:商品标题"
assert batch == ["opus-mt-zh-en:连衣裙", "opus-mt-zh-en:衬衫"]
assert fake_cache.get_calls == [
("llm", "en", "商品标题"),
("llm", "en", "商品标题"),
("opus-mt-zh-en", "en", "连衣裙"),
("opus-mt-zh-en", "en", "衬衫"),
]
assert fake_cache.set_calls == [
("llm", "en", "商品标题", "llm:商品标题"),
("opus-mt-zh-en", "en", "连衣裙", "opus-mt-zh-en:连衣裙"),
("opus-mt-zh-en", "en", "衬衫", "opus-mt-zh-en:衬衫"),
]
|
|
14e67b71
tangwang
分句后的 batching 现在是...
|
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
|
def test_translation_request_filter_injects_reqid():
reqid, token = bind_translation_request_id("req-test-1234567890")
try:
record = logging.LogRecord(
name="translation.service",
level=logging.INFO,
pathname=__file__,
lineno=1,
msg="hello",
args=(),
exc_info=None,
)
TranslationRequestFilter().filter(record)
assert reqid == "req-test-1234567890"
assert record.reqid == "req-test-1234567890"
finally:
reset_translation_request_id(token)
def test_translation_route_log_focuses_on_routing_decision(monkeypatch, caplog):
monkeypatch.setattr(TranslationCache, "_init_redis_client", staticmethod(lambda: None))
def _fake_create_backend(self, *, name, backend_type, cfg):
del self, backend_type, cfg
class _Backend:
model = name
@property
def supports_batch(self):
return True
def translate(self, text, target_lang, source_lang=None, scene=None):
del target_lang, source_lang, scene
return text
return _Backend()
monkeypatch.setattr(TranslationService, "_create_backend", _fake_create_backend)
service = TranslationService(
{
"service_url": "http://127.0.0.1:6006",
"timeout_sec": 10.0,
"default_model": "llm",
"default_scene": "general",
"capabilities": {
"llm": {
"enabled": True,
"backend": "llm",
"model": "dummy-llm",
"base_url": "https://example.com",
"timeout_sec": 10.0,
"use_cache": True,
}
},
"cache": {
"ttl_seconds": 60,
"sliding_expiration": True,
},
}
)
with caplog.at_level(logging.INFO):
service.translate("商品标题", target_lang="en", source_lang="zh", model="llm")
route_messages = [
record.getMessage()
for record in caplog.records
if record.name == "translation.service" and record.getMessage().startswith("Translation route |")
]
assert route_messages == [
"Translation route | backend=llm request_type=single use_cache=True cache_available=False"
]
|