59b0a342
 tangwang
创建手写 mapping JSON
|
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
|
"""
Query configuration constants.
Since all tenants share the same ES mapping, we can hardcode field lists here.
"""
import os
from typing import Dict, List
# Default index name
DEFAULT_INDEX_NAME = "search_products"
# Text embedding field
TEXT_EMBEDDING_FIELD = "title_embedding"
# Image embedding field
IMAGE_EMBEDDING_FIELD = "image_embedding"
# Default match fields for text search (with boost)
DEFAULT_MATCH_FIELDS = [
"title_zh^3.0",
"brief_zh^1.5",
"description_zh^1.0",
"vendor_zh^1.5",
"tags^1.0",
"category_path_zh^1.5",
"category_name_zh^1.5"
]
# Domain-specific match fields
DOMAIN_FIELDS: Dict[str, List[str]] = {
"default": DEFAULT_MATCH_FIELDS,
"title": ["title_zh^2.0"],
"vendor": ["vendor_zh^1.5"],
"category": ["category_path_zh^1.5", "category_name_zh^1.5"],
"tags": ["tags^1.0"]
}
# Source fields to return in search results
SOURCE_FIELDS = [
"tenant_id",
"spu_id",
"title_zh",
"brief_zh",
"description_zh",
"vendor_zh",
"tags",
"image_url",
"category_path_zh",
"category_name_zh",
"category_id",
"category_name",
"category_level",
"category1_name",
"category2_name",
"category3_name",
"option1_name",
"option2_name",
"option3_name",
"min_price",
"max_price",
"compare_at_price",
"total_inventory",
"create_time",
"update_time",
"skus",
"specifications"
]
# Query processing settings
ENABLE_TRANSLATION = os.environ.get("ENABLE_TRANSLATION", "true").lower() == "true"
ENABLE_TEXT_EMBEDDING = os.environ.get("ENABLE_TEXT_EMBEDDING", "true").lower() == "true"
TRANSLATION_API_KEY = os.environ.get("DEEPL_API_KEY")
TRANSLATION_SERVICE = "deepl"
# Ranking expression (currently disabled)
RANKING_EXPRESSION = "bm25() + 0.2*text_embedding_relevance()"
# Function score config
FUNCTION_SCORE_CONFIG = {
"score_mode": "sum",
"boost_mode": "multiply",
"functions": []
}
# Load rewrite dictionary from file if exists
def load_rewrite_dictionary() -> Dict[str, str]:
"""Load query rewrite dictionary from file."""
rewrite_file = os.path.join(
os.path.dirname(os.path.dirname(__file__)),
"config",
"query_rewrite.dict"
)
if not os.path.exists(rewrite_file):
return {}
rewrite_dict = {}
try:
with open(rewrite_file, 'r', encoding='utf-8') as f:
for line in f:
line = line.strip()
if not line or line.startswith('#'):
continue
parts = line.split('\t')
if len(parts) == 2:
rewrite_dict[parts[0].strip()] = parts[1].strip()
except Exception as e:
print(f"Warning: Failed to load rewrite dictionary: {e}")
return rewrite_dict
REWRITE_DICTIONARY = load_rewrite_dictionary()
|
|
bf89b597
tangwang
feat(search): ada...
|
115
116
117
118
119
120
121
122
123
|
# Default facets for faceted search
# 分类分面：使用category1_name, category2_name, category3_name
# specifications分面：使用嵌套聚合，按name分组，然后按value聚合
DEFAULT_FACETS = [
"category1_name", # 一级分类
"category2_name", # 二级分类
"category3_name", # 三级分类
"specifications" # 规格分面（特殊处理：嵌套聚合）
]
|