Spaces:
Sleeping
Sleeping
File size: 7,941 Bytes
57cf043 4a37130 57cf043 4a37130 57cf043 |
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 |
import logging
from enum import Enum
def configure_logging(level=logging.INFO, config_file_path='./common.log'):
formatter = logging.Formatter("[%(asctime)s.%(msecs)03d] %(module)30s:%(lineno)4d %(levelname)-7s - %(message)s")
console_handler = logging.StreamHandler()
console_handler.setLevel(level)
console_handler.setFormatter(formatter)
logging.basicConfig(
filename=config_file_path,
filemode="a",
level=level,
datefmt="%Y-%m-%d %H:%M:%S",
format="[%(asctime)s.%(msecs)03d] %(module)30s:%(lineno)4d %(levelname)-7s - %(message)s",
handlers=[console_handler]
)
def get_elastic_query(query):
return {
"query": {
"multi_match": {
"query": f"{query}",
"fields": ["text"],
"fuzziness": "AUTO",
"analyzer": "russian",
}
}
}
def get_elastic_people_query(query):
has_business_curator = (
"бизнес куратор" in query.lower()
or "бизнес-куратор" in query.lower()
or "куратор" in query.lower()
)
business_curator_boost = 30 if has_business_curator else 15
return {
"query": {
"bool": {
"should": [
{
"multi_match": {
"query": f"{query}",
"fields": ["person_name^3"],
"fuzziness": "AUTO",
"analyzer": "standard",
}
},
{
"nested": {
"path": "business_processes",
"query": {
"multi_match": {
"query": f"{query}",
"fields": [
"business_processes.production_activities_section",
"business_processes.processes_name",
],
"fuzziness": "AUTO",
"analyzer": "standard",
}
},
}
},
{
"nested": {
"path": "organizatinal_structure",
"query": {
"multi_match": {
"query": f"{query}",
"fields": ["organizatinal_structure.position^2"],
"fuzziness": "AUTO",
"analyzer": "standard",
}
},
}
},
{
"nested": {
"path": "business_curator",
"query": {
"multi_match": {
"query": f"{query}",
"fields": [
f"business_curator.company_name^{business_curator_boost}"
],
"fuzziness": "AUTO",
"analyzer": "standard",
}
},
}
},
]
}
},
"min_score": 13.0,
}
def get_elastic_group_query(query):
return {
"query": {
"bool": {
"should": [
{
"multi_match": {
"query": f"{query}",
"fields": ["group_name"],
"fuzziness": "AUTO",
"analyzer": "standard",
}
},
{
"multi_match": {
"query": "персонального состава Персональный состав Комитета ПАО ГМК Норильский никель Рабочей группы",
"fields": ["group_name"],
"operator": "or",
"boost": 0.1,
}
},
]
}
},
"min_score": 7.5,
}
def get_elastic_rocks_nn_query(query):
return {
"query": {
"function_score": {
"query": {
"multi_match": {
"query": f"{query}",
"fields": ["division_name", "division_name_2", "company_name"],
"fuzziness": "AUTO",
"analyzer": "custom_analyzer",
}
},
"functions": [{"filter": {"term": {"_id": "3"}}, "weight": 0.5}],
"boost_mode": "multiply",
}
},
"min_score": 0.5,
}
def get_elastic_segmentation_query(query):
return {
"query": {
"bool": {
"should": [
{
"multi_match": {
"query": f"{query}",
"fields": [
"segmentation_model",
"segmentation_model2",
"company_name",
],
"fuzziness": "AUTO",
"analyzer": "russian",
}
},
{
"multi_match": {
"query": "модели сегментации модель сегментации",
"fields": ["segmentation_model", "segmentation_model2"],
"operator": "or",
"boost": 0.1,
}
},
]
}
},
"min_score": 1.0,
}
def get_elastic_abbreviation_query(query):
return {
"query": {
"multi_match": {
"query": f"{query}",
"fuzziness": "AUTO",
"fields": ["text"],
"analyzer": "russian",
}
}
}
def combine_answer(answer):
"""
Args:
answer:
Returns:
"""
answer_combined = {}
indexes = []
for key in answer:
if key != 'people_search':
for answer_key in answer[key]:
answer_value = answer[key][answer_key]
filename_i = answer_value["doc_name"]
title_i = answer_value["title"]
if (
filename_i in answer_combined
and answer_value['index_answer'] not in indexes
):
answer_combined[filename_i]["chunks"].append(answer_value)
else:
answer_combined[filename_i] = {
"filename": filename_i,
"title": title_i,
"chunks": [answer_value],
}
indexes.append(answer_value['index_answer'])
return list(answer_combined.values())
class TypeQuestion(Enum):
TYPE_ONE = '[1]'
TYPE_TWO = '[2]'
TYPE_THREE = '[3]'
def get_source_format(filename: str) -> str:
"""
Получает формат файла из имени файла.
"""
format_ = filename.split('.')[-1]
return format_.upper()
|