Spaces:
Running
Running
File size: 1,818 Bytes
b77c0a2 01ae535 b77c0a2 01ae535 b77c0a2 01ae535 b77c0a2 |
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 |
import pickle
from config import (
MODEL_NAME,
SENTENCE_EMBEDDING_FILE,
SAMPLE_DATA_FILE, SUBJECT_DATA_FILE
)
from sentence_transformer_lib.sentence_transformer_helper import SentenceTransformerHelper
from data_lib.subject_data import SubjectData
from data_lib.sample_name_data import SampleNameData
class SentenceTransformerService:
def __init__(self):
self.sentenceTransformerHelper = None
self.dic_standard_subject = None
self.sample_name_sentence_embeddings = None
self.sampleData = None
def load_model_data(self):
"""Load model and data only once at startup"""
if self.sentenceTransformerHelper is not None:
print("Model already loaded. Skipping reload.")
return # Không load lại nếu đã có model
print("Loading models and data...")
# Load sentence transformer model
self.sentenceTransformerHelper = SentenceTransformerHelper(
convert_to_zenkaku_flag=True, replace_words=None, keywords=None
)
self.sentenceTransformerHelper.load_model_by_name(MODEL_NAME)
# Load standard subject dictionary
self.dic_standard_subject = SubjectData.create_standard_subject_dic_from_file(SUBJECT_DATA_FILE)
# Load pre-computed embeddings and similarities
with open(SENTENCE_EMBEDDING_FILE, "rb") as f:
self.sample_name_sentence_embeddings = pickle.load(f)
# Load and process sample data
self.sampleData = SampleNameData()
self.sampleData.load_data_from_csv(SAMPLE_DATA_FILE)
self.sampleData.process_data()
self.sampleData.build_search_tree()
print("Models and data loaded successfully")
# Global instance (singleton)
sentence_transformer_service = SentenceTransformerService()
|