fix

utils/summary_utils.py

@@ -1,17 +1,14 @@
-import re
-
 from langdetect import detect
 from transformers import pipeline
 
 from utils.tag_utils import filter_tags
 
-AiSummaryVersion = 2
+AiSummaryVersion = 3
 MinTagScore = 0.7
 summarization_pipeline = pipeline("summarization", model="Falconsai/text_summarization")
 en_translation_pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-mul-en")
-tag_gen_pipe_1 = pipeline("text-classification", model="yiyanghkust/finbert-esg-9-categories")
-tag_gen_pipe_2 = pipeline("text-classification", model="dima806/news-category-classifier-distilbert")
-tag_gen_pipe_3 = pipeline("text-classification", model="elozano/bert-base-cased-news-category")
+tag_gen_pipe_1 = pipeline("text-classification", model="dima806/news-category-classifier-distilbert")
+tag_gen_pipe_2 = pipeline("text-classification", model="elozano/bert-base-cased-news-category")
 
 
 def summarize(id: str, text: str):
@@ -19,14 +16,10 @@ def summarize(id: str, text: str):
         return {
             "ver": AiSummaryVersion
         }
-    print('XXXXXXXXXXXXXXXXXXXXX text')
     summary = get_summarization(text) if len(text) > 3000 else text
-    print('XXXXXXXXXXXXXXXXXXXXX summary')
-    print(summary)
     translated = get_en_translation(summary)
     tags = get_tags(translated, id)
     tags = filter_tags(tags)
-    print(tags)
     tags = sorted(list(set(tags)))
 
     value = {
@@ -73,7 +66,6 @@ def get_tags(text: str, id: str):
     try:
         tags1 = [tag['label'] for tag in tag_gen_pipe_1(text) if tag['score'] >= MinTagScore]
         tags2 = [tag['label'] for tag in tag_gen_pipe_2(text) if tag['score'] >= MinTagScore]
-        tags3 = [tag['label'] for tag in tag_gen_pipe_3(text) if tag['score'] >= MinTagScore]
-        return tags1 + tags2 + tags3
+        return tags1 + tags2
     except:
         return []