write data

doc_similarity/answer_similarity.py

+import json
 import os
 import random
 import sys
@@ -7,7 +8,9 @@ sys.path.append(os.path.realpath("."))
 import faiss
 import numpy as np
 from bert_serving.client import BertClient
+from utils.cache import redis_client_db
 from utils.es import es_scan, get_answer_info_from_es
+from utils.files import MODEL_PATH
 
 
 def cos_sim(vector_a, vector_b):
@@ -52,6 +55,8 @@ if __name__ == "__main__":
         level_dict[content_level].append(id)
         embedding_dict[id] = bc.encode([content]).tolist()[0]
 
+    redis_client_db.hmset("answer:level_dict", json.dumps(level_dict))
+
     tmp_tuple = random.choice(list(embedding_dict.items()))
     print(tmp_tuple)
     answer_ids = np.array(list(embedding_dict.keys())).astype("int")
@@ -66,9 +71,7 @@ if __name__ == "__main__":
     print("trained: " + str(index2.is_trained))
     print("total index: " + str(index2.ntotal))
 
-    base_dir = os.getcwd()
-    model_dir = os.path.join(base_dir, "_models")
-    index_path = os.path.join(model_dir, "faiss_answer_similarity.index")
+    index_path = os.path.join(MODEL_PATH, "faiss_answer_similarity.index")
     faiss.write_index(index2, index_path)
     print(index_path)