diff --git a/qa_amend.py b/qa_Ask.py
similarity index 100%
rename from qa_amend.py
rename to qa_Ask.py
diff --git a/qa_test.py b/qa_test.py
deleted file mode 100644
index a38e1ad..0000000
--- a/qa_test.py
+++ /dev/null
@@ -1,127 +0,0 @@
-
-import sys
-
-from kb_config import logger
-from sentence_transformers import CrossEncoder
-from faiss_kb_service import FaissKBService, DocumentWithVectorStoreId
-from langchain.docstore.document import Document
-from base_kb import KnowledgeFile
-
-class QAService():
- def __init__(self, kb_name, device) -> None:
-
- embed_model_path = 'bge-large-zh-v1.5'
- fkbs = FaissKBService(kb_name, embed_model_path=embed_model_path, device=device)
- fkbs.do_create_kb()
- self.fkbs = fkbs
- self.kb_name = kb_name
-
- def delete_qa_file(self, qa_file_id):
- kb_file = KnowledgeFile(qa_file_id, self.kb_name)
- self.fkbs.do_delete_doc(kb_file, not_refresh_vs_cache=True)
-
- def update_qa_doc(self, qa_file_id, doc_list, id_list):
- self.delete_qa_file(qa_file_id)
-
- doc_infos = self.fkbs.do_add_doc(doc_list, ids=id_list)
- logger.info('fassi add docs: ' + str(len(doc_infos)))
-
- self.fkbs.save_vector_store()
-
-
- def search(self,
- query,
- top_k = 3,
- score_threshold = 0.75,
- reranked=False):
-
- docs = self.fkbs.do_search(query, top_k, 1 - score_threshold)
-
- return docs
-
-
-import json
-
-
-def create_question_id(intent_code, j, test_question):
- return f"{intent_code}@{j}@{test_question}"
-
-
-
-def load_testing_data(file_path):
-
- test_data_list = []
- question_list = []
- id_list = []
-
- with open(file_path, encoding='utf-8') as f:
- data = json.load(f)
- for i, item in enumerate(data):
- test_question = item['testQuestion']
- intent_code = item['expectIntentCode']
- test_data_list.append((test_question, intent_code))
-
- q_list = item['expectIntentQuestionExample']
- for j, q in enumerate(q_list):
- q_id = create_question_id(intent_code, j, test_question)
- question_list.append(q)
- id_list.append(q_id)
- return test_data_list, question_list, id_list
-
-
-def convert_to_doc_list(question_list, id_list, qa_file_id):
- doc_list = []
- for question, id in zip(question_list, id_list):
-
- metadata = {
- 'source': qa_file_id,
- 'id': id
- }
- doc = Document(page_content=question, metadata=metadata)
- doc_list.append(doc)
-
- return doc_list
-
-import time
-def work():
- start_time = time.time()
- kb_name = 'my_kb_test'
- device = None
- qa_service = QAService(kb_name, device)
-
-
- test_data_list, question_list, id_list = load_testing_data(r'test_data/testing_data.json')
- print('Loaded data!')
-
- qa_file_id = 'QA_TEST_2' # the source of the qa, using for data cleaning, make sure to be unique
-
-
- doc_list = convert_to_doc_list(question_list, id_list, qa_file_id)
-
- qa_service.update_qa_doc(qa_file_id, doc_list, id_list)
-
- cnt = 0
- for query, code in test_data_list:
- rst = qa_service.search(query)
- if do_test(query, code, rst):
- cnt += 1
-
- print(str(cnt) + '/' + str(len(test_data_list)))
-
- end_time = time.time()
- elapsed_time = end_time - start_time
- print(f"总耗时: {elapsed_time} 秒")
-
-def do_test(query, expected_intent_code, rst):
- if rst is None or len(rst)==0:
- print('Empty: ' + query)
- return False
- for rst_doc, similarity_score in rst:
- page_content = rst_doc.page_content
- intent_code = rst_doc.metadata['id'].split('@')[0]
- print(
- f"{query} vs {page_content} : {expected_intent_code} vs {intent_code} - Similarity Score: {1 - similarity_score}")
- return True
-
-work()
-
diff --git a/test.py b/test.py
deleted file mode 100644
index 7773f78..0000000
--- a/test.py
+++ /dev/null
@@ -1,82 +0,0 @@
-
-
-import json
-
-
-
-def create_answer_id(i):
- return 'A_' + str(i)
-
-def create_question_id(intent_code, j):
- return intent_code + '@' + str(j)
-
-
-def load_traing_data(file_path):
-
- question_list = []
- id_list = []
-
- with open(file_path) as f:
- data = json.load(f)
- for i, item in enumerate(data):
- intent_code = item['intentCode']
- q_list = item['questionExample']
- for j, q in enumerate(q_list):
- q_id = create_question_id(intent_code, j)
- question_list.append(q)
- id_list.append(q_id)
-
- return question_list, id_list
-
-
-def load_testing_data(file_path):
-
- test_data_list = []
- question_list = []
- id_list = []
-
- with open(file_path, encoding='utf-8') as f:
- data = json.load(f)
- for i, item in enumerate(data):
- test_question = item['testQuestion']
- intent_code = item['expectIntentCode']
- test_data_list.append((test_question, intent_code))
-
- q_list = item['expectIntentQuestionExample']
- for j, q in enumerate(q_list):
- q_id = create_question_id(intent_code, j)
- question_list.append(q)
- id_list.append(q_id)
-
- return test_data_list, question_list, id_list
-
-
-
-
-def work():
- # question_list, id_list = load_traing_data('test_data/training_data.json')
-
- # print(question_list[0])
- # print(id_list[0])
-
- # print(question_list[21])
- # print(id_list[21])
-
- # intent_conde, idx = id_list[21].split('@')
- # print(intent_conde)
- # print(idx)
-
- test_data_list, question_list, id_list = load_testing_data('test_data/testing_data.json')
- q_len = len(question_list)
- print(question_list[0])
- print(id_list[0])
- print(question_list[q_len-1])
- print(id_list[q_len-1])
- print('#########')
- print(test_data_list[0][0])
- print(test_data_list[0][1])
-
-
-work()
-
-