github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-01 17:17:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

[devops] remove post commit ci (#5566)

Browse Source 
* [devops] remove post commit ci

* [misc] run pre-commit on all files

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Hongxin Liu
2024-04-08 15:09:40 +08:00
committed by GitHub
parent 341263df48
commit 641b1ee71a
82 changed files with 849 additions and 962 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
applications/ColossalQA/tests/test_document_loader.py
View File

@@ -1,21 +1,21 @@
import os
from colossalqa.data_loader.document_loader import DocumentLoader
def test_add_document():
PATH = os.environ.get('TEST_DOCUMENT_LOADER_DATA_PATH')
files = [[PATH, 'all data']]
PATH = os.environ.get("TEST_DOCUMENT_LOADER_DATA_PATH")
files = [[PATH, "all data"]]
document_loader = DocumentLoader(files)
documents = document_loader.all_data
all_files = []
for doc in documents:
assert isinstance(doc.page_content, str)==True
if doc.metadata['source'] not in all_files:
all_files.append(doc.metadata['source'])
assert isinstance(doc.page_content, str) == True
if doc.metadata["source"] not in all_files:
all_files.append(doc.metadata["source"])
print(all_files)
assert len(all_files) == 6
if __name__=='__main__':
if __name__ == "__main__":
test_add_document()

80
applications/ColossalQA/tests/test_retrieval_qa.py
View File

@@ -4,56 +4,44 @@ from colossalqa.retrieval_conversation_universal import UniversalRetrievalConver
def test_en_retrievalQA():
data_path_en = os.environ.get('TEST_DATA_PATH_EN')
data_path_zh = os.environ.get('TEST_DATA_PATH_ZH')
en_model_path = os.environ.get('EN_MODEL_PATH')
zh_model_path = os.environ.get('ZH_MODEL_PATH')
zh_model_name = os.environ.get('ZH_MODEL_NAME')
en_model_name = os.environ.get('EN_MODEL_NAME')
sql_file_path = os.environ.get('SQL_FILE_PATH')
qa_session = UniversalRetrievalConversation(files_en=[{
'data_path': data_path_en,
'name': 'company information',
'separator': '\n'
}],
files_zh=[{
'data_path': data_path_zh,
'name': 'company information',
'separator': '\n'
}],
zh_model_path=zh_model_path,
en_model_path=en_model_path,
zh_model_name=zh_model_name,
en_model_name=en_model_name,
sql_file_path=sql_file_path)
ans = qa_session.run("which company runs business in hotel industry?", which_language='en')
data_path_en = os.environ.get("TEST_DATA_PATH_EN")
data_path_zh = os.environ.get("TEST_DATA_PATH_ZH")
en_model_path = os.environ.get("EN_MODEL_PATH")
zh_model_path = os.environ.get("ZH_MODEL_PATH")
zh_model_name = os.environ.get("ZH_MODEL_NAME")
en_model_name = os.environ.get("EN_MODEL_NAME")
sql_file_path = os.environ.get("SQL_FILE_PATH")
qa_session = UniversalRetrievalConversation(
files_en=[{"data_path": data_path_en, "name": "company information", "separator": "\n"}],
files_zh=[{"data_path": data_path_zh, "name": "company information", "separator": "\n"}],
zh_model_path=zh_model_path,
en_model_path=en_model_path,
zh_model_name=zh_model_name,
en_model_name=en_model_name,
sql_file_path=sql_file_path,
)
ans = qa_session.run("which company runs business in hotel industry?", which_language="en")
print(ans)
def test_zh_retrievalQA():
data_path_en = os.environ.get('TEST_DATA_PATH_EN')
data_path_zh = os.environ.get('TEST_DATA_PATH_ZH')
en_model_path = os.environ.get('EN_MODEL_PATH')
zh_model_path = os.environ.get('ZH_MODEL_PATH')
zh_model_name = os.environ.get('ZH_MODEL_NAME')
en_model_name = os.environ.get('EN_MODEL_NAME')
sql_file_path = os.environ.get('SQL_FILE_PATH')
qa_session = UniversalRetrievalConversation(files_en=[{
'data_path': data_path_en,
'name': 'company information',
'separator': '\n'
}],
files_zh=[{
'data_path': data_path_zh,
'name': 'company information',
'separator': '\n'
}],
zh_model_path=zh_model_path,
en_model_path=en_model_path,
zh_model_name=zh_model_name,
en_model_name=en_model_name,
sql_file_path=sql_file_path)
ans = qa_session.run("哪家公司在经营酒店业务？", which_language='zh')
data_path_en = os.environ.get("TEST_DATA_PATH_EN")
data_path_zh = os.environ.get("TEST_DATA_PATH_ZH")
en_model_path = os.environ.get("EN_MODEL_PATH")
zh_model_path = os.environ.get("ZH_MODEL_PATH")
zh_model_name = os.environ.get("ZH_MODEL_NAME")
en_model_name = os.environ.get("EN_MODEL_NAME")
sql_file_path = os.environ.get("SQL_FILE_PATH")
qa_session = UniversalRetrievalConversation(
files_en=[{"data_path": data_path_en, "name": "company information", "separator": "\n"}],
files_zh=[{"data_path": data_path_zh, "name": "company information", "separator": "\n"}],
zh_model_path=zh_model_path,
en_model_path=en_model_path,
zh_model_name=zh_model_name,
en_model_name=en_model_name,
sql_file_path=sql_file_path,
)
ans = qa_session.run("哪家公司在经营酒店业务？", which_language="zh")
print(ans)