optimize log

qlib/finco/conf.py

@@ -13,7 +13,7 @@ class Config(SingletonBaseClass):
 
     def __init__(self):
         self.use_azure = os.getenv("USE_AZURE") == "True"
-        self.temperature = 0 if os.getenv("TEMPERATURE") is None else float(os.getenv("TEMPERATURE"))
+        self.temperature = 0.5 if os.getenv("TEMPERATURE") is None else float(os.getenv("TEMPERATURE"))
         self.max_tokens = 800 if os.getenv("MAX_TOKENS") is None else int(os.getenv("MAX_TOKENS"))
 
         self.openai_api_key = os.getenv("OPENAI_API_KEY")

qlib/finco/record.txt

@@ -1,2 +0,0 @@
-conda activate qlib38
-python cli_learn.py "build an A-share stock market daily portfolio in quantitative investment and minimize the maximum drawdown while maintaining return."

tests/finco/knowledge/execute/storage.yml

@@ -1,4 +0,0 @@
-- content: '[Success]: XXXX, the results looks reasonable  # Keywords: supervised
-    learning, data'
-- content: '[Fail]: XXXX, it raise memory error due to  YYYYY  # Keywords: supervised
-    learning, data'

tests/finco/knowledge/finance/storage.yml

@@ -1 +0,0 @@
-[]

tests/finco/test_sumarize.py

@@ -9,7 +9,6 @@ from qlib.finco.task import SummarizeTask
 from qlib.finco.workflow import WorkflowContextManager
 from qlib.finco.llm import APIBackend
 from qlib.finco.workflow import WorkflowManager
-from qlib.finco.knowledge import PracticeKnowledge, YamlStorage
 
 load_dotenv(verbose=True, override=True)
 
@@ -62,9 +61,6 @@ class TestSummarize(unittest.TestCase):
         resp = task.get_info_from_file("")
         print(resp)
 
-    def test_practice_knowledge(self):
-        pk = PracticeKnowledge(YamlStorage(path.joinpath(Path.cwd().joinpath("knowledge")/f"{self.KT_PRACTICE}/{YamlStorage.DEFAULT_NAME}")))
-        pk.add(["test1", "test2"])
 
 if __name__ == "__main__":
     unittest.main()