style: format code with Autopep8, isort and Ruff Formatter

src/everyai/data_loader/everyai_dataset.py

@@ -111,7 +111,10 @@ def load(self, path_or_database: str | Path = None, formatter: str = "csv"):
                 path_or_database = Path(path_or_database)
             if not isinstance(path_or_database, Path):
                 logging.error("Invalid file name: %s", path_or_database)
-            if path_or_database is not None and path_or_database.suffix != f".{formatter}":
+            if (
+                path_or_database is not None
+                and path_or_database.suffix != f".{formatter}"
+            ):
                 logging.warning("Change file format to %s", formatter)
                 path_or_database = path_or_database.with_suffix(f".{formatter}")
             else:
@@ -163,7 +166,7 @@ def save(self, path_or_database: str | Path = None, formatter: str = "csv"):
                     logging.error("Invalid format: %s", formatter)
 
     @staticmethod
-    def _initialize_mongo_connection():# -> Database:
+    def _initialize_mongo_connection():  # -> Database:
         mongodb_config = get_config(MONGO_CONFIG_PATH)
         result = get_mongo_connection(**mongodb_config)
         logging.info("Use default mongodb: %s", result)

src/everyai/generator/generate.py

@@ -31,9 +31,7 @@ def _openai_generate(
     ) -> str:
         client = OpenAI(api_key=api_key, base_url=base_url)
         messages = [{"role": "user", "content": user_input}]
-        result = client.chat.completions.create(
-            messages=messages, model=model_name
-        )
+        result = client.chat.completions.create(messages=messages, model=model_name)
         return result.choices[0].message.content
 
     def _huggingface_generate(
@@ -48,9 +46,7 @@ def _huggingface_generate(
                 logging.info("Using glm-4-9b-chat model")
                 logging.info("load model from %s", model_path_or_name)
                 if self.tokenizer is None:
-                    self.tokenizer = AutoTokenizer.from_pretrained(
-                        model_path_or_name
-                    )
+                    self.tokenizer = AutoTokenizer.from_pretrained(model_path_or_name)
                 else:
                     self.tokenizer = self.tokenizer
                     logging.info("Use existing tokenizer")

src/everyai/main.py

@@ -39,16 +39,12 @@ def generate():
                 file_path=data_config["file_path"],
                 data_type=data_config["data_type"],
             )
-            qa_datas = data_loader.load_data2list(
-                max_count=data_config["max_count"]
-            )
+            qa_datas = data_loader.load_data2list(max_count=data_config["max_count"])
             everyai_dataset = EveryaiDataset(
                 dataname=data_config["data_name"],
                 ai_list=[generate_config["model_name"]],
             )
-            for data in tqdm(
-                qa_datas, desc="Generating data", total=len(qa_datas)
-            ):
+            for data in tqdm(qa_datas, desc="Generating data", total=len(qa_datas)):
                 ai_response: str = generator.generate(data["question"])
                 everyai_dataset.insert_ai_response(
                     question=data["question"],
@@ -106,9 +102,7 @@ def classfiy():
         )
         everyai_dataset.load(formatter="mongodb")
         logging.info("Loaded data: %s", everyai_dataset.data_name)
-        texts, labels = everyai_dataset.get_records_with_1ai(
-            ["THUDM/glm-4-9b-chat-hf"]
-        )
+        texts, labels = everyai_dataset.get_records_with_1ai(["THUDM/glm-4-9b-chat-hf"])
         for classfiy_config in get_config(file_path=CLASSFIY_CONFIG_PATH)[
             "classfier_list"
         ]:
@@ -119,9 +113,7 @@ def classfiy():
                     )
                 case _:
                     raise ValueError("Classfier type not supported")
-            text_classfier.load_data(
-                texts, labels, data_name=everyai_dataset.data_name
-            )
+            text_classfier.load_data(texts, labels, data_name=everyai_dataset.data_name)
             text_classfier.train()
             text_classfier.test()
             text_classfier.save_model()