close auto load plugin

docs/modules/prompts.md

@@ -1,3 +1,5 @@
 # Prompts
 
-Prompt is a very important part of the interaction between the large model and the user, and to a certain extent, it determines the quality and accuracy of the answer generated by the large model. In this project, we will automatically optimize the corresponding prompt according to user input and usage scenarios, making it easier and more efficient for users to use large language models.
+Prompt is a very important part of the interaction between the large model and the user, and to a certain extent, it determines the quality and accuracy of the answer generated by the large model. In this project, we will automatically optimize the corresponding prompt according to user input and usage scenarios, making it easier and more efficient for users to use large language models.
+
+### 1.DB-GPT Prompt 

pilot/common/plugins.py

@@ -74,6 +74,9 @@ def create_directory_if_not_exists(directory_path: str) -> bool:
 
 
 def load_native_plugins(cfg: Config):
+    if not cfg.plugins_auto_load:
+        print("not auto load_native_plugins")
+        return
     print("load_native_plugins")
     ### TODO 默认拉主分支，后续拉发布版本
     branch_name = cfg.plugins_git_branch

pilot/configs/config.py

@@ -90,6 +90,7 @@ class Config(metaclass=Singleton):
         ### The associated configuration parameters of the plug-in control the loading and use of the plug-in
         self.plugins: List[AutoGPTPluginTemplate] = []
         self.plugins_openai = []
+        self.plugins_auto_load =  os.getenv("AUTO_LOAD_PLUGIN", "False") == "True"
 
         self.plugins_git_branch = os.getenv("PLUGINS_GIT_BRANCH", "plugin_dashboard")
 
@@ -154,8 +155,8 @@ class Config(metaclass=Singleton):
 
         ### EMBEDDING Configuration
         self.EMBEDDING_MODEL = os.getenv("EMBEDDING_MODEL", "text2vec")
-        self.KNOWLEDGE_CHUNK_SIZE = int(os.getenv("KNOWLEDGE_CHUNK_SIZE", 500))
-        self.KNOWLEDGE_SEARCH_TOP_SIZE = int(os.getenv("KNOWLEDGE_SEARCH_TOP_SIZE", 10))
+        self.KNOWLEDGE_CHUNK_SIZE = int(os.getenv("KNOWLEDGE_CHUNK_SIZE", 100))
+        self.KNOWLEDGE_SEARCH_TOP_SIZE = int(os.getenv("KNOWLEDGE_SEARCH_TOP_SIZE", 5))
         ### SUMMARY_CONFIG Configuration
         self.SUMMARY_CONFIG = os.getenv("SUMMARY_CONFIG", "VECTOR")