globalization, upgrade

pilot/conversation.py

@@ -99,7 +99,7 @@ def gen_sqlgen_conversation(dbname):
     schemas = mo.get_schema(dbname)
     for s in schemas:
         message += s["schema_info"] + ";"
-    return f"数据库{dbname}的Schema信息如下: {message}\n"
+    return f"Database {dbname} Schema information as follows: {message}\n"
 
 
 conv_one_shot = Conversation(
@@ -162,7 +162,7 @@ auto_dbgpt_one_shot = Conversation(
               
               
               Schema:
-              数据库gpt-user的Schema信息如下: users(city,create_time,email,last_login_time,phone,user_name);
+              Database gpt-user Schema information as follows: users(city,create_time,email,last_login_time,phone,user_name);
               
               
               Commands:

pilot/plugins.py

@@ -17,7 +17,7 @@ from pilot.logs import logger
 
 def inspect_zip_for_modules(zip_path: str, debug: bool = False) -> list[str]:
     """
-    加载zip文件的插件，完全兼容Auto_gpt_plugin
+    Loader zip plugin file. Native support Auto_gpt_plugin
 
     Args:
     zip_path (str): Path to the zipfile.

pilot/vector_store/extract_tovec.py

@@ -40,8 +40,8 @@ def knownledge_tovec_st(filename):
 
 
 def load_knownledge_from_doc():
-    """从数据集当中加载知识 
-    # TODO 如果向量存储已经存在, 则无需初始化
+    """Loader Knownledge from current datasets
+    # TODO if the vector store is exists, just use it. 
     """
 
     if not os.path.exists(DATASETS_DIR):

pilot/vector_store/file_loader.py

@@ -40,15 +40,15 @@ class KnownLedge2Vector:
         
     def init_vector_store(self):
         persist_dir = os.path.join(VECTORE_PATH, ".vectordb")
-        print("向量数据库持久化地址: ", persist_dir)
+        print("Vector store Persist address is: ", persist_dir)
         if os.path.exists(persist_dir):
-            # 从本地持久化文件中Load
-            print("从本地向量加载数据...")
+            # Loader from local file.
+            print("Loader data from local persist vector file...")
             vector_store = Chroma(persist_directory=persist_dir, embedding_function=self.embeddings)
             # vector_store.add_documents(documents=documents)
         else:
             documents = self.load_knownlege()
-            # 重新初始化
+            # reinit 
             vector_store = Chroma.from_documents(documents=documents, 
                                                  embedding=self.embeddings,
                                                  persist_directory=persist_dir)
@@ -61,17 +61,17 @@ class KnownLedge2Vector:
             for file in files:
                 filename = os.path.join(root, file)
                 docs = self._load_file(filename)
-                # 更新metadata数据
+                # update metadata. 
                 new_docs = [] 
                 for doc in docs:
                     doc.metadata = {"source": doc.metadata["source"].replace(DATASETS_DIR, "")} 
-                    print("文档2向量初始化中, 请稍等...", doc.metadata)
+                    print("Documents to vector running, please wait...", doc.metadata)
                     new_docs.append(doc)
                 docments += new_docs
         return docments
 
     def _load_file(self, filename):
-        # 加载文件
+        # Loader file
         if filename.lower().endswith(".pdf"):
             loader = UnstructuredFileLoader(filename) 
             text_splitor = CharacterTextSplitter()