删除重复的引入和纠正拼写错误 (#2599)

* 1.删除重复的引入
2.拼写错误

* 1.参数或者文档拼写错误纠正
2.doc下的faq、install已经删除，更新为ES部署指南，考虑到doc下的文档经常更新，即使扫描doc文件夹，也可能为空的情况，readme.md大概率不会删除。

init_database.py

@@ -6,7 +6,6 @@ from configs.model_config import NLTK_DATA_PATH, EMBEDDING_MODEL
 import nltk
 nltk.data.path = [NLTK_DATA_PATH] + nltk.data.path
 from datetime import datetime
-import sys
 
 
 if __name__ == "__main__":
@@ -50,11 +49,11 @@ if __name__ == "__main__":
     )
     parser.add_argument(
         "-i",
-        "--increament",
+        "--increment",
         action="store_true",
         help=('''
             update vector store for files exist in local folder and not exist in database.
-            use this option if you want to create vectors increamentally.
+            use this option if you want to create vectors incrementally.
             '''
         )
     )
@@ -100,7 +99,7 @@ if __name__ == "__main__":
 
     if args.clear_tables:
         reset_tables()
-        print("database talbes reseted")
+        print("database tables reset")
 
     if args.recreate_vs:
         create_tables()
@@ -110,8 +109,8 @@ if __name__ == "__main__":
         import_from_db(args.import_db)
     elif args.update_in_db:
         folder2db(kb_names=args.kb_name, mode="update_in_db", embed_model=args.embed_model)
-    elif args.increament:
-        folder2db(kb_names=args.kb_name, mode="increament", embed_model=args.embed_model)
+    elif args.increment:
+        folder2db(kb_names=args.kb_name, mode="increment", embed_model=args.embed_model)
     elif args.prune_db:
         prune_db_docs(args.kb_name)
     elif args.prune_folder:

server/knowledge_base/migrate.py

@@ -84,7 +84,7 @@ def file_to_kbfile(kb_name: str, files: List[str]) -> List[KnowledgeFile]:
 
 def folder2db(
         kb_names: List[str],
-        mode: Literal["recreate_vs", "update_in_db", "increament"],
+        mode: Literal["recreate_vs", "update_in_db", "increment"],
         vs_type: Literal["faiss", "milvus", "pg", "chromadb"] = DEFAULT_VS_TYPE,
         embed_model: str = EMBEDDING_MODEL,
         chunk_size: int = CHUNK_SIZE,
@@ -97,7 +97,7 @@ def folder2db(
         recreate_vs: recreate all vector store and fill info to database using existed files in local folder
         fill_info_only(disabled): do not create vector store, fill info to db using existed files only
         update_in_db: update vector store and database info using local files that existed in database only
-        increament: create vector store and database info for local files that not existed in database only
+        increment: create vector store and database info for local files that not existed in database only
     """
 
     def files2vs(kb_name: str, kb_files: List[KnowledgeFile]):
@@ -142,7 +142,7 @@ def folder2db(
             files2vs(kb_name, kb_files)
             kb.save_vector_store()
         # 对比本地目录与数据库中的文件列表，进行增量向量化
-        elif mode == "increament":
+        elif mode == "increment":
             db_files = kb.list_files()
             folder_files = list_files_from_folder(kb_name)
             files = list(set(folder_files) - set(db_files))
@@ -150,7 +150,7 @@ def folder2db(
             files2vs(kb_name, kb_files)
             kb.save_vector_store()
         else:
-            print(f"unspported migrate mode: {mode}")
+            print(f"unsupported migrate mode: {mode}")
 
 
 def prune_db_docs(kb_names: List[str]):

tests/test_migrate.py

@@ -14,8 +14,7 @@ from server.knowledge_base.migrate import folder2db, prune_db_docs, prune_folder
 # setup test knowledge base
 kb_name = "test_kb_for_migrate"
 test_files = {
-    "faq.md": str(root_path / "docs" / "faq.md"),
-    "install.md": str(root_path / "docs" / "install.md"),
+    "readme.md": str(root_path / "readme.md"),
 }
 
 
@@ -56,13 +55,13 @@ def test_recreate_vs():
             assert doc.metadata["source"] == name
 
 
-def test_increament():
+def test_increment():
     kb = KBServiceFactory.get_service_by_name(kb_name)
     kb.clear_vs()
     assert kb.list_files() == []
     assert kb.list_docs() == []
 
-    folder2db([kb_name], "increament")
+    folder2db([kb_name], "increment")
 
     files = kb.list_files()
     print(files)