Update upload filename length limit from 128 to 256, which is aligned with os

Signed-off-by: Jin Hai <haijin.chn@gmail.com>

Author: JinHai-CN

api/apps/kb_app.py

@@ -47,7 +47,7 @@ def create():
         return get_data_error_result(message="Dataset name must be string.")
     if dataset_name == "":
         return get_data_error_result(message="Dataset name can't be empty.")
-    if len(dataset_name) >= DATASET_NAME_LIMIT:
+    if len(dataset_name.encode("utf-8")) >= DATASET_NAME_LIMIT:
         return get_data_error_result(
             message=f"Dataset name length is {len(dataset_name)} which is large than {DATASET_NAME_LIMIT}")
 

api/constants.py

@@ -25,3 +25,4 @@
 REQUEST_MAX_WAIT_SEC = 300
 
 DATASET_NAME_LIMIT = 128
+FILE_NAME_LEN_LIMIT = 256

api/db/services/file_service.py

@@ -30,7 +30,7 @@
 from api.utils import get_uuid
 from api.utils.file_utils import filename_type, read_potential_broken_pdf, thumbnail_img
 from rag.utils.storage_factory import STORAGE_IMPL
-
+from api.constants import FILE_NAME_LEN_LIMIT
 
 class FileService(CommonService):
     # Service class for managing file operations and storage
@@ -412,7 +412,7 @@ def upload_document(self, kb, file_objs, user_id):
                 MAX_FILE_NUM_PER_USER = int(os.environ.get("MAX_FILE_NUM_PER_USER", 0))
                 if MAX_FILE_NUM_PER_USER > 0 and DocumentService.get_doc_count(kb.tenant_id) >= MAX_FILE_NUM_PER_USER:
                     raise RuntimeError("Exceed the maximum file number of a free user!")
-                if len(file.filename.encode("utf-8")) >= 128:
+                if len(file.filename.encode("utf-8")) >= FILE_NAME_LEN_LIMIT:
                     raise RuntimeError("Exceed the maximum length of file name!")
 
                 filename = duplicate_name(DocumentService.query, name=file.filename, kb_id=kb.id)

sdk/python/test/test_frontend_api/test_dataset.py

@@ -108,7 +108,7 @@ def test_invalid_name_dataset(get_auth):
 
     long_string = ""
 
-    while len(long_string) <= DATASET_NAME_LIMIT:
+    while len(long_string.encode("utf-8")) <= DATASET_NAME_LIMIT:
         long_string += random.choice(string.ascii_letters + string.digits)
 
     res = create_dataset(get_auth, long_string)