Refa: remove dataset language and validate dataset name length. (#5707)

### What problem does this PR solve?

#5686
#5702

### Type of change

- [x] Refactoring

api/apps/sdk/dataset.py

@@ -66,10 +66,6 @@ def create(tenant_id):
               type: string
               enum: ['me', 'team']
               description: Dataset permission.
-            language:
-              type: string
-              enum: ['Chinese', 'English']
-              description: Language of the dataset.
             chunk_method:
               type: string
               enum: ["naive", "manual", "qa", "table", "paper", "book", "laws",
@@ -91,11 +87,9 @@ def create(tenant_id):
     req = request.json
     e, t = TenantService.get_by_id(tenant_id)
     permission = req.get("permission")
-    language = req.get("language")
     chunk_method = req.get("chunk_method")
     parser_config = req.get("parser_config")
     valid_permission = ["me", "team"]
-    valid_language = ["Chinese", "English"]
     valid_chunk_method = [
         "naive",
         "manual",
@@ -114,8 +108,6 @@ def create(tenant_id):
     check_validation = valid(
         permission,
         valid_permission,
-        language,
-        valid_language,
         chunk_method,
         valid_chunk_method,
     )
@@ -134,6 +126,10 @@ def create(tenant_id):
     req["name"] = req["name"].strip()
     if req["name"] == "":
         return get_error_data_result(message="`name` is not empty string!")
+    if len(req["name"]) >= 128:
+        return get_error_data_result(
+            message="Dataset name should not be longer than 128 characters."
+        )
     if KnowledgebaseService.query(
         name=req["name"], tenant_id=tenant_id, status=StatusEnum.VALID.value
     ):
@@ -297,10 +293,6 @@ def update(tenant_id, dataset_id):
               type: string
               enum: ['me', 'team']
               description: Updated permission.
-            language:
-              type: string
-              enum: ['Chinese', 'English']
-              description: Updated language.
             chunk_method:
               type: string
               enum: ["naive", "manual", "qa", "table", "paper", "book", "laws",
@@ -324,11 +316,9 @@ def update(tenant_id, dataset_id):
     if any(key in req for key in invalid_keys):
         return get_error_data_result(message="The input parameters are invalid.")
     permission = req.get("permission")
-    language = req.get("language")
     chunk_method = req.get("chunk_method")
     parser_config = req.get("parser_config")
     valid_permission = ["me", "team"]
-    valid_language = ["Chinese", "English"]
     valid_chunk_method = [
         "naive",
         "manual",
@@ -347,8 +337,6 @@ def update(tenant_id, dataset_id):
     check_validation = valid(
         permission,
         valid_permission,
-        language,
-        valid_language,
         chunk_method,
         valid_chunk_method,
     )
@@ -416,6 +404,10 @@ def update(tenant_id, dataset_id):
         req["embd_id"] = req.pop("embedding_model")
     if "name" in req:
         req["name"] = req["name"].strip()
+        if len(req["name"]) >= 128:
+            return get_error_data_result(
+                message="Dataset name should not be longer than 128 characters."
+            )
         if (
             req["name"].lower() != kb.name.lower()
             and len(

api/utils/api_utils.py

@@ -335,11 +335,9 @@ def generate_confirmation_token(tenent_id):
     return "ragflow-" + serializer.dumps(get_uuid(), salt=tenent_id)[2:34]
 
 
-def valid(permission, valid_permission, language, valid_language, chunk_method, valid_chunk_method):
+def valid(permission, valid_permission, chunk_method, valid_chunk_method):
     if valid_parameter(permission, valid_permission):
         return valid_parameter(permission, valid_permission)
-    if valid_parameter(language, valid_language):
-        return valid_parameter(language, valid_language)
     if valid_parameter(chunk_method, valid_chunk_method):
         return valid_parameter(chunk_method, valid_chunk_method)
 

docs/references/http_api_reference.md

@@ -178,7 +178,6 @@ Creates a dataset.
   - `"name"`: `string`
   - `"avatar"`: `string`
   - `"description"`: `string`
-  - `"language"`: `string`
   - `"embedding_model"`: `string`
   - `"permission"`: `string`
   - `"chunk_method"`: `string`
@@ -214,11 +213,6 @@ curl --request POST \
 - `"description"`: (*Body parameter*), `string`  
   A brief description of the dataset to create.
 
-- `"language"`: (*Body parameter*), `string`  
-  The language setting of the dataset to create. Available options:  
-  - `"English"` (default)
-  - `"Chinese"`
-
 - `"embedding_model"`: (*Body parameter*), `string`  
   The name of the embedding model to use. For example: `"BAAI/bge-zh-v1.5"`
 

docs/references/python_api_reference.md

@@ -82,7 +82,6 @@ RAGFlow.create_dataset(
     avatar: str = "",
     description: str = "",
     embedding_model: str = "BAAI/bge-large-zh-v1.5",
-    language: str = "English",
     permission: str = "me", 
     chunk_method: str = "naive",
     parser_config: DataSet.ParserConfig = None
@@ -108,12 +107,6 @@ Base64 encoding of the avatar. Defaults to `""`
 
 A brief description of the dataset to create. Defaults to `""`.
 
-##### language: `str`
-
-The language setting of the dataset to create. Available options:
-
-- `"English"` (default)
-- `"Chinese"`
 
 ##### permission
 

sdk/python/ragflow_sdk/modules/dataset.py

@@ -30,7 +30,6 @@ class DataSet(Base):
         self.avatar = ""
         self.tenant_id = None
         self.description = ""
-        self.language = "English"
         self.embedding_model = ""
         self.permission = "me"
         self.document_count = 0