Refa: validation utils to use Pydantic v2 style models (#9037)

### What problem does this PR solve?

- Update BaseModel to use model_config instead of Config class
- Replace StrEnum with Literal types for method fields
- Convert Field declarations to Annotated style

### Type of change

- [x] Refactoring

api/utils/validation_utils.py

 #  limitations under the License.
 #
 from collections import Counter
-from enum import auto
-from typing import Annotated, Any
+from typing import Annotated, Any, Literal
 from uuid import UUID
 
 from flask import Request
-from pydantic import BaseModel, Field, StringConstraints, ValidationError, field_validator
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    StringConstraints,
+    ValidationError,
+    field_validator,
+)
 from pydantic_core import PydanticCustomError
-from strenum import StrEnum
 from werkzeug.exceptions import BadRequest, UnsupportedMediaType
 
 from api.constants import DATASET_NAME_LIMIT
         raise PydanticCustomError("invalid_UUID1_format", "Invalid UUID1 format")
 
 
-class PermissionEnum(StrEnum):
-    me = auto()
-    team = auto()
-
-
-class ChunkMethodEnum(StrEnum):
-    naive = auto()
-    book = auto()
-    email = auto()
-    laws = auto()
-    manual = auto()
-    one = auto()
-    paper = auto()
-    picture = auto()
-    presentation = auto()
-    qa = auto()
-    table = auto()
-    tag = auto()
-
-
-class GraphragMethodEnum(StrEnum):
-    light = auto()
-    general = auto()
-
-
 class Base(BaseModel):
-    class Config:
-        extra = "forbid"
+    model_config = ConfigDict(extra="forbid", strict=True)
 
 
 class RaptorConfig(Base):
-    use_raptor: bool = Field(default=False)
+    use_raptor: Annotated[bool, Field(default=False)]
     prompt: Annotated[
         str,
         StringConstraints(strip_whitespace=True, min_length=1),
             default="Please summarize the following paragraphs. Be careful with the numbers, do not make things up. Paragraphs as following:\n      {cluster_content}\nThe above is the content you need to summarize."
         ),
     ]
-    max_token: int = Field(default=256, ge=1, le=2048)
-    threshold: float = Field(default=0.1, ge=0.0, le=1.0)
-    max_cluster: int = Field(default=64, ge=1, le=1024)
-    random_seed: int = Field(default=0, ge=0)
+    max_token: Annotated[int, Field(default=256, ge=1, le=2048)]
+    threshold: Annotated[float, Field(default=0.1, ge=0.0, le=1.0)]
+    max_cluster: Annotated[int, Field(default=64, ge=1, le=1024)]
+    random_seed: Annotated[int, Field(default=0, ge=0)]
 
 
 class GraphragConfig(Base):
-    use_graphrag: bool = Field(default=False)
-    entity_types: list[str] = Field(default_factory=lambda: ["organization", "person", "geo", "event", "category"])
-    method: GraphragMethodEnum = Field(default=GraphragMethodEnum.light)
-    community: bool = Field(default=False)
-    resolution: bool = Field(default=False)
+    use_graphrag: Annotated[bool, Field(default=False)]
+    entity_types: Annotated[list[str], Field(default_factory=lambda: ["organization", "person", "geo", "event", "category"])]
+    method: Annotated[Literal["light", "general"], Field(default="light")]
+    community: Annotated[bool, Field(default=False)]
+    resolution: Annotated[bool, Field(default=False)]
 
 
 class ParserConfig(Base):
-    auto_keywords: int = Field(default=0, ge=0, le=32)
-    auto_questions: int = Field(default=0, ge=0, le=10)
-    chunk_token_num: int = Field(default=512, ge=1, le=2048)
-    delimiter: str = Field(default=r"\n", min_length=1)
-    graphrag: GraphragConfig = Field(default_factory=lambda: GraphragConfig(use_graphrag=False))
-    html4excel: bool = False
-    layout_recognize: str = "DeepDOC"
-    raptor: RaptorConfig = Field(default_factory=lambda: RaptorConfig(use_raptor=False))
-    tag_kb_ids: list[str] = Field(default_factory=list)
-    topn_tags: int = Field(default=1, ge=1, le=10)
-    filename_embd_weight: float | None = Field(default=0.1, ge=0.0, le=1.0)
-    task_page_size: int | None = Field(default=None, ge=1)
-    pages: list[list[int]] | None = None
+    auto_keywords: Annotated[int, Field(default=0, ge=0, le=32)]
+    auto_questions: Annotated[int, Field(default=0, ge=0, le=10)]
+    chunk_token_num: Annotated[int, Field(default=512, ge=1, le=2048)]
+    delimiter: Annotated[str, Field(default=r"\n", min_length=1)]
+    graphrag: Annotated[GraphragConfig, Field(default_factory=lambda: GraphragConfig(use_graphrag=False))]
+    html4excel: Annotated[bool, Field(default=False)]
+    layout_recognize: Annotated[str, Field(default="DeepDOC")]
+    raptor: Annotated[RaptorConfig, Field(default_factory=lambda: RaptorConfig(use_raptor=False))]
+    tag_kb_ids: Annotated[list[str], Field(default_factory=list)]
+    topn_tags: Annotated[int, Field(default=1, ge=1, le=10)]
+    filename_embd_weight: Annotated[float | None, Field(default=0.1, ge=0.0, le=1.0)]
+    task_page_size: Annotated[int | None, Field(default=None, ge=1)]
+    pages: Annotated[list[list[int]] | None, Field(default=None)]
 
 
 class CreateDatasetReq(Base):
     name: Annotated[str, StringConstraints(strip_whitespace=True, min_length=1, max_length=DATASET_NAME_LIMIT), Field(...)]
-    avatar: str | None = Field(default=None, max_length=65535)
-    description: str | None = Field(default=None, max_length=65535)
-    embedding_model: str | None = Field(default=None, max_length=255, serialization_alias="embd_id")
-    permission: PermissionEnum = Field(default=PermissionEnum.me, min_length=1, max_length=16)
-    chunk_method: ChunkMethodEnum = Field(default=ChunkMethodEnum.naive, min_length=1, max_length=32, serialization_alias="parser_id")
-    parser_config: ParserConfig | None = Field(default=None)
-
-    @field_validator("avatar")
+    avatar: Annotated[str | None, Field(default=None, max_length=65535)]
+    description: Annotated[str | None, Field(default=None, max_length=65535)]
+    embedding_model: Annotated[str | None, Field(default=None, max_length=255, serialization_alias="embd_id")]
+    permission: Annotated[Literal["me", "team"], Field(default="me", min_length=1, max_length=16)]
+    chunk_method: Annotated[
+        Literal["naive", "book", "email", "laws", "manual", "one", "paper", "picture", "presentation", "qa", "table", "tag"],
+        Field(default="naive", min_length=1, max_length=32, serialization_alias="parser_id"),
+    ]
+    parser_config: Annotated[ParserConfig | None, Field(default=None)]
+
+    @field_validator("avatar", mode="after")
     @classmethod
     def validate_avatar_base64(cls, v: str | None) -> str | None:
         """
     @field_validator("embedding_model", mode="before")
     @classmethod
     def normalize_embedding_model(cls, v: Any) -> Any:
+        """Normalize embedding model string by stripping whitespace"""
         if isinstance(v, str):
             return v.strip()
         return v
                 raise PydanticCustomError("format_invalid", "Model name and provider cannot be whitespace-only strings")
         return v
 
-    @field_validator("permission", mode="before")
-    @classmethod
-    def normalize_permission(cls, v: Any) -> Any:
-        return normalize_str(v)
+    # @field_validator("permission", mode="before")
+    # @classmethod
+    # def normalize_permission(cls, v: Any) -> Any:
+    #     return normalize_str(v)
 
     @field_validator("parser_config", mode="before")
     @classmethod
 
 
 class UpdateDatasetReq(CreateDatasetReq):
-    dataset_id: str = Field(...)
+    dataset_id: Annotated[str, Field(...)]
     name: Annotated[str, StringConstraints(strip_whitespace=True, min_length=1, max_length=DATASET_NAME_LIMIT), Field(default="")]
-    pagerank: int = Field(default=0, ge=0, le=100)
+    pagerank: Annotated[int, Field(default=0, ge=0, le=100)]
 
     @field_validator("dataset_id", mode="before")
     @classmethod
 
 
 class DeleteReq(Base):
-    ids: list[str] | None = Field(...)
+    ids: Annotated[list[str] | None, Field(...)]
 
     @field_validator("ids", mode="after")
     @classmethod
 class DeleteDatasetReq(DeleteReq): ...
 
 
-class OrderByEnum(StrEnum):
-    create_time = auto()
-    update_time = auto()
+class BaseListReq(BaseModel):
+    model_config = ConfigDict(extra="forbid")
 
-
-class BaseListReq(Base):
-    id: str | None = None
-    name: str | None = None
-    page: int = Field(default=1, ge=1)
-    page_size: int = Field(default=30, ge=1)
-    orderby: OrderByEnum = Field(default=OrderByEnum.create_time)
-    desc: bool = Field(default=True)
+    id: Annotated[str | None, Field(default=None)]
+    name: Annotated[str | None, Field(default=None)]
+    page: Annotated[int, Field(default=1, ge=1)]
+    page_size: Annotated[int, Field(default=30, ge=1)]
+    orderby: Annotated[Literal["create_time", "update_time"], Field(default="create_time")]
+    desc: Annotated[bool, Field(default=True)]
 
     @field_validator("id", mode="before")
     @classmethod
     def validate_id(cls, v: Any) -> str:
         return validate_uuid1_hex(v)
 
-    @field_validator("orderby", mode="before")
-    @classmethod
-    def normalize_orderby(cls, v: Any) -> Any:
-        return normalize_str(v)
-
 
 class ListDatasetReq(BaseListReq): ...

test/testcases/test_http_api/test_dataset_mangement/test_create_dataset.py

         [
             ("me", "me"),
             ("team", "team"),
-            ("me_upercase", "ME"),
-            ("team_upercase", "TEAM"),
-            ("whitespace", " ME "),
         ],
-        ids=["me", "team", "me_upercase", "team_upercase", "whitespace"],
+        ids=["me", "team"],
     )
     def test_permission(self, HttpApiAuth, name, permission):
         payload = {"name": name, "permission": permission}
             ("empty", ""),
             ("unknown", "unknown"),
             ("type_error", list()),
+            ("me_upercase", "ME"),
+            ("team_upercase", "TEAM"),
+            ("whitespace", " ME "),
         ],
-        ids=["empty", "unknown", "type_error"],
+        ids=["empty", "unknown", "type_error", "me_upercase", "team_upercase", "whitespace"],
     )
     def test_permission_invalid(self, HttpApiAuth, name, permission):
         payload = {"name": name, "permission": permission}
         [
             ("auto_keywords_min_limit", {"auto_keywords": -1}, "Input should be greater than or equal to 0"),
             ("auto_keywords_max_limit", {"auto_keywords": 33}, "Input should be less than or equal to 32"),
-            ("auto_keywords_float_not_allowed", {"auto_keywords": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("auto_keywords_type_invalid", {"auto_keywords": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("auto_keywords_float_not_allowed", {"auto_keywords": 3.14}, "Input should be a valid integer"),
+            ("auto_keywords_type_invalid", {"auto_keywords": "string"}, "Input should be a valid integer"),
             ("auto_questions_min_limit", {"auto_questions": -1}, "Input should be greater than or equal to 0"),
             ("auto_questions_max_limit", {"auto_questions": 11}, "Input should be less than or equal to 10"),
-            ("auto_questions_float_not_allowed", {"auto_questions": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("auto_questions_type_invalid", {"auto_questions": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("auto_questions_float_not_allowed", {"auto_questions": 3.14}, "Input should be a valid integer"),
+            ("auto_questions_type_invalid", {"auto_questions": "string"}, "Input should be a valid integer"),
             ("chunk_token_num_min_limit", {"chunk_token_num": 0}, "Input should be greater than or equal to 1"),
             ("chunk_token_num_max_limit", {"chunk_token_num": 2049}, "Input should be less than or equal to 2048"),
-            ("chunk_token_num_float_not_allowed", {"chunk_token_num": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("chunk_token_num_type_invalid", {"chunk_token_num": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("chunk_token_num_float_not_allowed", {"chunk_token_num": 3.14}, "Input should be a valid integer"),
+            ("chunk_token_num_type_invalid", {"chunk_token_num": "string"}, "Input should be a valid integer"),
             ("delimiter_empty", {"delimiter": ""}, "String should have at least 1 character"),
-            ("html4excel_type_invalid", {"html4excel": "string"}, "Input should be a valid boolean, unable to interpret input"),
+            ("html4excel_type_invalid", {"html4excel": "string"}, "Input should be a valid boolean"),
             ("tag_kb_ids_not_list", {"tag_kb_ids": "1,2"}, "Input should be a valid list"),
             ("tag_kb_ids_int_in_list", {"tag_kb_ids": [1, 2]}, "Input should be a valid string"),
             ("topn_tags_min_limit", {"topn_tags": 0}, "Input should be greater than or equal to 1"),
             ("topn_tags_max_limit", {"topn_tags": 11}, "Input should be less than or equal to 10"),
-            ("topn_tags_float_not_allowed", {"topn_tags": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("topn_tags_type_invalid", {"topn_tags": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("topn_tags_float_not_allowed", {"topn_tags": 3.14}, "Input should be a valid integer"),
+            ("topn_tags_type_invalid", {"topn_tags": "string"}, "Input should be a valid integer"),
             ("filename_embd_weight_min_limit", {"filename_embd_weight": -1}, "Input should be greater than or equal to 0"),
             ("filename_embd_weight_max_limit", {"filename_embd_weight": 1.1}, "Input should be less than or equal to 1"),
-            ("filename_embd_weight_type_invalid", {"filename_embd_weight": "string"}, "Input should be a valid number, unable to parse string as a number"),
+            ("filename_embd_weight_type_invalid", {"filename_embd_weight": "string"}, "Input should be a valid number"),
             ("task_page_size_min_limit", {"task_page_size": 0}, "Input should be greater than or equal to 1"),
-            ("task_page_size_float_not_allowed", {"task_page_size": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("task_page_size_type_invalid", {"task_page_size": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("task_page_size_float_not_allowed", {"task_page_size": 3.14}, "Input should be a valid integer"),
+            ("task_page_size_type_invalid", {"task_page_size": "string"}, "Input should be a valid integer"),
             ("pages_not_list", {"pages": "1,2"}, "Input should be a valid list"),
             ("pages_not_list_in_list", {"pages": ["1,2"]}, "Input should be a valid list"),
-            ("pages_not_int_list", {"pages": [["string1", "string2"]]}, "Input should be a valid integer, unable to parse string as an integer"),
-            ("graphrag_type_invalid", {"graphrag": {"use_graphrag": "string"}}, "Input should be a valid boolean, unable to interpret input"),
+            ("pages_not_int_list", {"pages": [["string1", "string2"]]}, "Input should be a valid integer"),
+            ("graphrag_type_invalid", {"graphrag": {"use_graphrag": "string"}}, "Input should be a valid boolean"),
             ("graphrag_entity_types_not_list", {"graphrag": {"entity_types": "1,2"}}, "Input should be a valid list"),
             ("graphrag_entity_types_not_str_in_list", {"graphrag": {"entity_types": [1, 2]}}, "nput should be a valid string"),
             ("graphrag_method_unknown", {"graphrag": {"method": "unknown"}}, "Input should be 'light' or 'general'"),
             ("graphrag_method_none", {"graphrag": {"method": None}}, "Input should be 'light' or 'general'"),
-            ("graphrag_community_type_invalid", {"graphrag": {"community": "string"}}, "Input should be a valid boolean, unable to interpret input"),
-            ("graphrag_resolution_type_invalid", {"graphrag": {"resolution": "string"}}, "Input should be a valid boolean, unable to interpret input"),
-            ("raptor_type_invalid", {"raptor": {"use_raptor": "string"}}, "Input should be a valid boolean, unable to interpret input"),
+            ("graphrag_community_type_invalid", {"graphrag": {"community": "string"}}, "Input should be a valid boolean"),
+            ("graphrag_resolution_type_invalid", {"graphrag": {"resolution": "string"}}, "Input should be a valid boolean"),
+            ("raptor_type_invalid", {"raptor": {"use_raptor": "string"}}, "Input should be a valid boolean"),
             ("raptor_prompt_empty", {"raptor": {"prompt": ""}}, "String should have at least 1 character"),
             ("raptor_prompt_space", {"raptor": {"prompt": " "}}, "String should have at least 1 character"),
             ("raptor_max_token_min_limit", {"raptor": {"max_token": 0}}, "Input should be greater than or equal to 1"),
             ("raptor_max_token_max_limit", {"raptor": {"max_token": 2049}}, "Input should be less than or equal to 2048"),
-            ("raptor_max_token_float_not_allowed", {"raptor": {"max_token": 3.14}}, "Input should be a valid integer, got a number with a fractional part"),
-            ("raptor_max_token_type_invalid", {"raptor": {"max_token": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("raptor_max_token_float_not_allowed", {"raptor": {"max_token": 3.14}}, "Input should be a valid integer"),
+            ("raptor_max_token_type_invalid", {"raptor": {"max_token": "string"}}, "Input should be a valid integer"),
             ("raptor_threshold_min_limit", {"raptor": {"threshold": -0.1}}, "Input should be greater than or equal to 0"),
             ("raptor_threshold_max_limit", {"raptor": {"threshold": 1.1}}, "Input should be less than or equal to 1"),
-            ("raptor_threshold_type_invalid", {"raptor": {"threshold": "string"}}, "Input should be a valid number, unable to parse string as a number"),
+            ("raptor_threshold_type_invalid", {"raptor": {"threshold": "string"}}, "Input should be a valid number"),
             ("raptor_max_cluster_min_limit", {"raptor": {"max_cluster": 0}}, "Input should be greater than or equal to 1"),
             ("raptor_max_cluster_max_limit", {"raptor": {"max_cluster": 1025}}, "Input should be less than or equal to 1024"),
-            ("raptor_max_cluster_float_not_allowed", {"raptor": {"max_cluster": 3.14}}, "Input should be a valid integer, got a number with a fractional par"),
-            ("raptor_max_cluster_type_invalid", {"raptor": {"max_cluster": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("raptor_max_cluster_float_not_allowed", {"raptor": {"max_cluster": 3.14}}, "Input should be a valid integer"),
+            ("raptor_max_cluster_type_invalid", {"raptor": {"max_cluster": "string"}}, "Input should be a valid integer"),
             ("raptor_random_seed_min_limit", {"raptor": {"random_seed": -1}}, "Input should be greater than or equal to 0"),
-            ("raptor_random_seed_float_not_allowed", {"raptor": {"random_seed": 3.14}}, "Input should be a valid integer, got a number with a fractional part"),
-            ("raptor_random_seed_type_invalid", {"raptor": {"random_seed": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("raptor_random_seed_float_not_allowed", {"raptor": {"random_seed": 3.14}}, "Input should be a valid integer"),
+            ("raptor_random_seed_type_invalid", {"raptor": {"random_seed": "string"}}, "Input should be a valid integer"),
             ("parser_config_type_invalid", {"delimiter": "a" * 65536}, "Parser config exceeds size limit (max 65,535 characters)"),
         ],
         ids=[

test/testcases/test_http_api/test_dataset_mangement/test_list_datasets.py

         [
             ({"orderby": "create_time"}, lambda r: (is_sorted(r["data"], "create_time", True))),
             ({"orderby": "update_time"}, lambda r: (is_sorted(r["data"], "update_time", True))),
-            ({"orderby": "CREATE_TIME"}, lambda r: (is_sorted(r["data"], "create_time", True))),
-            ({"orderby": "UPDATE_TIME"}, lambda r: (is_sorted(r["data"], "update_time", True))),
-            ({"orderby": " create_time "}, lambda r: (is_sorted(r["data"], "update_time", True))),
         ],
-        ids=["orderby_create_time", "orderby_update_time", "orderby_create_time_upper", "orderby_update_time_upper", "whitespace"],
+        ids=["orderby_create_time", "orderby_update_time"],
     )
     def test_orderby(self, HttpApiAuth, params, assertions):
         res = list_datasets(HttpApiAuth, params)
         [
             {"orderby": ""},
             {"orderby": "unknown"},
+            ({"orderby": "CREATE_TIME"}, lambda r: (is_sorted(r["data"], "create_time", True))),
+            ({"orderby": "UPDATE_TIME"}, lambda r: (is_sorted(r["data"], "update_time", True))),
+            ({"orderby": " create_time "}, lambda r: (is_sorted(r["data"], "update_time", True))),
         ],
-        ids=["empty", "unknown"],
+        ids=["empty", "unknown", "orderby_create_time_upper", "orderby_update_time_upper", "whitespace"],
     )
     def test_orderby_invalid(self, HttpApiAuth, params):
         res = list_datasets(HttpApiAuth, params)

test/testcases/test_http_api/test_dataset_mangement/test_update_dataset.py

         [
             "me",
             "team",
-            "ME",
-            "TEAM",
-            " ME ",
         ],
-        ids=["me", "team", "me_upercase", "team_upercase", "whitespace"],
+        ids=["me", "team"],
     )
     def test_permission(self, HttpApiAuth, add_dataset_func, permission):
         dataset_id = add_dataset_func
             "",
             "unknown",
             list(),
+            "ME",
+            "TEAM",
+            " ME ",
         ],
-        ids=["empty", "unknown", "type_error"],
+        ids=["empty", "unknown", "type_error", "me_upercase", "team_upercase", "whitespace"],
     )
     def test_permission_invalid(self, HttpApiAuth, add_dataset_func, permission):
         dataset_id = add_dataset_func
         [
             ({"auto_keywords": -1}, "Input should be greater than or equal to 0"),
             ({"auto_keywords": 33}, "Input should be less than or equal to 32"),
-            ({"auto_keywords": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"auto_keywords": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"auto_keywords": 3.14}, "Input should be a valid integer"),
+            ({"auto_keywords": "string"}, "Input should be a valid integer"),
             ({"auto_questions": -1}, "Input should be greater than or equal to 0"),
             ({"auto_questions": 11}, "Input should be less than or equal to 10"),
-            ({"auto_questions": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"auto_questions": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"auto_questions": 3.14}, "Input should be a valid integer"),
+            ({"auto_questions": "string"}, "Input should be a valid integer"),
             ({"chunk_token_num": 0}, "Input should be greater than or equal to 1"),
             ({"chunk_token_num": 2049}, "Input should be less than or equal to 2048"),
-            ({"chunk_token_num": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"chunk_token_num": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"chunk_token_num": 3.14}, "Input should be a valid integer"),
+            ({"chunk_token_num": "string"}, "Input should be a valid integer"),
             ({"delimiter": ""}, "String should have at least 1 character"),
-            ({"html4excel": "string"}, "Input should be a valid boolean, unable to interpret input"),
+            ({"html4excel": "string"}, "Input should be a valid boolean"),
             ({"tag_kb_ids": "1,2"}, "Input should be a valid list"),
             ({"tag_kb_ids": [1, 2]}, "Input should be a valid string"),
             ({"topn_tags": 0}, "Input should be greater than or equal to 1"),
             ({"topn_tags": 11}, "Input should be less than or equal to 10"),
-            ({"topn_tags": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"topn_tags": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"topn_tags": 3.14}, "Input should be a valid integer"),
+            ({"topn_tags": "string"}, "Input should be a valid integer"),
             ({"filename_embd_weight": -1}, "Input should be greater than or equal to 0"),
             ({"filename_embd_weight": 1.1}, "Input should be less than or equal to 1"),
-            ({"filename_embd_weight": "string"}, "Input should be a valid number, unable to parse string as a number"),
+            ({"filename_embd_weight": "string"}, "Input should be a valid number"),
             ({"task_page_size": 0}, "Input should be greater than or equal to 1"),
-            ({"task_page_size": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"task_page_size": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"task_page_size": 3.14}, "Input should be a valid integer"),
+            ({"task_page_size": "string"}, "Input should be a valid integer"),
             ({"pages": "1,2"}, "Input should be a valid list"),
             ({"pages": ["1,2"]}, "Input should be a valid list"),
-            ({"pages": [["string1", "string2"]]}, "Input should be a valid integer, unable to parse string as an integer"),
-            ({"graphrag": {"use_graphrag": "string"}}, "Input should be a valid boolean, unable to interpret input"),
+            ({"pages": [["string1", "string2"]]}, "Input should be a valid integer"),
+            ({"graphrag": {"use_graphrag": "string"}}, "Input should be a valid boolean"),
             ({"graphrag": {"entity_types": "1,2"}}, "Input should be a valid list"),
             ({"graphrag": {"entity_types": [1, 2]}}, "nput should be a valid string"),
             ({"graphrag": {"method": "unknown"}}, "Input should be 'light' or 'general'"),
             ({"graphrag": {"method": None}}, "Input should be 'light' or 'general'"),
-            ({"graphrag": {"community": "string"}}, "Input should be a valid boolean, unable to interpret input"),
-            ({"graphrag": {"resolution": "string"}}, "Input should be a valid boolean, unable to interpret input"),
-            ({"raptor": {"use_raptor": "string"}}, "Input should be a valid boolean, unable to interpret input"),
+            ({"graphrag": {"community": "string"}}, "Input should be a valid boolean"),
+            ({"graphrag": {"resolution": "string"}}, "Input should be a valid boolean"),
+            ({"raptor": {"use_raptor": "string"}}, "Input should be a valid boolean"),
             ({"raptor": {"prompt": ""}}, "String should have at least 1 character"),
             ({"raptor": {"prompt": " "}}, "String should have at least 1 character"),
             ({"raptor": {"max_token": 0}}, "Input should be greater than or equal to 1"),
             ({"raptor": {"max_token": 2049}}, "Input should be less than or equal to 2048"),
-            ({"raptor": {"max_token": 3.14}}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"raptor": {"max_token": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"raptor": {"max_token": 3.14}}, "Input should be a valid integer"),
+            ({"raptor": {"max_token": "string"}}, "Input should be a valid integer"),
             ({"raptor": {"threshold": -0.1}}, "Input should be greater than or equal to 0"),
             ({"raptor": {"threshold": 1.1}}, "Input should be less than or equal to 1"),
-            ({"raptor": {"threshold": "string"}}, "Input should be a valid number, unable to parse string as a number"),
+            ({"raptor": {"threshold": "string"}}, "Input should be a valid number"),
             ({"raptor": {"max_cluster": 0}}, "Input should be greater than or equal to 1"),
             ({"raptor": {"max_cluster": 1025}}, "Input should be less than or equal to 1024"),
-            ({"raptor": {"max_cluster": 3.14}}, "Input should be a valid integer, got a number with a fractional par"),
-            ({"raptor": {"max_cluster": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"raptor": {"max_cluster": 3.14}}, "Input should be a valid integer"),
+            ({"raptor": {"max_cluster": "string"}}, "Input should be a valid integer"),
             ({"raptor": {"random_seed": -1}}, "Input should be greater than or equal to 0"),
-            ({"raptor": {"random_seed": 3.14}}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"raptor": {"random_seed": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"raptor": {"random_seed": 3.14}}, "Input should be a valid integer"),
+            ({"raptor": {"random_seed": "string"}}, "Input should be a valid integer"),
             ({"delimiter": "a" * 65536}, "Parser config exceeds size limit (max 65,535 characters)"),
         ],
         ids=[

test/testcases/test_sdk_api/test_dataset_mangement/test_create_dataset.py

         [
             ("me", "me"),
             ("team", "team"),
-            ("me_upercase", "ME"),
-            ("team_upercase", "TEAM"),
-            ("whitespace", " ME "),
         ],
-        ids=["me", "team", "me_upercase", "team_upercase", "whitespace"],
+        ids=["me", "team"],
     )
     def test_permission(self, client, name, permission):
         payload = {"name": name, "permission": permission}
         [
             ("empty", ""),
             ("unknown", "unknown"),
+            ("me_upercase", "ME"),
+            ("team_upercase", "TEAM"),
+            ("whitespace", " ME "),
         ],
-        ids=["empty", "unknown"],
+        ids=["empty", "unknown", "me_upercase", "team_upercase", "whitespace"],
     )
     def test_permission_invalid(self, client, name, permission):
         payload = {"name": name, "permission": permission}
         [
             ("auto_keywords_min_limit", {"auto_keywords": -1}, "Input should be greater than or equal to 0"),
             ("auto_keywords_max_limit", {"auto_keywords": 33}, "Input should be less than or equal to 32"),
-            ("auto_keywords_float_not_allowed", {"auto_keywords": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("auto_keywords_type_invalid", {"auto_keywords": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("auto_keywords_float_not_allowed", {"auto_keywords": 3.14}, "Input should be a valid integer"),
+            ("auto_keywords_type_invalid", {"auto_keywords": "string"}, "Input should be a valid integer"),
             ("auto_questions_min_limit", {"auto_questions": -1}, "Input should be greater than or equal to 0"),
             ("auto_questions_max_limit", {"auto_questions": 11}, "Input should be less than or equal to 10"),
-            ("auto_questions_float_not_allowed", {"auto_questions": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("auto_questions_type_invalid", {"auto_questions": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("auto_questions_float_not_allowed", {"auto_questions": 3.14}, "Input should be a valid integer"),
+            ("auto_questions_type_invalid", {"auto_questions": "string"}, "Input should be a valid integer"),
             ("chunk_token_num_min_limit", {"chunk_token_num": 0}, "Input should be greater than or equal to 1"),
             ("chunk_token_num_max_limit", {"chunk_token_num": 2049}, "Input should be less than or equal to 2048"),
-            ("chunk_token_num_float_not_allowed", {"chunk_token_num": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("chunk_token_num_type_invalid", {"chunk_token_num": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("chunk_token_num_float_not_allowed", {"chunk_token_num": 3.14}, "Input should be a valid integer"),
+            ("chunk_token_num_type_invalid", {"chunk_token_num": "string"}, "Input should be a valid integer"),
             ("delimiter_empty", {"delimiter": ""}, "String should have at least 1 character"),
-            ("html4excel_type_invalid", {"html4excel": "string"}, "Input should be a valid boolean, unable to interpret input"),
+            ("html4excel_type_invalid", {"html4excel": "string"}, "Input should be a valid boolean"),
             ("tag_kb_ids_not_list", {"tag_kb_ids": "1,2"}, "Input should be a valid list"),
             ("tag_kb_ids_int_in_list", {"tag_kb_ids": [1, 2]}, "Input should be a valid string"),
             ("topn_tags_min_limit", {"topn_tags": 0}, "Input should be greater than or equal to 1"),
             ("topn_tags_max_limit", {"topn_tags": 11}, "Input should be less than or equal to 10"),
-            ("topn_tags_float_not_allowed", {"topn_tags": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("topn_tags_type_invalid", {"topn_tags": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("topn_tags_float_not_allowed", {"topn_tags": 3.14}, "Input should be a valid integer"),
+            ("topn_tags_type_invalid", {"topn_tags": "string"}, "Input should be a valid integer"),
             ("filename_embd_weight_min_limit", {"filename_embd_weight": -1}, "Input should be greater than or equal to 0"),
             ("filename_embd_weight_max_limit", {"filename_embd_weight": 1.1}, "Input should be less than or equal to 1"),
-            ("filename_embd_weight_type_invalid", {"filename_embd_weight": "string"}, "Input should be a valid number, unable to parse string as a number"),
+            ("filename_embd_weight_type_invalid", {"filename_embd_weight": "string"}, "Input should be a valid number"),
             ("task_page_size_min_limit", {"task_page_size": 0}, "Input should be greater than or equal to 1"),
-            ("task_page_size_float_not_allowed", {"task_page_size": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ("task_page_size_type_invalid", {"task_page_size": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("task_page_size_float_not_allowed", {"task_page_size": 3.14}, "Input should be a valid integer"),
+            ("task_page_size_type_invalid", {"task_page_size": "string"}, "Input should be a valid integer"),
             ("pages_not_list", {"pages": "1,2"}, "Input should be a valid list"),
             ("pages_not_list_in_list", {"pages": ["1,2"]}, "Input should be a valid list"),
-            ("pages_not_int_list", {"pages": [["string1", "string2"]]}, "Input should be a valid integer, unable to parse string as an integer"),
-            ("graphrag_type_invalid", {"graphrag": {"use_graphrag": "string"}}, "Input should be a valid boolean, unable to interpret input"),
+            ("pages_not_int_list", {"pages": [["string1", "string2"]]}, "Input should be a valid integer"),
+            ("graphrag_type_invalid", {"graphrag": {"use_graphrag": "string"}}, "Input should be a valid boolean"),
             ("graphrag_entity_types_not_list", {"graphrag": {"entity_types": "1,2"}}, "Input should be a valid list"),
             ("graphrag_entity_types_not_str_in_list", {"graphrag": {"entity_types": [1, 2]}}, "nput should be a valid string"),
             ("graphrag_method_unknown", {"graphrag": {"method": "unknown"}}, "Input should be 'light' or 'general'"),
             ("graphrag_method_none", {"graphrag": {"method": None}}, "Input should be 'light' or 'general'"),
-            ("graphrag_community_type_invalid", {"graphrag": {"community": "string"}}, "Input should be a valid boolean, unable to interpret input"),
-            ("graphrag_resolution_type_invalid", {"graphrag": {"resolution": "string"}}, "Input should be a valid boolean, unable to interpret input"),
-            ("raptor_type_invalid", {"raptor": {"use_raptor": "string"}}, "Input should be a valid boolean, unable to interpret input"),
+            ("graphrag_community_type_invalid", {"graphrag": {"community": "string"}}, "Input should be a valid boolean"),
+            ("graphrag_resolution_type_invalid", {"graphrag": {"resolution": "string"}}, "Input should be a valid boolean"),
+            ("raptor_type_invalid", {"raptor": {"use_raptor": "string"}}, "Input should be a valid boolean"),
             ("raptor_prompt_empty", {"raptor": {"prompt": ""}}, "String should have at least 1 character"),
             ("raptor_prompt_space", {"raptor": {"prompt": " "}}, "String should have at least 1 character"),
             ("raptor_max_token_min_limit", {"raptor": {"max_token": 0}}, "Input should be greater than or equal to 1"),
             ("raptor_max_token_max_limit", {"raptor": {"max_token": 2049}}, "Input should be less than or equal to 2048"),
-            ("raptor_max_token_float_not_allowed", {"raptor": {"max_token": 3.14}}, "Input should be a valid integer, got a number with a fractional part"),
-            ("raptor_max_token_type_invalid", {"raptor": {"max_token": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("raptor_max_token_float_not_allowed", {"raptor": {"max_token": 3.14}}, "Input should be a valid integer"),
+            ("raptor_max_token_type_invalid", {"raptor": {"max_token": "string"}}, "Input should be a valid integer"),
             ("raptor_threshold_min_limit", {"raptor": {"threshold": -0.1}}, "Input should be greater than or equal to 0"),
             ("raptor_threshold_max_limit", {"raptor": {"threshold": 1.1}}, "Input should be less than or equal to 1"),
-            ("raptor_threshold_type_invalid", {"raptor": {"threshold": "string"}}, "Input should be a valid number, unable to parse string as a number"),
+            ("raptor_threshold_type_invalid", {"raptor": {"threshold": "string"}}, "Input should be a valid number"),
             ("raptor_max_cluster_min_limit", {"raptor": {"max_cluster": 0}}, "Input should be greater than or equal to 1"),
             ("raptor_max_cluster_max_limit", {"raptor": {"max_cluster": 1025}}, "Input should be less than or equal to 1024"),
-            ("raptor_max_cluster_float_not_allowed", {"raptor": {"max_cluster": 3.14}}, "Input should be a valid integer, got a number with a fractional par"),
-            ("raptor_max_cluster_type_invalid", {"raptor": {"max_cluster": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("raptor_max_cluster_float_not_allowed", {"raptor": {"max_cluster": 3.14}}, "Input should be a valid integer"),
+            ("raptor_max_cluster_type_invalid", {"raptor": {"max_cluster": "string"}}, "Input should be a valid integer"),
             ("raptor_random_seed_min_limit", {"raptor": {"random_seed": -1}}, "Input should be greater than or equal to 0"),
-            ("raptor_random_seed_float_not_allowed", {"raptor": {"random_seed": 3.14}}, "Input should be a valid integer, got a number with a fractional part"),
-            ("raptor_random_seed_type_invalid", {"raptor": {"random_seed": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ("raptor_random_seed_float_not_allowed", {"raptor": {"random_seed": 3.14}}, "Input should be a valid integer"),
+            ("raptor_random_seed_type_invalid", {"raptor": {"random_seed": "string"}}, "Input should be a valid integer"),
             ("parser_config_type_invalid", {"delimiter": "a" * 65536}, "Parser config exceeds size limit (max 65,535 characters)"),
         ],
         ids=[

test/testcases/test_sdk_api/test_dataset_mangement/test_list_datasets.py

         [
             {"orderby": "create_time"},
             {"orderby": "update_time"},
-            {"orderby": "CREATE_TIME"},
-            {"orderby": "UPDATE_TIME"},
-            {"orderby": " create_time "},
         ],
-        ids=["orderby_create_time", "orderby_update_time", "orderby_create_time_upper", "orderby_update_time_upper", "whitespace"],
+        ids=["orderby_create_time", "orderby_update_time"],
     )
     def test_orderby(self, client, params):
         client.list_datasets(**params)
         [
             {"orderby": ""},
             {"orderby": "unknown"},
+            {"orderby": "CREATE_TIME"},
+            {"orderby": "UPDATE_TIME"},
+            {"orderby": " create_time "},
         ],
-        ids=["empty", "unknown"],
+        ids=["empty", "unknown", "orderby_create_time_upper", "orderby_update_time_upper", "whitespace"],
     )
     def test_orderby_invalid(self, client, params):
         with pytest.raises(Exception) as excinfo:

test/testcases/test_sdk_api/test_dataset_mangement/test_update_dataset.py

         [
             "me",
             "team",
-            "ME",
-            "TEAM",
-            " ME ",
         ],
-        ids=["me", "team", "me_upercase", "team_upercase", "whitespace"],
+        ids=["me", "team"],
     )
     def test_permission(self, client, add_dataset_func, permission):
         dataset = add_dataset_func
             "",
             "unknown",
             list(),
+            "ME",
+            "TEAM",
+            " ME ",
         ],
-        ids=["empty", "unknown", "type_error"],
+        ids=["empty", "unknown", "type_error", "me_upercase", "team_upercase", "whitespace"],
     )
     def test_permission_invalid(self, add_dataset_func, permission):
         dataset = add_dataset_func
         [
             ({"auto_keywords": -1}, "Input should be greater than or equal to 0"),
             ({"auto_keywords": 33}, "Input should be less than or equal to 32"),
-            ({"auto_keywords": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"auto_keywords": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"auto_keywords": 3.14}, "Input should be a valid integer"),
+            ({"auto_keywords": "string"}, "Input should be a valid integer"),
             ({"auto_questions": -1}, "Input should be greater than or equal to 0"),
             ({"auto_questions": 11}, "Input should be less than or equal to 10"),
-            ({"auto_questions": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"auto_questions": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"auto_questions": 3.14}, "Input should be a valid integer"),
+            ({"auto_questions": "string"}, "Input should be a valid integer"),
             ({"chunk_token_num": 0}, "Input should be greater than or equal to 1"),
             ({"chunk_token_num": 2049}, "Input should be less than or equal to 2048"),
-            ({"chunk_token_num": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"chunk_token_num": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"chunk_token_num": 3.14}, "Input should be a valid integer"),
+            ({"chunk_token_num": "string"}, "Input should be a valid integer"),
             ({"delimiter": ""}, "String should have at least 1 character"),
-            ({"html4excel": "string"}, "Input should be a valid boolean, unable to interpret input"),
+            ({"html4excel": "string"}, "Input should be a valid boolean"),
             ({"tag_kb_ids": "1,2"}, "Input should be a valid list"),
             ({"tag_kb_ids": [1, 2]}, "Input should be a valid string"),
             ({"topn_tags": 0}, "Input should be greater than or equal to 1"),
             ({"topn_tags": 11}, "Input should be less than or equal to 10"),
-            ({"topn_tags": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"topn_tags": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"topn_tags": 3.14}, "Input should be a valid integer"),
+            ({"topn_tags": "string"}, "Input should be a valid integer"),
             ({"filename_embd_weight": -1}, "Input should be greater than or equal to 0"),
             ({"filename_embd_weight": 1.1}, "Input should be less than or equal to 1"),
-            ({"filename_embd_weight": "string"}, "Input should be a valid number, unable to parse string as a number"),
+            ({"filename_embd_weight": "string"}, "Input should be a valid number"),
             ({"task_page_size": 0}, "Input should be greater than or equal to 1"),
-            ({"task_page_size": 3.14}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"task_page_size": "string"}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"task_page_size": 3.14}, "Input should be a valid integer"),
+            ({"task_page_size": "string"}, "Input should be a valid integer"),
             ({"pages": "1,2"}, "Input should be a valid list"),
             ({"pages": ["1,2"]}, "Input should be a valid list"),
-            ({"pages": [["string1", "string2"]]}, "Input should be a valid integer, unable to parse string as an integer"),
-            ({"graphrag": {"use_graphrag": "string"}}, "Input should be a valid boolean, unable to interpret input"),
+            ({"pages": [["string1", "string2"]]}, "Input should be a valid integer"),
+            ({"graphrag": {"use_graphrag": "string"}}, "Input should be a valid boolean"),
             ({"graphrag": {"entity_types": "1,2"}}, "Input should be a valid list"),
             ({"graphrag": {"entity_types": [1, 2]}}, "nput should be a valid string"),
             ({"graphrag": {"method": "unknown"}}, "Input should be 'light' or 'general'"),
             ({"graphrag": {"method": None}}, "Input should be 'light' or 'general'"),
-            ({"graphrag": {"community": "string"}}, "Input should be a valid boolean, unable to interpret input"),
-            ({"graphrag": {"resolution": "string"}}, "Input should be a valid boolean, unable to interpret input"),
-            ({"raptor": {"use_raptor": "string"}}, "Input should be a valid boolean, unable to interpret input"),
+            ({"graphrag": {"community": "string"}}, "Input should be a valid boolean"),
+            ({"graphrag": {"resolution": "string"}}, "Input should be a valid boolean"),
+            ({"raptor": {"use_raptor": "string"}}, "Input should be a valid boolean"),
             ({"raptor": {"prompt": ""}}, "String should have at least 1 character"),
             ({"raptor": {"prompt": " "}}, "String should have at least 1 character"),
             ({"raptor": {"max_token": 0}}, "Input should be greater than or equal to 1"),
             ({"raptor": {"max_token": 2049}}, "Input should be less than or equal to 2048"),
-            ({"raptor": {"max_token": 3.14}}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"raptor": {"max_token": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"raptor": {"max_token": 3.14}}, "Input should be a valid integer"),
+            ({"raptor": {"max_token": "string"}}, "Input should be a valid integer"),
             ({"raptor": {"threshold": -0.1}}, "Input should be greater than or equal to 0"),
             ({"raptor": {"threshold": 1.1}}, "Input should be less than or equal to 1"),
-            ({"raptor": {"threshold": "string"}}, "Input should be a valid number, unable to parse string as a number"),
+            ({"raptor": {"threshold": "string"}}, "Input should be a valid number"),
             ({"raptor": {"max_cluster": 0}}, "Input should be greater than or equal to 1"),
             ({"raptor": {"max_cluster": 1025}}, "Input should be less than or equal to 1024"),
-            ({"raptor": {"max_cluster": 3.14}}, "Input should be a valid integer, got a number with a fractional par"),
-            ({"raptor": {"max_cluster": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"raptor": {"max_cluster": 3.14}}, "Input should be a valid integer"),
+            ({"raptor": {"max_cluster": "string"}}, "Input should be a valid integer"),
             ({"raptor": {"random_seed": -1}}, "Input should be greater than or equal to 0"),
-            ({"raptor": {"random_seed": 3.14}}, "Input should be a valid integer, got a number with a fractional part"),
-            ({"raptor": {"random_seed": "string"}}, "Input should be a valid integer, unable to parse string as an integer"),
+            ({"raptor": {"random_seed": 3.14}}, "Input should be a valid integer"),
+            ({"raptor": {"random_seed": "string"}}, "Input should be a valid integer"),
             ({"delimiter": "a" * 65536}, "Parser config exceeds size limit (max 65,535 characters)"),
         ],
         ids=[