[Misc] Use VLLMValidationError in batch, pooling, and tokenize protocol validators (#36256)

Signed-off-by: umut-polat <52835619+umut-polat@users.noreply.github.com>

vllm/entrypoints/openai/run_batch.py

@@ -54,6 +54,7 @@ from vllm.entrypoints.pooling.score.protocol import (
     ScoreResponse,
 )
 from vllm.entrypoints.utils import create_error_response
+from vllm.exceptions import VLLMValidationError
 from vllm.logger import init_logger
 from vllm.reasoning import ReasoningParserManager
 from vllm.utils import random_uuid
@@ -86,9 +87,10 @@ class BatchTranscriptionRequest(TranscriptionRequest):
     def validate_no_file(cls, data: Any):
         """Ensure file field is not provided in batch requests."""
         if isinstance(data, dict) and "file" in data:
-            raise ValueError(
+            raise VLLMValidationError(
                 "The 'file' field is not supported in batch requests. "
-                "Use 'file_url' instead."
+                "Use 'file_url' instead.",
+                parameter="file",
             )
         return data
 
@@ -116,9 +118,10 @@ class BatchTranslationRequest(TranslationRequest):
     def validate_no_file(cls, data: Any):
         """Ensure file field is not provided in batch requests."""
         if isinstance(data, dict) and "file" in data:
-            raise ValueError(
+            raise VLLMValidationError(
                 "The 'file' field is not supported in batch requests. "
-                "Use 'file_url' instead."
+                "Use 'file_url' instead.",
+                parameter="file",
             )
         return data
 

vllm/entrypoints/pooling/base/protocol.py

@@ -11,6 +11,7 @@ from vllm.entrypoints.chat_utils import (
     ChatTemplateContentFormatOption,
 )
 from vllm.entrypoints.openai.engine.protocol import OpenAIBaseModel
+from vllm.exceptions import VLLMValidationError
 from vllm.renderers import ChatParams, merge_kwargs
 from vllm.utils import random_uuid
 from vllm.utils.serial_utils import EmbedDType, EncodingFormat, Endianness
@@ -147,9 +148,9 @@ class ChatRequestMixin(OpenAIBaseModel):
     @classmethod
     def check_generation_prompt(cls, data):
         if data.get("continue_final_message") and data.get("add_generation_prompt"):
-            raise ValueError(
+            raise VLLMValidationError(
                 "Cannot set both `continue_final_message` and "
-                "`add_generation_prompt` to True."
+                "`add_generation_prompt` to True.",
             )
         return data
 

vllm/entrypoints/serve/tokenize/protocol.py

@@ -17,6 +17,7 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
 from vllm.entrypoints.openai.engine.protocol import (
     OpenAIBaseModel,
 )
+from vllm.exceptions import VLLMValidationError
 from vllm.renderers import ChatParams, TokenizeParams, merge_kwargs
 
 
@@ -120,9 +121,9 @@ class TokenizeChatRequest(OpenAIBaseModel):
     @classmethod
     def check_generation_prompt(cls, data):
         if data.get("continue_final_message") and data.get("add_generation_prompt"):
-            raise ValueError(
+            raise VLLMValidationError(
                 "Cannot set both `continue_final_message` and "
-                "`add_generation_prompt` to True."
+                "`add_generation_prompt` to True.",
             )
         return data