[Frontend] Automatic detection of chat content format from AST (#9919)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/entrypoints/openai/protocol.py

@@ -5,9 +5,8 @@ from argparse import Namespace
 from typing import Any, Dict, List, Literal, Optional, Union
 
 import torch
-from openai.types.chat import ChatCompletionContentPartParam
 from pydantic import BaseModel, ConfigDict, Field, model_validator
-from typing_extensions import Annotated, Required, TypedDict
+from typing_extensions import Annotated
 
 from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
 from vllm.pooling_params import PoolingParams
@@ -35,26 +34,6 @@ assert _LONG_INFO.min == _MOCK_LONG_INFO.min
 assert _LONG_INFO.max == _MOCK_LONG_INFO.max
 
 
-class CustomChatCompletionMessageParam(TypedDict, total=False):
-    """Enables custom roles in the Chat Completion API."""
-    role: Required[str]
-    """The role of the message's author."""
-
-    content: Union[str, List[ChatCompletionContentPartParam]]
-    """The contents of the message."""
-
-    name: str
-    """An optional name for the participant.
-
-    Provides the model information to differentiate between participants of the
-    same role.
-    """
-
-    tool_call_id: Optional[str]
-
-    tool_calls: Optional[List[dict]]
-
-
 class OpenAIBaseModel(BaseModel):
     # OpenAI API does not allow extra fields
     model_config = ConfigDict(extra="forbid")
@@ -1054,16 +1033,56 @@ class TokenizeCompletionRequest(OpenAIBaseModel):
     model: str
     prompt: str
 
-    add_special_tokens: bool = Field(default=True)
+    add_special_tokens: bool = Field(
+        default=True,
+        description=(
+            "If true (the default), special tokens (e.g. BOS) will be added to "
+            "the prompt."),
+    )
 
 
 class TokenizeChatRequest(OpenAIBaseModel):
     model: str
     messages: List[ChatCompletionMessageParam]
 
-    add_generation_prompt: bool = Field(default=True)
-    continue_final_message: bool = Field(default=False)
-    add_special_tokens: bool = Field(default=False)
+    add_generation_prompt: bool = Field(
+        default=True,
+        description=
+        ("If true, the generation prompt will be added to the chat template. "
+         "This is a parameter used by chat template in tokenizer config of the "
+         "model."),
+    )
+    continue_final_message: bool = Field(
+        default=False,
+        description=
+        ("If this is set, the chat will be formatted so that the final "
+         "message in the chat is open-ended, without any EOS tokens. The "
+         "model will continue this message rather than starting a new one. "
+         "This allows you to \"prefill\" part of the model's response for it. "
+         "Cannot be used at the same time as `add_generation_prompt`."),
+    )
+    add_special_tokens: bool = Field(
+        default=False,
+        description=(
+            "If true, special tokens (e.g. BOS) will be added to the prompt "
+            "on top of what is added by the chat template. "
+            "For most models, the chat template takes care of adding the "
+            "special tokens so this should be set to false (as is the "
+            "default)."),
+    )
+    chat_template: Optional[str] = Field(
+        default=None,
+        description=(
+            "A Jinja template to use for this conversion. "
+            "As of transformers v4.44, default chat template is no longer "
+            "allowed, so you must provide a chat template if the tokenizer "
+            "does not define one."),
+    )
+    chat_template_kwargs: Optional[Dict[str, Any]] = Field(
+        default=None,
+        description=("Additional kwargs to pass to the template renderer. "
+                     "Will be accessible by the chat template."),
+    )
 
     @model_validator(mode="before")
     @classmethod