[Frontend][2/n] Make pooling entrypoints request schema consensus | ChatRequest (#32574)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-01-22 10:32:44 +00:00
committed by GitHub
parent 64e3d67ac0
commit 328cbb2773
24 changed files with 456 additions and 205 deletions
+2 -59
View File
@@ -5,13 +5,12 @@ from typing import Any, TypeAlias
from pydantic import (
Field,
model_validator,
)
from vllm import PoolingParams
from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
from vllm.entrypoints.openai.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.entrypoints.pooling.base.protocol import (
ChatRequestMixin,
CompletionRequestMixin,
PoolingBasicRequestMixin,
)
@@ -57,57 +56,11 @@ class EmbeddingCompletionRequest(PoolingBasicRequestMixin, CompletionRequestMixi
)
class EmbeddingChatRequest(PoolingBasicRequestMixin):
messages: list[ChatCompletionMessageParam]
class EmbeddingChatRequest(PoolingBasicRequestMixin, ChatRequestMixin):
encoding_format: EncodingFormat = "float"
dimensions: int | None = None
# --8<-- [start:chat-embedding-extra-params]
add_generation_prompt: bool = Field(
default=False,
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: str | None = 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: dict[str, Any] | None = Field(
default=None,
description=(
"Additional keyword args to pass to the template renderer. "
"Will be accessible by the chat template."
),
)
mm_processor_kwargs: dict[str, Any] | None = Field(
default=None,
description=("Additional kwargs to pass to the HF processor."),
@@ -134,16 +87,6 @@ class EmbeddingChatRequest(PoolingBasicRequestMixin):
)
# --8<-- [end:chat-embedding-extra-params]
@model_validator(mode="before")
@classmethod
def check_generation_prompt(cls, data):
if data.get("continue_final_message") and data.get("add_generation_prompt"):
raise ValueError(
"Cannot set both `continue_final_message` and "
"`add_generation_prompt` to True."
)
return data
def to_pooling_params(self):
return PoolingParams(
truncate_prompt_tokens=self.truncate_prompt_tokens,