[Frontend][3/n] Make pooling entrypoints request schema consensus | EmbedRequest & ClassifyRequest (#32905)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-01-23 12:03:44 +00:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 3f3f89529d
commit 05f3d714db
11 changed files with 330 additions and 265 deletions
+8 -69
View File
@@ -7,92 +7,31 @@ from pydantic import (
Field,
)
from vllm import PoolingParams
from vllm.entrypoints.openai.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.entrypoints.pooling.base.protocol import (
ChatRequestMixin,
CompletionRequestMixin,
EmbedRequestMixin,
PoolingBasicRequestMixin,
)
from vllm.utils import random_uuid
from vllm.utils.serial_utils import EmbedDType, EncodingFormat, Endianness
class EmbeddingCompletionRequest(PoolingBasicRequestMixin, CompletionRequestMixin):
class EmbeddingCompletionRequest(
PoolingBasicRequestMixin, CompletionRequestMixin, EmbedRequestMixin
):
# Ordered by official OpenAI API documentation
# https://platform.openai.com/docs/api-reference/embeddings
encoding_format: EncodingFormat = "float"
dimensions: int | None = None
# --8<-- [start:embedding-extra-params]
normalize: bool | None = Field(
default=None,
description="Whether to normalize the embeddings outputs. Default is True.",
)
embed_dtype: EmbedDType = Field(
default="float32",
description=(
"What dtype to use for encoding. Default to using float32 for base64 "
"encoding to match the OpenAI python client behavior. "
"This parameter will affect base64 and binary_response."
),
)
endianness: Endianness = Field(
default="native",
description=(
"What endianness to use for encoding. Default to using native for "
"base64 encoding to match the OpenAI python client behavior."
"This parameter will affect base64 and binary_response."
),
)
# --8<-- [end:embedding-extra-params]
def to_pooling_params(self):
return PoolingParams(
dimensions=self.dimensions,
use_activation=self.normalize,
truncate_prompt_tokens=self.truncate_prompt_tokens,
)
pass
class EmbeddingChatRequest(PoolingBasicRequestMixin, ChatRequestMixin):
encoding_format: EncodingFormat = "float"
dimensions: int | None = None
# --8<-- [start:chat-embedding-extra-params]
class EmbeddingChatRequest(
PoolingBasicRequestMixin, ChatRequestMixin, EmbedRequestMixin
):
mm_processor_kwargs: dict[str, Any] | None = Field(
default=None,
description=("Additional kwargs to pass to the HF processor."),
)
normalize: bool | None = Field(
default=None,
description="Whether to normalize the embeddings outputs. Default is True.",
)
embed_dtype: EmbedDType = Field(
default="float32",
description=(
"What dtype to use for encoding. Default to using float32 for base64 "
"encoding to match the OpenAI python client behavior. "
"This parameter will affect base64 and binary_response."
),
)
endianness: Endianness = Field(
default="native",
description=(
"What endianness to use for encoding. Default to using native for "
"base64 encoding to match the OpenAI python client behavior."
"This parameter will affect base64 and binary_response."
),
)
# --8<-- [end:chat-embedding-extra-params]
def to_pooling_params(self):
return PoolingParams(
truncate_prompt_tokens=self.truncate_prompt_tokens,
dimensions=self.dimensions,
use_activation=self.normalize,
)
EmbeddingRequest: TypeAlias = EmbeddingCompletionRequest | EmbeddingChatRequest