Skip to content

vllm.entrypoints.pooling.scoring.typing

Classes:

ScoreMultiModalParam

Bases: TypedDict

A specialized parameter type for scoring multimodal content

The reasons why don't reuse CustomChatCompletionMessageParam directly: 1. Score tasks don't need the 'role' field (user/assistant/system) that's required in chat completions 2. Including chat-specific fields would confuse users about their purpose in scoring 3. This is a more focused interface that only exposes what's needed for scoring

Attributes:

Source code in vllm/entrypoints/pooling/scoring/typing.py 
23
24
25
26
27
28
29
30
31
32
33
34
class ScoreMultiModalParam(TypedDict, total=False):
    """
    A specialized parameter type for scoring multimodal content

    The reasons why don't reuse `CustomChatCompletionMessageParam` directly:
    1. Score tasks don't need the 'role' field (user/assistant/system) that's required in chat completions
    2. Including chat-specific fields would confuse users about their purpose in scoring
    3. This is a more focused interface that only exposes what's needed for scoring
    """  # noqa: E501

    content: Required[list[ScoreContentPartParam]]
    """The multimodal contents"""

content instance-attribute

The multimodal contents