类class agentscope.model

Parameters

class Parameters(BaseModel)

源码Source agentscope/model/_volcengine/_model.py:30–75

参数，与模型服务通信并返回生成或向量化结果。位于 agentscope.model 包。

The parameters for the Volcengine Ark chat model. Declared in agentscope.model.

属性摘要Attribute Summary

属性Attribute	类型Type	说明Description	值Value
`max_tokens`	int \| None	最大令牌数字段。	`Field(default=None, title='Max Tokens', description='The maximum number of tokens for the LLM output.', gt=0)`
`thinking_enable`	bool \| None	`thinking_enable` 字段。	`Field(default=None, title='Thinking', description='Whether to enable or disable thinking mode. When unset, Ark uses its default auto mode.')`
`reasoning_effort`	Literal['minimal', 'low', 'medium', 'high'] \| None	`reasoning_effort` 字段。	`Field(default=None, title='Reasoning Effort', description='Controls the depth of reasoning in thinking mode. Supported values are minimal, low, medium, and high. The minimal level disables reasoning.')`
`temperature`	float \| None	`temperature` 字段。	`Field(default=None, title='Temperature', description='The temperature for the LLM output.', ge=0, le=2)`
`top_p`	float \| None	`top_p` 字段。	`Field(default=None, title='Top P', description='The top P value for the LLM output.', gt=0, le=1)`

属性详情Attribute Detail

max_tokens

int | None = Field(default=None, title='Max Tokens', description='The maximum number of tokens for the LLM output.', gt=0)

最大令牌数字段。声明为 int | None。

The maximum number of tokens for the LLM output.

源码Source agentscope/model/_volcengine/_model.py:33

thinking_enable

bool | None = Field(default=None, title='Thinking', description='Whether to enable or disable thinking mode. When unset, Ark uses its default auto mode.')

thinking_enable 字段。声明为 bool | None。

Whether to enable or disable thinking mode.

源码Source agentscope/model/_volcengine/_model.py:40

reasoning_effort

Literal['minimal', 'low', 'medium', 'high'] | None = Field(default=None, title='Reasoning Effort', description='Controls the depth of reasoning in thinking mode. Supported values are minimal, low, medium, and high. The minimal level disables reasoning.')

reasoning_effort 字段。声明为 Literal['minimal', 'low', 'medium', 'high'] | None。

Controls the depth of reasoning in thinking mode.

源码Source agentscope/model/_volcengine/_model.py:49

temperature

float | None = Field(default=None, title='Temperature', description='The temperature for the LLM output.', ge=0, le=2)

temperature 字段。声明为 float | None。

The temperature for the LLM output.

源码Source agentscope/model/_volcengine/_model.py:61

top_p

float | None = Field(default=None, title='Top P', description='The top P value for the LLM output.', gt=0, le=1)

top_p 字段。声明为 float | None。

The top P value for the LLM output.

源码Source agentscope/model/_volcengine/_model.py:69