类class
agentscope.modelParameters
class Parameters(BaseModel)源码Source
agentscope/model/_moonshot/_model.py:29–73参数，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 Moonshot AI 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 | `thinking_enable` 字段。 | Field(default=False, title='Thinking', description='Whether to enable thinking mode. For kimi-k2-thinking, thinking is always enabled. For kimi-k2.6, thinking is enabled by default but can be disabled.') |
reasoning_effort | Literal['low', 'high', 'max'] | None | `reasoning_effort` 字段。 | Field(default=None, title='Reasoning Effort', description="The reasoning effort level for kimi-k3. Supports 'low', 'high', and 'max' (default 'max').") |
temperature | float | None | `temperature` 字段。 | Field(default=None, title='Temperature', description='The temperature for the LLM output.', ge=0, le=1) |
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/_moonshot/_model.py:32thinking_enable
bool = Field(default=False, title='Thinking', description='Whether to enable thinking mode. For kimi-k2-thinking, thinking is always enabled. For kimi-k2.6, thinking is enabled by default but can be disabled.')thinking_enable 字段。声明为 bool。
Whether to enable thinking mode.
源码Source
agentscope/model/_moonshot/_model.py:39reasoning_effort
Literal['low', 'high', 'max'] | None = Field(default=None, title='Reasoning Effort', description="The reasoning effort level for kimi-k3. Supports 'low', 'high', and 'max' (default 'max').")reasoning_effort 字段。声明为 Literal['low', 'high', 'max'] | None。
The reasoning effort level for kimi-k3.
源码Source
agentscope/model/_moonshot/_model.py:49temperature
float | None = Field(default=None, title='Temperature', description='The temperature for the LLM output.', ge=0, le=1)temperature 字段。声明为 float | None。
The temperature for the LLM output.
源码Source
agentscope/model/_moonshot/_model.py:59top_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/_moonshot/_model.py:67