类class
agentscope.modelParameters
class Parameters(BaseModel)源码Source
agentscope/model/_openai_chat/_model.py:41–109参数用于 OpenAI 聊天模型。位于 agentscope.model 包。
The parameters for the OpenAI 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 reasoning for reasoning models (e.g. o3, o4-mini, gpt-5.5). Use reasoning_effort to control the depth of reasoning.') |
reasoning_effort | Literal['none', 'minimal', 'low', 'medium', 'high', 'xhigh'] | None | `reasoning_effort` 字段。 | Field(default=None, title='Reasoning Effort', description='Controls the depth of reasoning for reasoning models (e.g. o3, o4-mini, gpt-5.5). Supported values are model-dependent and may include: none, minimal, low, medium, high, xhigh.') |
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) |
parallel_tool_calls | bool | `parallel_tool_calls` 字段。 | Field(default=True, title='Parallel Tool Calls', description='Whether to enable parallel tool calls.') |
voice | str | None | 语音字段。 | Field(default=None, title='Voice', description="Voice for audio output on omni-style models (e.g. ``gpt-audio-mini``). Setting this implicitly asks the model to speak its response — ``modalities`` is filled in automatically. Supported voices vary by model — see the model card's ``voice.suggestions``. Any value the API accepts works — the suggestions are convenience-only. Leave unset for text-only responses.") |
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/_openai_chat/_model.py:44thinking_enable
bool = Field(default=False, title='Thinking', description='Whether to enable reasoning for reasoning models (e.g. o3, o4-mini, gpt-5.5). Use reasoning_effort to control the depth of reasoning.')thinking_enable 字段。声明为 bool。
Whether to enable reasoning for reasoning models (e.g.
源码Source
agentscope/model/_openai_chat/_model.py:51reasoning_effort
Literal['none', 'minimal', 'low', 'medium', 'high', 'xhigh'] | None = Field(default=None, title='Reasoning Effort', description='Controls the depth of reasoning for reasoning models (e.g. o3, o4-mini, gpt-5.5). Supported values are model-dependent and may include: none, minimal, low, medium, high, xhigh.')reasoning_effort 字段。声明为 Literal['none', 'minimal', 'low', 'medium', 'high', 'xhigh'] | None。
Controls the depth of reasoning for reasoning models (e.g.
源码Source
agentscope/model/_openai_chat/_model.py:61temperature
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/_openai_chat/_model.py:74top_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/_openai_chat/_model.py:82parallel_tool_calls
bool = Field(default=True, title='Parallel Tool Calls', description='Whether to enable parallel tool calls.')parallel_tool_calls 字段。声明为 bool。
Whether to enable parallel tool calls.
源码Source
agentscope/model/_openai_chat/_model.py:90voice
str | None = Field(default=None, title='Voice', description="Voice for audio output on omni-style models (e.g. ``gpt-audio-mini``). Setting this implicitly asks the model to speak its response — ``modalities`` is filled in automatically. Supported voices vary by model — see the model card's ``voice.suggestions``. Any value the API accepts works — the suggestions are convenience-only. Leave unset for text-only responses.")语音字段。声明为 str | None。
Voice for audio output on omni-style models (e.g.
源码Source
agentscope/model/_openai_chat/_model.py:96