autogen.tools.experimental.WebSearchPreviewTool

WebSearchPreviewTool

WebSearchPreviewTool(
    *,
    llm_config: LLMConfig | dict[str, Any],
    search_context_size: Literal['low', 'medium', 'high'] = 'medium',
    user_location: dict[str, str] | None = None,
    instructions: str | None = None,
    text_format: Type[BaseModel] | None = None
)

WebSearchPreviewTool is a tool that uses OpenAI’s web_search_preview tool to perform a search.
Initialize the WebSearchPreviewTool.

Parameters:

Name	Description
llm_config	Type: LLMConfig | dict[str, typing.Any]
search_context_size	Type: Literal[‘low’, ‘medium’, ‘high’] Default: ‘medium’
user_location	Type: dict[str, str] | None Default: None
instructions	Type: str | None Default: None
text_format	Type: Type[pydantic.main.BaseModel] | None Default: None

Instance Attributes

description

func

function_schema

Get the schema for the function.
This is the old way of handling function calls with OpenAI and compatible frameworks.
It is provided for backward compatibility.

name

realtime_tool_schema

Get the schema for the tool.
This is the preferred way of handling function calls with OpeaAI and compatible frameworks.

tool_schema

Get the schema for the tool.
This is the preferred way of handling function calls with OpeaAI and compatible frameworks.

Instance Methods

register_for_execution

register_for_execution(self, agent: ConversableAgent) -> 

Registers the tool for direct execution by a ConversableAgent.
This method registers the tool so that it can be executed by the agent, typically outside of the context of an LLM interaction.

Parameters:

Name	Description
agent	The agent to which the tool will be registered. Type: ConversableAgent

register_for_llm

register_for_llm(self, agent: ConversableAgent) -> 

Registers the tool for use with a ConversableAgent’s language model (LLM).
This method registers the tool so that it can be invoked by the agent during interactions with the language model.

Parameters:

Name	Description
agent	The agent to which the tool will be registered. Type: ConversableAgent

register_tool

register_tool(self, agent: ConversableAgent) -> 

Register a tool to be both proposed and executed by an agent.
Equivalent to calling both register_for_llm and register_for_execution with the same agent.
Note: This will not make the agent recommend and execute the call in the one step. If the agent recommends the tool, it will need to be the next agent to speak in order to execute the tool.

Parameters:

Name	Description
agent	The agent to which the tool will be registered. Type: ConversableAgent