WebSearchPreviewTool - AG2

WebSearchPreviewTool

`autogen.tools.experimental.WebSearchPreviewTool`

WebSearchPreviewTool(*, llm_config, search_context_size='medium', user_location=None, instructions=None, text_format=None)

Bases: Tool

WebSearchPreviewTool is a tool that uses OpenAI's web_search_preview tool to perform a search.

Initialize the WebSearchPreviewTool.

PARAMETER	DESCRIPTION
`llm_config`	The LLM configuration to use. This should be a dictionary containing the model name and other parameters. TYPE:`LLMConfig
`search_context_size`	The size of the search context. One of `low`, `medium`, or `high`. `medium` is the default. TYPE:`Literal['low', 'medium', 'high']`DEFAULT:`'medium'`
`user_location`	The location of the user. This should be a dictionary containing the city, country, region, and timezone. TYPE:`dict[str, str]
`instructions`	Inserts a system (or developer) message as the first item in the model's context. TYPE:`str
`text_format`	The format of the text to be returned. This should be a subclass of `BaseModel`. The default is `None`, which means the text will be returned as a string. TYPE:`type[BaseModel]

Source code in autogen/tools/experimental/web_search_preview/web_search_preview.py

`name property`

name

`description property`

description

`func property`

func

`tool_schema property`

tool_schema

Get the schema for the tool.

`function_schema property`

function_schema

Get the schema for the function.

`realtime_tool_schema property`

realtime_tool_schema

Get the schema for the tool.

`web_search_tool_param instance-attribute`

web_search_tool_param = WebSearchToolParam(type='web_search_preview', search_context_size=search_context_size, user_location=UserLocation(**user_location) if user_location else None)

`instructions instance-attribute`

instructions = instructions

`text_format instance-attribute`

text_format = text_format

`model instance-attribute`

model = None

`api_key instance-attribute`

api_key = None

`register_for_llm`

register_for_llm(agent)

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.

PARAMETER	DESCRIPTION
`agent`	The agent to which the tool will be registered. TYPE:`ConversableAgent`

Source code in autogen/tools/tool.py

`register_for_execution`

register_for_execution(agent)

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.

PARAMETER	DESCRIPTION
`agent`	The agent to which the tool will be registered. TYPE:`ConversableAgent`

Source code in autogen/tools/tool.py

`register_tool`

register_tool(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.

PARAMETER	DESCRIPTION
`agent`	The agent to which the tool will be registered. TYPE:`ConversableAgent`

Source code in autogen/tools/tool.py