Tools
Tavily
Example
The following assistant will run a search on Tavily for “language models” and print the response.
cookbook/tools/tavily_tools.py
from phi.assistant import Assistant
from phi.tools.tavily import TavilyTools
assistant = Assistant(tools=[TavilyTools()], show_tool_calls=True)
assistant.print_response("Search tavily for 'language models'", markdown=True)
Toolkit Params
api_key
str
The API key used for authentication to access the service.
search
bool
default: "True"Determines whether search functionality is enabled.
max_tokens
int
default: "6000"The maximum number of tokens to use in operations.
include_answer
bool
default: "True"Specifies if the answer should be included in the response.
search_depth
Literal['basic', 'advanced']
default: "advanced"Defines the depth of search, either ‘basic’ or ‘advanced’.
format
Literal['json', 'markdown']
default: "markdown"The format of the output, either ‘json’ or ‘markdown’.
use_search_context
bool
default: "False"Indicates if the search should consider the context provided in the request.
Toolkit Functions
web_search_using_tavily
This function uses the Tavily API to provide realtime online information about the query.