Agent

The Agent class provides an easy to use interface to language models.

Example

agent.py
from phi.agent import Agent

agent = Agent(description="You help people with their health and fitness goals.")

# -*- Print a response
agent.print_response('Share a quick healthy breakfast recipe.', markdown=True)

# -*- Get the response as a string
response = agent.run('Share a quick healthy breakfast recipe.', stream=False)

# -*- Get the response as a stream
response = ""
for delta in agent.run('Share a quick healthy breakfast recipe.'):
    response += delta

Agent Params

Parameter	Type	Default	Description
`model`	`Optional[Model]`	`None`	Model to use for this Agent (alias: "provider")
`name`	`Optional[str]`	`None`	Agent name
`agent_id`	`Optional[str]`	`None`	Agent UUID (autogenerated if not set)
`agent_data`	`Optional[Dict[str, Any]]`	`None`	Metadata associated with this agent
`introduction`	`Optional[str]`	`None`	Agent introduction. This is added to the chat history when a run is started.
`user_id`	`Optional[str]`	`None`	ID of the user interacting with this agent
`user_data`	`Optional[Dict[str, Any]]`	`None`	Metadata associated with the user interacting with this agent
`session_id`	`Optional[str]`	`None`	Session UUID (autogenerated if not set)
`session_name`	`Optional[str]`	`None`	Session name
`session_data`	`Optional[Dict[str, Any]]`	`None`	Metadata associated with this session
`memory`	`AgentMemory`	`AgentMemory()`	Agent Memory
`add_history_to_messages`	`bool`	`False`	Add chat history to the messages sent to the Model. (alias: "add_chat_history_to_messages")
`num_history_responses`	`int`	`3`	Number of historical responses to add to the messages.
`knowledge`	`Optional[AgentKnowledge]`	`None`	Agent Knowledge (alias: "knowledge_base")
`add_context`	`bool`	`False`	Enable RAG by adding context from AgentKnowledge to the user prompt.
`retriever`	`Optional[Callable[..., Optional[list[dict]]]]`	`None`	Function to get context to add to the user_message
`context_format`	`Literal["json", "yaml"]`	`"json"`	Format of the context
`add_context_instructions`	`bool`	`False`	If True, add instructions for using the context to the system prompt
`storage`	`Optional[AgentStorage]`	`None`	Agent Storage
`tools`	`Optional[List[Union[Tool, Toolkit, Callable, Dict, Function]]]`	`None`	A list of tools provided to the Model.
`show_tool_calls`	`bool`	`False`	Show tool calls in Agent response.
`tool_call_limit`	`Optional[int]`	`None`	Maximum number of tool calls allowed.
`tool_choice`	`Optional[Union[str, Dict[str, Any]]]`	`None`	Controls which (if any) tool is called by the model.
`reasoning`	`bool`	`False`	Enable reasoning by working through the problem step by step.
`reasoning_model`	`Optional[Model]`	`None`	Model to use for reasoning
`reasoning_agent`	`Optional[Agent]`	`None`	Agent to use for reasoning
`reasoning_min_steps`	`int`	`1`	Minimum number of reasoning steps
`reasoning_max_steps`	`int`	`10`	Maximum number of reasoning steps
`read_chat_history`	`bool`	`False`	Add a tool that allows the Model to read the chat history.
`search_knowledge`	`bool`	`True`	Add a tool that allows the Model to search the knowledge base (aka Agentic RAG)
`update_knowledge`	`bool`	`False`	Add a tool that allows the Model to update the knowledge base.
`read_tool_call_history`	`bool`	`False`	Add a tool that allows the Model to get the tool call history.
`add_messages`	`Optional[List[Union[Dict, Message]]]`	`None`	A list of extra messages added after the system message and before the user message.
`system_prompt`	`Optional[str]`	`None`	System prompt: provide the system prompt as a string
`system_prompt_template`	`Optional[PromptTemplate]`	`None`	System prompt template: provide the system prompt as a PromptTemplate
`use_default_system_message`	`bool`	`True`	If True, build a default system message using agent settings and use that
`system_message_role`	`str`	`"system"`	Role for the system message
`description`	`Optional[str]`	`None`	A description of the Agent that is added to the start of the system message.
`task`	`Optional[str]`	`None`	The task the agent should achieve.
`instructions`	`Optional[List[str]]`	`None`	List of instructions for the agent.
`guidelines`	`Optional[List[str]]`	`None`	List of guidelines for the agent.
`expected_output`	`Optional[str]`	`None`	Provide the expected output from the Agent.
`additional_context`	`Optional[str]`	`None`	Additional context added to the end of the system message.
`prevent_hallucinations`	`bool`	`False`	If True, add instructions to return "I dont know" when the agent does not know the answer.
`prevent_prompt_leakage`	`bool`	`False`	If True, add instructions to prevent prompt leakage
`limit_tool_access`	`bool`	`False`	If True, add instructions for limiting tool access to the default system prompt if tools are provided
`markdown`	`bool`	`False`	If markdown=true, add instructions to format the output using markdown
`add_name_to_instructions`	`bool`	`False`	If True, add the agent name to the instructions
`add_datetime_to_instructions`	`bool`	`False`	If True, add the current datetime to the instructions to give the agent a sense of time
`user_prompt`	`Optional[Union[List, Dict, str]]`	`None`	User prompt: provide the user prompt as a string
`user_prompt_template`	`Optional[PromptTemplate]`	`None`	User prompt template: provide the user prompt as a PromptTemplate
`use_default_user_message`	`bool`	`True`	If True, build a default user prompt using references and chat history
`user_message_role`	`str`	`"user"`	Role for the user message
`response_model`	`Optional[Type[BaseModel]]`	`None`	Provide a response model to get the response as a Pydantic model (alias: "output_model")
`parse_response`	`bool`	`True`	If True, the response from the Model is converted into the response_model
`structured_outputs`	`bool`	`False`	Use the structured_outputs from the Model if available
`save_response_to_file`	`Optional[str]`	`None`	Save the response to a file
`team`	`Optional[List["Agent"]]`	`None`	An Agent can have a team of agents that it can transfer tasks to.
`role`	`Optional[str]`	`None`	When the agent is part of a team, this is the role of the agent in the team
`add_transfer_instructions`	`bool`	`True`	Add instructions for transferring tasks to team members
`debug_mode`	`bool`	`False`	debug_mode=True enables debug logs
`monitoring`	`bool`	`False`	monitoring=True logs Agent information to phidata.app for monitoring
`telemetry`	`bool`	`True`	telemetry=True logs minimal telemetry for analytics

Building Blocks

Command Line

Example

Agent Params

Building Blocks

Command Line

​Example

​Agent Params

Example

Agent Params