Agents#

This page presents all APIs and classes related to Agents in PyAgentSpec.

Agent class#

class pyagentspec.agent.Agent(*, id=<factory>, name, description=None, metadata=<factory>, min_agentspec_version=AgentSpecVersionEnum.v25_4_1, max_agentspec_version=AgentSpecVersionEnum.v25_4_1, inputs=None, outputs=None, llm_config, system_prompt, tools=<factory>)#

Bases: AgenticComponent

An agent is a component that can do several rounds of conversation to solve a task.

It can be executed by itself, or be executed in a flow using an AgentNode.

Examples

>>> from pyagentspec.agent import Agent
>>> from pyagentspec.property import Property
>>> expertise_property=Property(
...     json_schema={"title": "domain_of_expertise", "type": "string"}
... )
>>> system_prompt = '''You are an expert in {{domain_of_expertise}}.
... Please help the users with their requests.'''
>>> agent = Agent(
...     name="Adaptive expert agent",
...     system_prompt=system_prompt,
...     llm_config=llm_config,
...     inputs=[expertise_property],
... )
Parameters:

  • id (str) – A unique identifier for this Component

  • name (str) – Name of this Component

  • description (str | None) – Optional description of this Component

  • metadata (Dict[str, Any] | None) – Optional, additional metadata related to this Component

  • min_agentspec_version (AgentSpecVersionEnum) –

  • max_agentspec_version (AgentSpecVersionEnum) –

  • inputs (List[Property] | None) – List of inputs accepted by this component

  • outputs (List[Property] | None) – List of outputs exposed by this component

  • llm_config (LlmConfig) – Configuration of the LLM to use for this Agent

  • system_prompt (str) – Initial system prompt used for the initialization of the agent’s context

  • tools (List[Tool]) – List of tools that the agent can use to fulfil user requests

On this page