Agent¶
::: agenticai_core.designtime.models.agent.Agent options: show_root_heading: true show_source: false members_order: source
AgentMeta¶
::: agenticai_core.designtime.models.agent.AgentMeta options: show_root_heading: true show_source: false
AgentConfig¶
::: agenticai_core.designtime.models.agent.AgentConfig options: show_root_heading: true show_source: false
AgentConfigBuilder¶
::: agenticai_core.designtime.models.agent.AgentConfigBuilder options: show_root_heading: true show_source: false show_if_no_docstring: true show_signature: true show_signature_annotations: true filters: - "!^_" # Hide private methods but show public ones
Supporting Classes¶
Communication¶
::: agenticai_core.designtime.models.agent.Communication options: show_root_heading: true
CommunicationType¶
::: agenticai_core.designtime.models.agent.CommunicationType options: show_root_heading: true
Endpoint¶
::: agenticai_core.designtime.models.agent.Endpoint options: show_root_heading: true
ResponseRoutingMode¶
::: agenticai_core.designtime.models.agent.ResponseRoutingMode options: show_root_heading: true
Usage Examples¶
Creating a Basic Agent¶
from agenticai_core.designtime.models.agent import Agent
from agenticai_core.designtime.models.llm_model import LlmModel, LlmModelConfig
from agenticai_core.designtime.models.prompt import Prompt
from agenticai_core.designtime.models.tool import Tool
agent = Agent(
name="FinanceAssist",
description="Banking assistant for account management",
role="WORKER",
sub_type="REACT",
type="AUTONOMOUS",
llm_model=LlmModel(
model="gpt-4o",
provider="Open AI",
connection_name="Default Connection",
modelConfig=LlmModelConfig(
temperature=0.7,
max_tokens=1600
)
),
prompt=Prompt(
system="You are a helpful banking assistant.",
custom="Assist with account inquiries and transactions."
),
tools=[
Tool(name="Get_Balance", type="inlineTool", ...)
]
)
Using Builder Pattern¶
from agenticai_core.designtime.models.agent import AgentConfigBuilder
agent_dict = AgentConfigBuilder() \
.set_name("CustomerService") \
.set_description("Customer service agent") \
.set_role("WORKER") \
.set_sub_type("REACT") \
.set_type("AUTONOMOUS") \
.set_llm_model(llm_model) \
.set_prompt(prompt) \
.set_tools([tool1, tool2]) \
.build()
agent = Agent(**agent_dict)
Converting to AgentMeta¶
# Convert full Agent to lightweight AgentMeta
agent_meta = agent.to_agent_meta()
# Use in orchestrator registration
app_agents = [agent.to_agent_meta() for agent in agents]