Welcome to the PersonaAgent documentation!
PersonaAgent enables AG2 (AutoGen) agents to embody distinct personas through explicit role
, goal
, and backstory
components, allowing for more authentic and consistent agent behavior.
pip install ag2-persona
from ag2_persona import PersonaBuilder
# Create an expert agent using PersonaBuilder
expert = (PersonaBuilder.from_markdown("library/data_analyst.md")
.set_name("data_analyst")
.llm_config({"model": "gpt-4", "temperature": 0.7})
.build())
# Use like any AG2 agent
response = expert.generate_reply(messages=[{"content": "Analyze this data"}])