Monitor and interact with the Plexe model building process through callbacks and logging.
Callback
base class defines four key methods that are triggered at different points:
on_build_start(info)
: Called once when model.build()
beginson_iteration_start(info)
: Called at the start of each build iterationon_iteration_end(info)
: Called at the end of each build iterationon_build_end(info)
: Called once when the entire build process completesinfo
parameter provides context about the current state, including:
on_iteration_end
)chain_of_thought=True
in model.build()
. It captures the
detailed reasoning steps and decision-making process of the AI agents.
Callback
:
chain_of_thought=True
to see what’s happening