Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

docs: improve LLMCallStartedEvent docstring to clarify multimodal support

Devin AIe3dde17af0e0
diff --git a/src/crewai/utilities/events/llm_events.py b/src/crewai/utilities/events/llm_events.py
index 10a648e86..b92072340 100644
--- a/src/crewai/utilities/events/llm_events.py
+++ b/src/crewai/utilities/events/llm_events.py
@@ -12,7 +12,12 @@ class LLMCallType(Enum):
class LLMCallStartedEvent(CrewEvent):
- """Event emitted when a LLM call starts"""
+ """Event emitted when a LLM call starts
+
+ Attributes:
+ messages: Content can be either a string or a list of dictionaries that support
+ multimodal content (text, images, etc.)
+ """
type: str = "llm_call_started"
messages: Union[str, List[Dict[str, Any]]]