run
step signifies the execution of an agent or a chain that takes multiple steps. Unlike other step types, it does not have to be part of a Thread.
This is useful if you are monitoring non conversational use cases.
message
step represents a message exchange within a Thread. There are two primary subtypes of message steps:
tool
step is used to document interactions with external tools or services. This step type is particularly useful for applications that interact with external APIs, databases, or services.
llm
step is used to document interactions with large language models (LLMs). This step type is particularly useful for applications that leverage AI models, such as GPT-3, for generating responses, content, or performing analysis.
Output on the platform