Verbose Tracing Output in Autogen-Agents with Phoenix: Is It Normal?
I'm trying to use autogen-agents with phoenix, the tracing output looks really verbose, is that expected?
I'm trying to use autogen-agents with phoenix, the tracing output looks really verbose, is that expected?
also attached the script
馃挕聽Hint: Mention RunLLM in the thread for followups.
By verbosity, I mean why are there so many traces, most of them with some IDs appended, the content feels hard to read. So you mean the verbosity isn't expected?
Can you check if your termination conditions are working as expected?
Yeah, it does seem working as expected. Here is a diff run of the same script, and the last assistant does say APPROVE at the end, e.g.
btw, I'm not very familiar with autogen yet, but I learned that phoenix with autoinstrument can be quite a useful tool to understand how these agent frameworks works under the hood, so I'm trying out autogen + phoenix to get a sense of how autogen works.
-