Jacob M.

It seemed to work for me! Thanks!

One follow up question - what's the best way to report correctness/success of the experiment by these labels? Right now, I found docs that point me to this:

import phoenix as px
client = px.Client()

# Get the current dataset version
dataset = client.get_dataset(id="...", version_id="...")

df = dataset.as_dataframe()

df.head()

experiment = client.get_experiment(experiment_id="...")

Amazing! Thank you. 😊

Figured it out. Since I'm running experiments/evaluations, the traces are being stored in the dataset experiment run and not in the "traces" views within the web UI. It could be helpful to add that disclaimer somewhere in the documentation. 🙂 Thanks again for all of the support! We made it through! 🎉

Not working either. I refactored my code to be function-based vs. a class as well. Still not working. There must be some config I'm not seeing.

Or it's the fact that I'm running it in a class.

Even the manual traces aren't working. It must be something small that's wrong with my setup. 😭

Thanks for all of your help trying to debug this!!!!!! 🙏🏼

Unfortunately, that didn't work. So, going the manual span route. I've already spent too long on trying to get the automatic route to work.