Abram

> > > The input for this span is totally wrong. Let's look at how [others](https://github.com/BerriAI/litellm/blob/deb87f71e330dcaf56574a477d9457d589754cd3/litellm/integrations/langfuse.py) process the data from litellm and copy it ( a note here, everyone seems...

Closing this issue as completed will resolve the second issue addressed https://github.com/Agenta-AI/agenta/issues/1196.

Hi @Arshil-Akkala, Are you using the latest version of agenta to serve the variant? If not, please try upgrading with this command: ```bash pip install agenta --upgrade ``` If the...

> Hey @aybruhm, >  > got another one, so while running it each time I should add these into `requirements.txt`, any other alternative we have to make the changes...

> That the Trace has a usage of 293 although no usage is returned.. I can't reproduce this, @mmabrouk. For me, I get the usage (total, completion and prompt tokens):...

> @israelvictory87 this has been fixed in the litellm PR, no? > > Correct.

> Hello @mmabrouk . Is this issue open ? If yes, I would like to work on it again. I've previously fixed similar issues in agenta and would love to...

@mmabrouk I can't seem to reproduce the bug on my local host and cloud beta. I just tested it on cloud prod and it also works.

Got it! Thank you for the video demonstration.

Am I missing something, @MohammedMaaz? 🤔 https://github.com/Agenta-AI/agenta/assets/55067204/b76a0cb1-2199-4b34-a4da-f91401f1ab40