Nicolas Herment
Nicolas Herment
I tested with node 0.6.3 and Alain's fix work. I didn't tried or even looked into the backward compatibility though...
Hi, Is there a ETA on this merge ? Is the project still in active development ? Thanks, - Nicolas
@emanuelet I'm going through this and trying to reproduce your issue but it would be of great help if you could provide a fully working example. As Matteo mentioned, the...
@sourabhbhandari and @zrks, 0.10.5 is out and should solve this issue. Can you please confirm?
@lightme16 what version of holmes are you using?
I suspect Holmes already support this as litellm accepts the `AZURE_AD_TOKEN` en var for the AD token. This is documented here for Azure: https://docs.robusta.dev/master/configuration/ai-analysis.html#azure-ai I will double check (likely tomorrow)...
Hi @thoraxe , Can you try this branch: https://github.com/robusta-dev/holmesgpt/pull/210/files ? There are 2 main changes: - Holmes no longer intercepts and blocks litellm calls even if litellm.validate() call fails. This...
Indeed LiteLLM does not support not having a ad_token. This should be fixed in an upcoming change: https://github.com/BerriAI/litellm/issues/6790. We will revisit support for this once litellm releases the fix. In...
Hi @balzat , this has been added to the main branch. It will be part of the next release `0.19.0`
I can confirm this. Installing v1.31.8 is a workaround for now: `pip install litellm[proxy]==1.31.8` Likely this bug was introduced in `1.31.9`