Richi
Richi
I currently have the same issue using self hosted gpt-oss over vllm with multiple mcp servers. Merging the PR would be great! I am ready to help.
@vblagoje How to proceed? What about adding MistralChatGenerator to the whitelist. And a whitelist for embedders that share a base class?
After merge of #2497 its done
@vblagoje Its a honor. However I am quite busy currently. Nonetheless lets talk about it. Whats in your mind about a rebase? From my POV just special components missing cost...
@vblagoje I checked the Langfuse SDK - they already use heuristics in _parse_usage() to handle different formats. For embeddings specifically, they detect it by checking if usage has only 2...
@vblagoje After #2522 I am capable of this.
@vblagoje I solved it locally. The changes are in #2522. Errors work out of the box, whereas "WARNING" and "DEBUG" can be set manually.
@shimmyshimmer Hey, I unfortunaetly dont understand. I had an identation error in my pull request, for which reason you needed to revert it. However @ccyjava fixed the reverted pr. Currently...
The issue in psycopg has been closed. However would it be an option to encode default special chars? It was a very nasty bug for me and I would prevent...