HRUSHIKESH DOKALA
HRUSHIKESH DOKALA
@cbrzn, we are enhancing Autogen support for non openai models, feel free to check the roadmap #2946 . thanks
@wireless90 sorry for the issue, but we dont support NeuroengineClient, please do check out the blog on how to register a custom model client at https://microsoft.github.io/autogen/blog/2024/01/26/Custom-Models/
> Thanks. Do you think we can close this and revisit the idea once the new version is merged? It can be part of `agbench` Sure @ekzhu , we can...
thanks for the contribution @marklysze , looks great!!
> > Hi @marklysze ! I tried to run Ollama without litellm. I copied the url "http://localhost:11434" in browser and it shows 'ollama is running'. I followed the step and...
@gamercoder153 use can also leverage the loggers to make this possible. give that a try if it works for the usecase
looks good to me👍, thanks for the efforts @marklysze
hey @qingyun-wu, im picking this up, with help of @randombet, will post the updates soon.
> Thanks. How about adding the test into the contrib-openai CI? can you please mention if it is for the ReasoningAgent or for the Benchmark? fyi: the ci tests for...
> I've tested with Anthropic, Gemini, DeepSeek, committed a summary file. > > [See here](https://github.com/ag2ai/ag2/blob/7232dbbbe1ff36084fe77164835d376963f44437/benchmark/simple-bench/2025-01-02-Results.md). > > The strongest results are from Anthropic (and Anthropic's chat UI scored the highest)....