Eero Tamminen

> With OPEA we do not prescribe use of a model nor vector database or even which version of OPEA release. For an air-gapped deployment, a priori all desired models...

> The current version check for `3.0.0+` fails to handle cases where protoc is above version `3.0.0` but does not start with a `3`, for example protoc may have a...

Please add link(s) to PRs actually implementing this feature.

I noticed one problem with the refined documents. List for further READMEs point to directories, not to the READMEs in them. See e.g: https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA#deployment-options => `#readme` suffix should be added...

> It would be great to file a Github issue @joshuayao see https://github.com/opea-project/GenAIExamples/issues/1885.

Regarding CI fail, I don't think vLLM used for embeddings yet, in which case this would be unrelated to vLLM update: ``` + echo '[ mega-codegen ] HTTP status is...

This is more of a reminder to include note of the related improvements to releases including them. Michael tracks this project release notes, so he may do another Phoronix test...

> I am proud to share that our upstream software stack now supports Direct Submission on BMG. More information about performance here -> https://www.phoronix.com/review/intel-b580-opencl-january Wow, that's great improvement, from worst...

> If such a project fetches Level Zero repo Is there any such a project, and why it would do that, instead of using L0 normally? > then its build...

Marking as draft, until also manually tested.