Charlie Yang

I came up with same idea and when you post this, I was having my breakfast.

Scenario for batch processor in neural search document ingestion: Since OpenSearch 2.7, ml-commons released its remote connector, allowing opensearch to connect with remote inference endpoint. However, ml-commons can take a...

> Thanks @gaobinlong > > > @reta , could you also help to take a look at this RFC, thanks! > > @msfroh @model-collapse @chishui I think the idea of...

@reta What is your estimation where the circuit breaking will happen? If you mean it will happen in side the batch processor's own process, that could be, because it is...

Hi, @ramda1234786 can you elaborate more on how to reproduce?

I am going to pick this PR up right now, @br3no @reuschling sorry for the late reply. Let me check your code first. @br3no could you kindly rebase your code...

> two phase search in theory should benefit all BM25 based search, right? But looks like this RFC is specific for sparse neural? Not so confident on this, two phase...

Seems you are trying to add prompts for text embedding right? Here is my thought. 1, It is tough to deploy GPT based LLM inside opensearch cluster since we don't...

@br3no does my reply solve your problem? If yes, this issue will be closed.

@br3no @reuschling if possible, let's book a video meeting to talk about this. You can reach me in the public slack channel. The name is Charlie Yang.