Marco Minerva

I have understood, so at least we need something like this, right? https://stackoverflow.com/a/73358042/1728189

Hi @dluc! Finally, I can return to this issue. What do you think if we start implementing also in RabbitMQ the same behavior we have in Azure Queues? https://github.com/microsoft/kernel-memory/blob/8c0ad8c144c5b9b2b8f1fa0de72ba54e2aa723a0/extensions/AzureQueues/AzureQueuesPipeline.cs#L192-L231

Yes. I can start, for example, creating the extra queues and then making a draft PR, so you can see the work in progress. Do you agree?

Actually, adding poison queues support like in Azure Queues has required a smaller amount of changes than I thought, so I have make a single PR with all the changes:...

I was thinking about a generic `FailureReason` property because in this way we can centralize all the failures handling, even if the handler does not explicitly set the **LogEntries**, for...

I have tried to put my idea in a PR: https://github.com/microsoft/kernel-memory/pull/443. So, you can see if it is the approach you're thinking about.

I think that you can support this scenario when the issue https://github.com/microsoft/kernel-memory/issues/379 will be completed (currently there is a PR in preview). With that, you will be able to inject...

Thank you @dluc for the answer. Now I'm experimenting some weird situations in which a question that had a similarity of 0.79 with `text-embedding-ada-002`, now has only 0.33 with `text-embedding-3-small`...

Yes, chunks are the same. The text is relevant as `text-embedding-ada-002` says. For example, among the others I have a chunk (about 1000 tokens) that contains something like "and near...

You can use it with this third-party extension: https://github.com/kbeaugrand/SemanticKernel.Connectors.Memory.SqlServer. You can find an example of its integration in my GitHub repository at https://github.com/marcominerva/OpenAIEmbeddingSample.