Mark Pollack

When we review the overall organization of response objects multiple AI models (not just openai) we will revisit this.

so we closed the [PR](https://github.com/spring-projects/spring-ai/pull/21) due to the implementation not being based on the mongodb vector search offering. So now closing the issue.

https://python.langchain.com/docs/modules/data_connection/retrievers/parent_document_retriever as a reference. I'd like to have some RAG evaluation setup in place to better understand how things improve or not based on these types of algorithms. Putting in...

Hi thanks, glad our paths cross again. There is a long list of every model types, let alone whatever happens with multi-modal support within a single model, that we should...

Closing as it as been merged. Docs will follow shortly.

The work from https://github.com/spring-projects-experimental/spring-ai/pull/80 should be reviewed in addition to the above links.

We may consider putting is a small WIP under a 'sandbox' or 'samples' project directory that is not distributed as a maven artifact for 0.8.0

Yes, this is the case Thomas. Closing

I think the testing of the vector stores is rather anemic , we sort of trust they implemented it right, but with the same data we are using, it is...

I see your point, contains is better than assuming it would be first, but for now, I think we can spend time more effectevly on other areas. Should issues come...