Jeff MAURY

I woujld add that RAG recipes would need: - an additional embedding model to start from We may also add a datastore from which the embeddings will be computed but...

> @slemeur @jeffmaury can you please confirm that the earlier comments in this ticket are still valid and elaborate some more on the exact requirements? Who is the user and...

> @jeffmaury can you please help me understand, who is is the user, who wants to connect their vector db and what are they doing? It could be in a...

Such metrics are not exposed in a standard manner. We could expose the number of token processed (prompt and response) in addition to the elasped time that is already displayed

For the tokens number we can get it from the JSON payload For extra information we need to find a way to get it that is not llama cpp specific

Upstream PR: https://github.com/abetlen/llama-cpp-python/pull/1552

User download a file, import it into AI Lab, removes it from AI Lab => no more file on user's disk

> Personally I think we should provide the ability for extensions to extend details pages with extra tabs using webviews, and things like this, image checker, etc could be provided...

> We do not display a difference icon between downloaded and remote as we are using the status to indicate if the model is being used or not. > >...

> What about these 2 options on the left for the downloaded models?  White background = downloaded green bullet = in use ?