Blake R

> > Also, the visibility in the docs is not correct, some yaml parts were hidden. I had to look into the raw file. > > @blakerosenthal , perhaps another...

Hey folks, I'm getting up to speed with the codebase and am noticing we don't have any tests in `tests/deploy/ui`. Would this be a good issue to start filling those...

I lean towards option 2 as well: history at the chat level, maybe to default to True for all chats via the persistent config or during startup at the CLI...

It looks like Langchain creates a special input type that is a combination of prompt + message_history, then builds a [history-aware retriever](https://api.python.langchain.com/en/latest/_modules/langchain/chains/history_aware_retriever.html#create_history_aware_retriever) that further rephrases the prompt using the history...

> The current case would have only a single item in there, whereas with chat history we would have multiple entries. If we go for this implementation, we also need...

> Aren't the start and end of the sentence contradict each other? If we have the history at the chat level, we cannot have it globally set either through the...

@pmeier Can I close this?

> ... just run > > https://github.com/Quansight/ragna/blob/0cb205f24ca9fb322ac32a2e1aaec6b34928cd2e/ragna/deploy/_cli/core.py#L100-L101 > > directly. I'm not 100% sure this works, but it should. I will try this and see what happens. I think I...

@pmeier (cc @pierrotsmnrd) Running into a bit of a snag running the two servers in the test env. The tests running in CI are experiencing timeouts waiting for the server...

@pmeier This is ready for another look. Video from failing playwright tests is now [uploaded as an artifact](https://github.com/Quansight/ragna/actions/runs/9322199554). Waiting half a second before clicking "start conversation" seems to resolve all...