tigerinus
tigerinus
I will try that notebook. However our frontend is written in VueJS. Would be nice to have an example code in JS. If we call `/stream` directly we see the...
@eyurtsev I have no idea how to get the notebook example working for my app: I tried ```python from langchain.prompts.chat import ChatPromptTemplate from langserve import RemoteRunnable llm = RemoteRunnable('http://localhost:8000') prompt...
It is by design or a bug that ConversationalRetrievalChain doesn't support streaming?
For this error: ``` [ 65.063369] __vm_enough_memory: pid: 1000, comm: nvc:[driver], no enough memory for the allocation ``` Try enabling full support of memory overcommit: ```shell sysctl -w vm.overcommit_memory=1 ```
Would be nice to support `ResponseEntity
@ndeloof thanks for looking into this. I am writing a tool, which you can think of a frontend wrapper of docker compose. Part of the feature is to show the...
@ndeloof - please see my PR.
> Hi, may I ask how do you load the model, in my case with single GPU I also had that problem and I had to use `disable_exllama=True` while loading...
@anlek - We will be looking into this in future iteration. Currently CasaOS depends on container labelling heavily, so exposing label editing is a bit risky. But we will see.
It's such a shame that I haven't got to understand [how Traefik works](https://doc.traefik.io/traefik/getting-started/quick-start/) until recently... It's definitely a big plus to CasaOS. Seriously looking into this...