Javier Martinez
Javier Martinez
We need more information about your setup (machine, profile, examples, etc) to help you :)
Fixed in last `main` version :)
Keep calm guys :) Talking of the original post, if you read the server response error, you'll know that you've tried to send more tokens than your model supports by...
Can you try to reclone in another folder? It's very rare issue
@BenBatsir You can't add this line to `Dockerfile.external`, as it is something you need to run on the `ollama` container. In this situation, I have three ideas on how to...
First of all, can you pull new changes? We've updated Qdrant dependencies :) Talking about Qdrant cloud topic, I've used a couple days ago without bugs. It seems like you...
Glad to heard about evaluation. You can start looking at `llamaindex` integration: https://docs.ragas.io/en/stable/howtos/integrations/llamaindex.html If you check the doc, you will see that you can already use llamaindex on datasets to...
Can you try again? I just try with last changes, and it's working as expected
Currently, by default, we use the sentence division as you have said. We have chosen this way because several articles have commented that it is the simplest but one of...
By default, I would say almost no. It is very difficult to find a general solution to solve all the problems. Anyway, we have on the roadmap to move to...