Luis Novo
Luis Novo
I can send you the full ofx in pvt if you prefer.
Thank you all for following up on this. New version resolves it for good.
This should be fixed now. Pushed the vectorization to be a background task, running chunks individually and implementing a proper retry mechanism for failures. Please give it a shot.
Some great points there.. you can already to the System Prompt part with the notebook description, although not especifically, it works. But I'll consider the other stuff.. Good suggestions nevertheless.
Can you confirm this happens even after you load the model to memory? Like second, third messages too?
Thanks. Can you also provide some logs for the container? Perhaps there is something interesting to help point to the root of the issue.
Maintainers, here is a start for the fix. Didn't have time to test, but should be on the right path: https://github.com/souzatharsis/podcastfy/pull/257
It's been built as we speak for new front-end. How do you envision selecting documents for context? Let the LLM decide or specify doc ids?
Hey everyone, thanks for putting an effort into this. I really appreciate it. But, instead of just having people enter API Keys, we need to go a step further. I...
Yes, will work on it