Jiaping(JP) Zhang

Ya I think this feature will be a great integration with another project - https://github.com/alexanderatallah/window.ai

Since the base LLM model is LLaMA, it seems it's not permitted for commercial use, right? Have you thought of fine-tuning on top of Open-LLaMA/ Dolly/ StableLM instead?

Any update on supporting 3.10?

This is really important because it hinders the ability to experiment on the colab platform since it only allows to use python3.10... Hope someone looks into this issue soon.

Ya it would be great to fix this issue soon if possible!

It seems like it could be a nice extension to implement in the `split_` function. I have a few more question about the re-training process. For the retraining using the...

@massquantity Another question, since for the ranking task with implicit data which only contains positive examples, how can we still get the learned embedding for those items that are not...

Hmm I thought the model can still infer the embeddings for the new or long-tail items if we pass the features that are generalizable across the item/user set.. since the...

> I was not able to upload any files in my ChatbotUI while hosting my models locally with Ollama. I found out that the variable embeddingsProvider in app/api/retrieval/process/route.ts initialized in...

> Is there any way you can tell which Executor is causing the error? Perhaps commenting them out of the Flow one by one until the error disappears/appears? > >...