Yi Ding

Results 11 comments of Yi Ding

I agree with Logan here that 2K is too small for many RAG applications. In fact, we should be going higher to 8K for Llama 3 and 64K for Mixtral...

> cc @Disiok > > looks pretty good to me! > > @yisding could you add a unit test in `tests/readers/test_json.py`? If that's too tricky no worries. at the very...

> Seems like a good idea to me! > > > I still have to test this. One thing I'm not 100% sure about is how well the embeddings model...

Thanks for doing this! Is this ready to merge?

Checked with @logan-markewich. This looks good. Thank you!

Can you try Node 20 and see if it fixes it? We generally test against LTS versions but I’ll also take a look if I can reproduce it on Node...

More detailed instructions you can try feeding to GPT: In JavaScript, store entire chat history as an array of objects with fields for user or agent and utterance text. POST...

Thanks, we will take a look. Appreciate the bug report!