Joshua Nielsen

Hi @kylelamb1324 thanks for reaching out. Are you running on a windows machine? > On Windows the subprocesses will import (i.e. execute) the main module at start. You need to...

@churchec you wouldn't insert it in lppls.py but in the program that is calling lppls. You would do something like the following: ``` if __name__ == '__main__': # compute the...

Hi @AleksLi1,what is the error message you're receiving?

@AleksLi1, it looks like you're getting a `FileNotFoundError`. I think this is an issue with the `avoiding_bubbles` repo. When I was writing that, I wanted to avoid recomputing the lppls-ci...

Hi @peter308, are you able to provide your code? Thanks!

Thanks @samueldgSBCS would you be willing to post a draft PR with your suggestion?

Hi @SpenceSidne08, Thank you for the kind words. We should be able to apply the model to minutely data. Are you able to provide a sample of the data you...

Here is an example https://colab.research.google.com/drive/1iDvGHyclOsHImQI4qRQNL3_xvmjxnc3D?usp=sharing The trick is to convert time to evenly spaced numbers over a specified interval via numpy's `linspace` function. You lose timestamps but these can be...

Sounds good thanks!

Perhaps the better approach is to implement a similarity score threshold, and only query the completions endpoint if enough context is found in the embeddings database?