ggordbegli

I upgraded the context to 16k. So longer videos should work now, such as a ~1 hour speech.

This is wonderful. I made questionyoutube.com yesterday to solve a similar problem, I think this is better in the limit though.

If you can just get search time down, and make the summarization a little better, that would be amazing.

For instance, I tried this with 'what Toyotas should I avoid' and it found good relevant videos, but in the summary of 'Bad Toyotas you need to avoid' it misses that certain Toyotas from 2007-2009 had an oil burning issue, which was the main topic of the video. Querying the transcript of the video with 'what Toyotas do I need to avoid' gives a more complete answer. I'm curious how your handling the initial summary.

I embed descriptions using Open AI's "text-embedding-ada-002" embedding model[0]. Then I use cosign similarity to find the closest embeddings to that of the selected company[1].

[0]https://platform.openai.com/docs/guides/embeddings/embedding...

[1]https://scikit-learn.org/stable/modules/generated/sklearn.me...

You can try out paperswithprompts.com

I created a crude site that ranks universities & departments based on professor review data.

https://www.bananacharts.com/rank.html