David Marx

yeah forget gpt-3.5-turbo. I think it's just too unreliable for code generation. may as well focus on using whatever tools are most likely to work rather than wrestling with 3.5

looks like the `graphToPrompt()` function is probably the conversion code we're all looking for. https://github.com/comfyanonymous/ComfyUI/blob/master/web/scripts/app.js#L1857-L1989

bumping. any movement on this?

> @matifali I'm trying to understand your expectations, hence the following questions > > * Assume you have 1 cell > *Code in this cell prints numbers from 1 to...

Do any of this user's repositories?

So to summarize: 1. The default behavior doesn't compute levenshtein distance but instead computes Ratcliff/Obershelp match ratio, which is similar but not identical to jaccard similarity. 2. If python-levenshtein is...

had kept this open for communication purposes, closing in favor of #30810

absolutely! for additional context, here's some discussion of project goals: * https://github.com/dmarx/Multi-Modal-Comparators/pull/14#discussion_r860348282 * https://github.com/dmarx/Multi-Modal-Comparators/issues/4#issuecomment-1102728236 * facilitating/backdooring support for perceptors trained on languages other than english in AI tools for creatives...

> ok sounds good, I'll get started on the pypi part my plan is simply to get into pypi all the dependencies, so we can directly pypi depend on them...

@rom1504 just checking in. have you had a chance to take a stab at this? would love it if we could distribute this on pypi rather than asking users to...