First pass feedback on differences is that R2R is building with all database / llm providers in mind.
Further, it seems Canopy has picked some pretty different abstractions to focus on. For instance, they mention `ChatEngine` as core abstraction, whereas R2R attempts to be a bit more agnostic.
That being said, there are definitely some commonalities, so thanks for sharing this repo! I will be sure to give it a deep dive.
Yes, this is an easy lift, could* you add an issue?
We also offer qdrant and pgvector, and will expand into most major providers with time. I personally recommend qdrant after trying 6 or 7 different ones while trying to scale out.
There are claims and anecdotal reports but (caveat that I'm not an earthquake scientist lol) doesn't seem to have expert consensus and I'm not seeing anything that passes the bar of not being able to be explained by people who've heard that animals predict earthquakes retroactively blaming any behavior they noticed on earthquake awareness.
Is it possible they're just hearing the sound of them (you can often hear the sound they're making a few seconds before it hits where you are - I live in NZ) before us due to their much better hearing?
Mainly because it's not pleasant to work w/ bad management. Bad culture starts from management - pretentiousness, stressed colleagues, micromanagement etc.