I run a dockerized version of qdrant for RAG related stuff and have been pretty happy with it.
What would change that to 'very happy' in your use case?
Thanks for your work on Qdrant! I actually don't really have any complaints at this time. I'm using it in conjunction with Qwen3-VL to autocaption/describe images and then place them in a large vector Qdrant db so its easy to semantically search through ~100k worth of image assets.