Nice read. I agree that for a lot of hobby use cases you can just load the embeddings from parquet and compute the similarities in-memory.
To find similarity between my blogposts [1] I wanted to experiment with a local vector database and found ChromaDB fairly easy to use (similar to SQLite just a file on your machine).
I implemented this feature on my blog a couple of weeks ago. I view it as the equivalent of a retweet, only that I own the content. If someone wants to subscribe, they can follow the respective rss feed. Maybe in the future I automatically push the updates to mastodon/bluesky/etc.
Feedback welcome