> Postgres makes those files searchable. memory.entries stores chunks and line references, memory.embeddings holds 384-dimensional vectors, and memory.claims tracks evidence, confidence, and status.
That seems wildly wasteful, especially since earlier in the article it states that the Muse instance has a SQLite database and schema already...
What would prevent them from getting the data out of postgres?
The VM is about the same specs as a 9EUR/month VPS from Hetzner but it only runs a fraction of the time, they spin it down when Muse stops using it. Meta is a hyperscaler with optimized infra and they don't need to make a profit because VMs are not their actual service. I think it costs them at least 10x less than inference for most users.