// semantic search
Embeddings.
Every technical posting gets a semantic embedding, which is how “similar jobs” finds postings that mean the same thing in different words. This is how much of the catalogue has one right now — live.
measuring…
of eligible postings embedded
- Embedded
- measuring…
- Eligible
- measuring…
- In the queue
- 23,336
- Speed
- 31 / min
- Time left
- ~12 h 38 min
- Queue measured
- 13:03 UTC
“Embedded” is eligible postings minus the queue, current to the queue’s last sample. A full count — measuring… embedded — was last taken at measuring…; it runs every few hours because it reads every open posting.
// help speed it up
Lend your machine for a while.
The volunteer client runs the embedding model on your own computer and sends back vectors for postings in the queue. Pick how much of your machine it may use — easy, medium or hard — and watch the queue above move faster.