Backlog F5: where a large knowledge-base import spends its time
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
92733317a9
commit
8932502768
1 file changed
+21
+21
@@ -1065,6 +1065,27 @@ training yet; quality gating of a published adapter is by hand (ctl eval).
|
||||
|
||||
---
|
||||
|
||||
### F5. Large imports (M) — measured 2026-10-09, open
|
||||
The metallurgy corpus (2,314 files, 108,779 chunks, bge-m3 on the one
|
||||
GPU) went in at about 25 chunks/s, the same over a phone hotspot and the
|
||||
LAN. The engine's slots were the limit: llama.cpp `--parallel 4` embeds
|
||||
four texts per pass, while llmgw-kb sends 32 a request from 6 workers. The
|
||||
usage rows show 4.6 s a request on average, 1.8 s of it in the gateway's
|
||||
queue and 0.04 s in the guard. The GPU sat at 18–50% and the store machine
|
||||
at a third of its CPUs.
|
||||
- An embedding model's profile with many slots by default (`--parallel`
|
||||
32–64, `--ctx-size` to match, `--batch-size`/`--ubatch-size` at least the
|
||||
longest chunk), or `ctl model serve` choosing that for a model with
|
||||
`capabilities.embeddings`. With the default 512, one 516-token chunk failed.
|
||||
- Embedding on the gateway's side of a document PUT, so the client sends
|
||||
text only: today an embeddings answer is ~21 KB of JSON a chunk, and
|
||||
the text and vector go up again (~11 KB).
|
||||
- The store next: HNSW inserts took half of one of pg01's two cores; at a
|
||||
million chunks the vectors alone outgrow its 4 GB. halfvec (pgvector ≥
|
||||
0.7) and a larger store machine.
|
||||
- Done: a batch of embeddings checked text by text against the context
|
||||
(branch `embeddings-batch`); it was refused as one over-long prompt.
|
||||
|
||||
## D. Facts worth knowing before starting
|
||||
|
||||
- Admin API: `127.0.0.1:9090`, no auth, `ctlClient` in `internal/cli/ctl.go`.
|
||||
|
||||
Reference in new issue
Block a user