P5b review: background embedder re-queues a failed document and waits for a busy gate; no empty vectors cached
Owner review of p5b (tasks 01-03 by Ornith): - background.go: `seen` was never cleared, so a document whose background embedding failed (Dixie hiccup) or was abandoned could never be queued again: every later question on it stayed BM25 for the life of the process. Dedupe now covers only queued and in-progress documents. - background.go: acquireGate gave up after one retry and dropped the document; the task said to keep retrying once a second. It now waits (background work has no deadline). - retrieval.go/background.go: a vector the server left out is not cached as an empty vector. - bm25.go: Scores on a nil *BM25 dereferenced it; returns nil. Regression tests in review_test.go; both fail on the old code. End-to-end against Dixie (local serve): Karpathy's thesis, 95 pages / 51 chunks: bm25 in 19 s, hybrid (51 embedded) after the background; RP2040 datasheet, 642 pages / 284 chunks (a 422 before P5b): bm25 in 13.5 s, all 284 embedded within 90 s, hybrid answer correct with its quote. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -85,7 +85,10 @@ func (w *bgWorker) run() {
|
||||
|
||||
w.process(job)
|
||||
|
||||
// Forget the document whether it finished or not: dedupe covers only queued and
|
||||
// in-progress work, so a later question re-queues a document whose embedding failed.
|
||||
w.mu.Lock()
|
||||
delete(w.seen, job.contentHash+"|"+job.callerClass)
|
||||
w.inProg = false
|
||||
w.mu.Unlock()
|
||||
}
|
||||
@@ -121,12 +124,7 @@ func (w *bgWorker) process(job embedJob) {
|
||||
for k := range batch {
|
||||
batch[k] = job.chunks[idx[b+k]]
|
||||
}
|
||||
if !w.acquireGate() {
|
||||
if e.Log != nil {
|
||||
e.Log.Warn("background embed gate")
|
||||
}
|
||||
return
|
||||
}
|
||||
w.acquireGate()
|
||||
ectx, cancel := context.WithTimeout(context.Background(), e.timeout())
|
||||
vecs, err := e.embed(ectx, batch)
|
||||
cancel()
|
||||
@@ -138,22 +136,22 @@ func (w *bgWorker) process(job embedJob) {
|
||||
return
|
||||
}
|
||||
for k := range batch {
|
||||
e.Cache.PutEmbed(key(idx[b+k]), vecs[k])
|
||||
if k < len(vecs) && len(vecs[k]) > 0 {
|
||||
e.Cache.PutEmbed(key(idx[b+k]), vecs[k])
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// acquireGate takes the Dixie gate, retrying once per second on a refusal so interactive digests
|
||||
// get turns. It returns false only if the gate cannot be taken after the first retry, so the
|
||||
// document is not stuck behind a permanently busy gate.
|
||||
func (w *bgWorker) acquireGate() bool {
|
||||
ok, _ := w.engine.Gate.Acquire(context.Background())
|
||||
if ok {
|
||||
return true
|
||||
// acquireGate takes the Dixie gate, sleeping a second after each refusal (queue full or wait
|
||||
// expired) so interactive digests get their turns. Background work has no deadline: it waits.
|
||||
func (w *bgWorker) acquireGate() {
|
||||
for {
|
||||
if ok, _ := w.engine.Gate.Acquire(context.Background()); ok {
|
||||
return
|
||||
}
|
||||
time.Sleep(time.Second)
|
||||
}
|
||||
time.Sleep(1 * time.Second)
|
||||
ok, _ = w.engine.Gate.Acquire(context.Background())
|
||||
return ok
|
||||
}
|
||||
|
||||
// WaitBackground returns when the background worker is idle: the queue empty and nothing embedding.
|
||||
|
||||
Reference in New Issue
Block a user