7c7bd8ceeb
Maven can now be told who someone is. She cannot yet tell who is speaking, and this commit is careful to say so rather than pretend otherwise. What works: profiles are enrolled from several deliberately recorded samples, listed, and deleted. They live in the existing memory_vectors table under a "speaker:" id prefix, so there is no migration; what that needed was a wider interface than memory.Store, hence memory.Catalog with ByPrefix and Delete. Delete is the load-bearing half — a voiceprint someone asked to be rid of has to actually go, and a search-only store cannot do that. InMemoryStore.Insert became an upsert by id to match what the persistent store already did. What does not work, and why it is not faked: there is no speaker-embedding model on this box. Sixteen ggufs in /mnt/hdd1/llms, all text; no ECAPA, no x-vector, no titanet, no wespeaker, no .onnx anywhere under /mnt/hdd1. So newSpeakerEmbedder returns nil, internal/speaker falls back to speaker.Disabled, Identify answers ErrDisabled, and the daemon logs which half is off at startup. The plan's "simple MFCC + GMM" floor is refused in the package comment: MFCC cosine distance detects channel and loudness as much as voice, and a biometric that is confidently wrong writes false claims about named people into his memory. A bad floor is worse than none here. Refused as well, and the reason is in enroll.go's doc comment: the plan asked for unknown speakers to be enrolled on first interaction with a TTS "кто это?". There is no request shape in the protocol that could express that. Taking a biometric of whoever walks past the microphone does it to guests who are not party to the exchange, and a synthesised question into a room is not consent from whoever answers. Authority: enrolment is AuthStepUp, because it is a deliberate sit-down act that writes a biometric of a named person and never something done by voice mid-conversation. Deletion is one rung lower at AuthWrite, deliberately inverting the usual pattern — getting rid of a biometric must never be the harder half. Listing is AuthRead and never returns the vectors themselves. Off unless configured: no speaker block means the three methods answer ErrUnknownMethod, so a default box has no wire path that takes a voiceprint. make build and make test pass. Vikunja #255 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TrVSBKe3RFDF4fGYKWYQnX
164 lines
4.2 KiB
Go
164 lines
4.2 KiB
Go
package memory
|
|
|
|
import (
|
|
"context"
|
|
"sort"
|
|
"strings"
|
|
"sync"
|
|
)
|
|
|
|
// Result is a single search hit.
|
|
type Result struct {
|
|
ID string
|
|
Score float64
|
|
Meta map[string]string
|
|
}
|
|
|
|
// Store is a vector memory interface.
|
|
type Store interface {
|
|
Insert(ctx context.Context, id string, vec []float32, meta map[string]string) error
|
|
Search(ctx context.Context, vec []float32, topK int) ([]Result, error)
|
|
}
|
|
|
|
// Record is a stored vector read back whole — id, vector and metadata — as
|
|
// opposed to Result, which is a search hit and carries a score instead of the
|
|
// vector.
|
|
type Record struct {
|
|
ID string
|
|
Vec []float32
|
|
Meta map[string]string
|
|
}
|
|
|
|
// Catalog is a Store that can also be enumerated by id prefix and deleted from.
|
|
//
|
|
// Search is not enough for every user of the vector table. Speaker profiles
|
|
// (internal/speaker) need to list exactly their own rows without scoring
|
|
// anything, because listing enrolled voices is not a similarity question, and
|
|
// they need Delete because a voiceprint is data about a person and "forget this
|
|
// voice" has to actually remove it. Note and fact recall use plain Store and are
|
|
// unaffected.
|
|
type Catalog interface {
|
|
Store
|
|
// ByPrefix returns every row whose id starts with prefix, in no particular
|
|
// order. An empty prefix returns everything.
|
|
ByPrefix(ctx context.Context, prefix string) ([]Record, error)
|
|
// Delete removes one row by id. Deleting a row that is not there is not an
|
|
// error: the caller asked for it to be gone and it is gone.
|
|
Delete(ctx context.Context, id string) error
|
|
}
|
|
|
|
// item is a single stored vector with metadata.
|
|
type item struct {
|
|
id string
|
|
vec []float32
|
|
meta map[string]string
|
|
}
|
|
|
|
// InMemoryStore implements Store with cosine similarity search.
|
|
type InMemoryStore struct {
|
|
mu sync.RWMutex
|
|
items []item
|
|
}
|
|
|
|
// compile-time check: InMemoryStore satisfies Catalog.
|
|
var _ Catalog = (*InMemoryStore)(nil)
|
|
|
|
func NewInMemoryStore() *InMemoryStore {
|
|
return &InMemoryStore{}
|
|
}
|
|
|
|
// Insert upserts by id, matching the persistent store.MemoryStore: a repeated
|
|
// id replaces the prior row rather than accumulating a second copy. Re-indexing
|
|
// a note is an update, and re-enrolling a voice must replace the old voiceprint
|
|
// rather than leave it searchable.
|
|
func (s *InMemoryStore) Insert(_ context.Context, id string, vec []float32, meta map[string]string) error {
|
|
s.mu.Lock()
|
|
defer s.mu.Unlock()
|
|
for i := range s.items {
|
|
if s.items[i].id == id {
|
|
s.items[i] = item{id: id, vec: vec, meta: meta}
|
|
return nil
|
|
}
|
|
}
|
|
s.items = append(s.items, item{id: id, vec: vec, meta: meta})
|
|
return nil
|
|
}
|
|
|
|
// ByPrefix implements Catalog.
|
|
func (s *InMemoryStore) ByPrefix(_ context.Context, prefix string) ([]Record, error) {
|
|
s.mu.RLock()
|
|
defer s.mu.RUnlock()
|
|
var out []Record
|
|
for _, it := range s.items {
|
|
if !strings.HasPrefix(it.id, prefix) {
|
|
continue
|
|
}
|
|
out = append(out, Record{ID: it.id, Vec: append([]float32(nil), it.vec...), Meta: it.meta})
|
|
}
|
|
return out, nil
|
|
}
|
|
|
|
// Delete implements Catalog.
|
|
func (s *InMemoryStore) Delete(_ context.Context, id string) error {
|
|
s.mu.Lock()
|
|
defer s.mu.Unlock()
|
|
for i := range s.items {
|
|
if s.items[i].id == id {
|
|
s.items = append(s.items[:i], s.items[i+1:]...)
|
|
return nil
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (s *InMemoryStore) Search(_ context.Context, vec []float32, topK int) ([]Result, error) {
|
|
s.mu.RLock()
|
|
defer s.mu.RUnlock()
|
|
|
|
if topK <= 0 {
|
|
topK = 10
|
|
}
|
|
|
|
type scored struct {
|
|
id string
|
|
score float64
|
|
meta map[string]string
|
|
}
|
|
|
|
scores := make([]scored, 0, len(s.items))
|
|
for _, it := range s.items {
|
|
score := cosine(vec, it.vec)
|
|
scores = append(scores, scored{id: it.id, score: score, meta: it.meta})
|
|
}
|
|
|
|
sort.Slice(scores, func(i, j int) bool {
|
|
return scores[i].score > scores[j].score // descending
|
|
})
|
|
|
|
if topK > len(scores) {
|
|
topK = len(scores)
|
|
}
|
|
|
|
out := make([]Result, topK)
|
|
for i := 0; i < topK; i++ {
|
|
out[i] = Result{
|
|
ID: scores[i].id,
|
|
Score: scores[i].score,
|
|
Meta: scores[i].meta,
|
|
}
|
|
}
|
|
return out, nil
|
|
}
|
|
|
|
// cosine similarity (dot product, assumes L2-normalized vectors).
|
|
func cosine(a, b []float32) float64 {
|
|
if len(a) != len(b) || len(a) == 0 {
|
|
return 0
|
|
}
|
|
var dot float64
|
|
for i := range a {
|
|
dot += float64(a[i]) * float64(b[i])
|
|
}
|
|
return dot
|
|
}
|