Files
hyperguild/ingestion/internal/vectorstore/sync.go
Mathias 37fdd33b2d
All checks were successful
CI / Lint / Test / Vet (push) Successful in 11s
CI / Mirror to GitHub (push) Has been skipped
feat(ingestion): chunk markdown before embedding (#38)
Long markdown files (>~8KB) silently failed to embed because nomic-embed-text
on iguana has a 2048-token context. embed sync logged errors=1 every cycle
with no useful body until #37 added per-item logging — three files exceed
the ceiling: finbert source (8 KB), koala-machine-state (7.1 KB),
litellm-absorption (8.8 KB). Curated knowledge entries should never be
vector-blind.

Approach: chunk-before-embed, no schema change.

vectorstore/chunk.go (new)
- ChunkMarkdown splits at H1/H2 boundaries; sections over maxBytes are
  further split at paragraph boundaries, packing greedily under budget.
- NumberChunks assigns "<parent>#NNNN" storage paths (1-based, zero-padded
  to 4 digits — handles files with up to ~10k sections in stable sort order).
- ParentPath strips the chunk suffix for retrieval-side dedup.

vectorstore/sync.go
- After ChunkMarkdown produces N pieces, each is embedded + upserted as a
  separate brain_embeddings row at "<parent>#NNNN". maxChunkBytes = 4000
  (≈1000 nomic tokens, well under the 2048 ceiling with headroom for
  unicode/code blocks).
- "Already embedded?" check now reduces known paths to parent set via
  ParentPath, so the first chunk hit short-circuits the file.
- Delete walk also reduces via ParentPath; when a parent file disappears,
  every chunk row (and any pre-existing bare-path row, for backward
  compatibility with rows written before this change) gets dropped.

search/search.go
- hybridMerge collapses chunk-path vector hits to parent via ParentPath
  before scope check, RRF accumulation, and hydration. A file with three
  chunk hits returns one result row, not three.

Backward compatibility: pre-existing bare-path rows in brain_embeddings
keep working — ParentPath returns them unchanged, knownParents handles
them as if they were "wiki/foo.md#NNNN" hits, sync skips re-embed, and
search dedup is a no-op for them. No migration required to ship.

Tests:
- chunk_test.go covers short / heading split / oversized section /
  content preservation / chunk numbering / parent-path stripping.
- sync_test.go adds long-file chunking, single-chunk-row short file,
  skip-if-any-chunk-known, delete-all-chunks-of-disappeared-file.
  Existing tests updated for #NNNN paths.
- search_test.go adds chunk-paths-dedupe-to-parent.

Closes gitea/mathias/infra#38.
2026-05-19 21:57:09 +02:00

171 lines
5.2 KiB
Go

package vectorstore
import (
"context"
"fmt"
"log/slog"
"os"
"path/filepath"
"strings"
"time"
)
// Embedder produces dense vectors. The embed package's Client satisfies
// this; it's declared locally so vectorstore doesn't depend on embed.
type Embedder interface {
Embed(ctx context.Context, text string) ([]float32, error)
}
// Store is the subset of PGStore that Sync needs. Lets tests stub it.
type Store interface {
KnownPaths(ctx context.Context) (map[string]struct{}, error)
Upsert(ctx context.Context, path string, embedding []float32) error
Delete(ctx context.Context, path string) error
}
// SyncResult tallies what Sync did. Returned for logs / metrics; callers
// generally don't act on the fields directly.
type SyncResult struct {
Added int
Updated int
Deleted int
Errors []error
}
// scanDirs is the set of brainDir subdirectories whose .md files are
// embedded for vector retrieval. wiki/ holds LLM-extracted entity and
// source pages; knowledge/ holds curated hand-written entries.
var scanDirs = []string{"wiki", "knowledge"}
// maxChunkBytes is the per-chunk byte budget passed to ChunkMarkdown.
// Sized to fit comfortably under nomic-embed-text's 2048-token default
// context (~4 chars/token for English markdown → ~8 KB ceiling; we sit
// at 4 KB to leave headroom for unicode, code blocks, and tokenizer
// variance).
const maxChunkBytes = 4000
// Sync brings the embedding store in line with brain/{wiki,knowledge}/
// on disk:
// - new files (in the tree, not in the store) get embedded + upserted
// - files whose mtime exceeds the store's updated_at get re-embedded
// - files no longer on disk get deleted from the store
//
// Designed to be called on a ticker. Best-effort: per-file errors are
// collected into SyncResult.Errors and do not abort the run.
func Sync(ctx context.Context, brainDir string, store Store, embedder Embedder) (SyncResult, error) {
var res SyncResult
if store == nil || embedder == nil {
return res, nil
}
known, err := store.KnownPaths(ctx)
if err != nil {
return res, fmt.Errorf("known paths: %w", err)
}
// Build a parent → "any chunk known?" set so we can skip files that
// already have at least one chunk row in the store.
knownParents := make(map[string]struct{}, len(known))
for p := range known {
knownParents[ParentPath(p)] = struct{}{}
}
seenParents := make(map[string]struct{})
for _, sub := range scanDirs {
root := filepath.Join(brainDir, sub)
if _, err := os.Stat(root); os.IsNotExist(err) {
continue
}
err = filepath.WalkDir(root, func(path string, d os.DirEntry, err error) error {
if err != nil {
return err
}
if d.IsDir() || !strings.HasSuffix(path, ".md") || d.Name() == "_index.md" {
return nil
}
rel, err := filepath.Rel(brainDir, path)
if err != nil {
return err
}
relSlash := filepath.ToSlash(rel)
seenParents[relSlash] = struct{}{}
if _, ok := knownParents[relSlash]; ok {
// File has at least one chunk in the store already.
// TODO: compare mtime once Store exposes updated_at so we
// re-embed on edit. For now, skip.
return nil
}
content, readErr := os.ReadFile(path)
if readErr != nil {
res.Errors = append(res.Errors, fmt.Errorf("read %s: %w", relSlash, readErr))
return nil
}
chunks := NumberChunks(relSlash, ChunkMarkdown(string(content), maxChunkBytes))
for _, ch := range chunks {
vec, embErr := embedder.Embed(ctx, ch.Content)
if embErr != nil {
res.Errors = append(res.Errors, fmt.Errorf("embed %s: %w", ch.Path, embErr))
continue
}
if upErr := store.Upsert(ctx, ch.Path, vec); upErr != nil {
res.Errors = append(res.Errors, fmt.Errorf("upsert %s: %w", ch.Path, upErr))
continue
}
res.Added++
}
return nil
})
if err != nil {
return res, fmt.Errorf("walk %s: %w", sub, err)
}
}
// Drop chunk rows whose parent file is gone.
for path := range known {
if _, ok := seenParents[ParentPath(path)]; ok {
continue
}
if err := store.Delete(ctx, path); err != nil {
res.Errors = append(res.Errors, fmt.Errorf("delete %s: %w", path, err))
continue
}
res.Deleted++
}
return res, nil
}
// StartSync launches Sync on a ticker in a background goroutine. The
// goroutine exits when ctx is cancelled. Failures are logged via slog.
func StartSync(ctx context.Context, brainDir string, store Store, embedder Embedder, interval time.Duration) {
if interval <= 0 {
interval = 5 * time.Minute
}
go func() {
t := time.NewTicker(interval)
defer t.Stop()
// Run once immediately so first-boot doesn't wait a full tick.
if r, err := Sync(ctx, brainDir, store, embedder); err != nil {
slog.Error("embed sync failed", "err", err)
} else if r.Added+r.Deleted > 0 || len(r.Errors) > 0 {
slog.Info("embed sync", "added", r.Added, "deleted", r.Deleted, "errors", len(r.Errors))
for _, e := range r.Errors {
slog.Warn("embed sync item failed", "err", e)
}
}
for {
select {
case <-ctx.Done():
return
case <-t.C:
if r, err := Sync(ctx, brainDir, store, embedder); err != nil {
slog.Error("embed sync failed", "err", err)
} else if r.Added+r.Deleted > 0 || len(r.Errors) > 0 {
slog.Info("embed sync", "added", r.Added, "deleted", r.Deleted, "errors", len(r.Errors))
}
}
}
}()
}