feat(brain): hybrid BM25 + pgvector retrieval (opt-in)
Wires nomic-embed-text (iguana ollama) + pgvector on the shared
postgres18 into brain_query / brain_answer via Reciprocal Rank Fusion.
Pure BM25 stays the default; setting BRAIN_PG_DSN and BRAIN_EMBED_URL
together opts in. Setting one without the other is misconfiguration →
exit 1.
New packages:
- internal/embed
Client.Embed(ctx, text) → []float32 via POST {URL}/api/embed.
Defaults to nomic-embed-text:latest (768 dim). nil-on-empty-URL so
callers gate on a single nil check.
- internal/vectorstore
PGStore wraps a pgxpool against postgres18. Init creates
brain_embeddings(path PK, vector(768), updated_at) + HNSW cosine
index idempotently. Upsert / Delete / Search / KnownPaths.
Sync(brainDir, store, embedder) diffs brain/wiki/ against the store
and upserts new files / deletes removed ones; StartSync runs it on
a ticker (default 300s). Integration tests gated by BRAIN_PG_TEST_DSN.
- scripts/brain-embeddings-init.sql
One-time DBA setup: brain DB, brain_app role, vector extension,
GRANTs. Idempotent.
Search layer:
- search.QueryOptions gains Vector + Embedder fields.
- QueryContext is the cancellable variant; Query stays for callers.
- When both are set, BM25 (top-N) and pgvector (top-4N) candidates
merge via Reciprocal Rank Fusion (k=60, Cormack et al. 2009 — no
tuning knob, robust to scale differences between rankers).
- Vector-only hits are hydrated from disk so callers see uniform
Result records (path, title, excerpt, wing, hall, score).
- Wing/hall filters still apply to vector candidates via path-prefix.
- On embedder/vector errors the search falls back to BM25 — embedding
outage degrades quality but doesn't take the brain offline.
MCP wiring:
- mcp.Server.WithHybridRetrieval(v, e) opt-in setter, same shape as
WithReranker.
- brainQuery and brainAnswer pass the wired vector/embedder through
to search.QueryContext.
REST:
- POST /backfill-embeddings drives Sync synchronously. Returns
{added, deleted, errors[]}. 503 when feature is unconfigured.
cmd/server/main.go:
- BRAIN_PG_DSN + BRAIN_EMBED_URL together enable hybrid; one alone
→ exit 1.
- vectorAdapter bridges *PGStore (returns []Hit) to
search.VectorSearcher (which takes []VectorHit) without either
package importing the other.
- BRAIN_EMBED_SYNC_INTERVAL (default 300s) controls the background
Sync ticker.
Backend pivot from Qdrant to pgvector recorded in DECISIONS.md
2026-05-18 (supersedes 2026-04-08): postgres18 already runs in
databases/ ns, Qdrant was never deployed, one engine beats two.
Dependency: github.com/jackc/pgx/v5 — modern, native pgvector via
parametric vector literals.
Tests:
- embed.Client: empty-URL nil, request shape, dimension, upstream
error propagation, empty-text rejection.
- vectorstore.PGStore: dimension validation (unit); upsert/search/
KnownPaths (integration, BRAIN_PG_TEST_DSN-gated).
- vectorstore.Sync: adds new files, skips known, deletes
disappeared, skips _index.md, no-op when nil, collects embedder
errors.
- search.Query: hybrid promotes vector-only hits via RRF; falls
back to BM25 on embedder error.
Closes hyperguild#8.
This commit is contained in:
47
scripts/brain-embeddings-init.sql
Normal file
47
scripts/brain-embeddings-init.sql
Normal file
@@ -0,0 +1,47 @@
|
||||
-- One-time DBA setup for the brain vector store on postgres18.
|
||||
--
|
||||
-- Creates the `brain` database, the `brain_app` role, and the pgvector
|
||||
-- extension. The ingestion service connects as brain_app and creates
|
||||
-- the table + HNSW index idempotently at startup (see
|
||||
-- internal/vectorstore.PGStore.Init).
|
||||
--
|
||||
-- Run from koala as the postgres superuser:
|
||||
--
|
||||
-- kubectl exec -n databases postgres18-0 -- \
|
||||
-- psql -U postgres -f /tmp/brain-embeddings-init.sql
|
||||
--
|
||||
-- Or apply with:
|
||||
--
|
||||
-- PASSWORD='<sops-generated>' \
|
||||
-- kubectl exec -i -n databases postgres18-0 -- \
|
||||
-- psql -U postgres -v password="'$PASSWORD'" \
|
||||
-- < scripts/brain-embeddings-init.sql
|
||||
--
|
||||
-- Idempotent: rerunning is safe.
|
||||
|
||||
\set ON_ERROR_STOP on
|
||||
|
||||
DO $$
|
||||
BEGIN
|
||||
IF NOT EXISTS (SELECT 1 FROM pg_database WHERE datname = 'brain') THEN
|
||||
CREATE DATABASE brain;
|
||||
END IF;
|
||||
END
|
||||
$$;
|
||||
|
||||
DO $$
|
||||
BEGIN
|
||||
IF NOT EXISTS (SELECT 1 FROM pg_roles WHERE rolname = 'brain_app') THEN
|
||||
EXECUTE format('CREATE ROLE brain_app LOGIN PASSWORD %L', :'password');
|
||||
END IF;
|
||||
END
|
||||
$$;
|
||||
|
||||
GRANT ALL PRIVILEGES ON DATABASE brain TO brain_app;
|
||||
|
||||
\c brain
|
||||
|
||||
CREATE EXTENSION IF NOT EXISTS vector;
|
||||
GRANT ALL ON SCHEMA public TO brain_app;
|
||||
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON TABLES TO brain_app;
|
||||
ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON SEQUENCES TO brain_app;
|
||||
Reference in New Issue
Block a user