feat(kb): add kb-query service skeleton (search API, no ingress yet)
Module 5 phase 4 step 1 (docs/kb/modules/05-faza4-plan.md, §4): first
user-facing HTTP entry point to the KB. FastAPI wrapping
kb_retrieval.cascade_query/flat_query — GET /search (query_text -> embed via
Ollama@SOLARIA -> cascade/flat -> envelope join -> JSON with per-source
links) and GET /healthz. Search API only, no answer synthesis (phase 5) and
no server-side dist filtering — the 0.45/0.55 colour thresholds are a
frontend concern (plan §7, a later step).
Hard startup invariant (plan §2 decision 2): refuses to start unless the
configured EMBED_MODEL is present in both document_chunk.model and
document_summary.embedding_model. Note the latter: document_summary.model is
the LLM that *wrote* the summary (claude-haiku-4-5/gemma3:12b), not the
embedder — checked live against kb-postgres@PIHA before writing this, see
app/startup.py's docstring. Verified end-to-end with a live docker run: the
invariant crash-loops on a mismatched EMBED_MODEL and passes through to a
real /search hit against the live corpus with a correct model.
Repo-only: no deploy, no npm/OIDC/DNS wiring (plan §8, later step), no local
embed fallback (plan §5, later step) — Ollama@SOLARIA is called directly and
a failure surfaces as 503, not a crash.
Also: scripts/deploy/deploy.sh's gate now builds each service via
`docker compose build` instead of a raw `docker build <svc_dir>`, so a
service whose docker-compose.yml declares a repo-root build context (needed
here to COPY packages/kb-retrieval/, the packages/ Dockerfile convention
already documented in CLAUDE.md) resolves the same way in the gate as it
does at real deploy time (deploy-node.sh's `docker compose ... up --build`).
No behavior change for existing single-context services — verified against
llm-gateway's compose file.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-22 16:06:18 +02:00
|
|
|
services:
|
|
|
|
|
kb-query:
|
|
|
|
|
build:
|
|
|
|
|
# Repo-root context (not the usual `.` = this dir) so the Dockerfile can
|
|
|
|
|
# `COPY packages/kb-retrieval/` — the packages/ Dockerfile convention from
|
|
|
|
|
# CLAUDE.md. scripts/deploy/deploy.sh's gate and deploy-node.sh's
|
|
|
|
|
# `docker compose ... up --build` both resolve this the same way.
|
|
|
|
|
context: ../..
|
|
|
|
|
dockerfile: services/kb-query/Dockerfile
|
|
|
|
|
container_name: kb-query
|
|
|
|
|
restart: unless-stopped
|
|
|
|
|
ports:
|
|
|
|
|
# LAN-only bind, never 0.0.0.0 — same convention as paperless/nextcloud
|
|
|
|
|
# (exposure: private). npm@PIHA vhost + OIDC are a later step (plan §8);
|
|
|
|
|
# this bind is what that vhost will eventually proxy to.
|
|
|
|
|
# Requires .env (from env.example) next to this file at deploy.
|
|
|
|
|
- "${LAN_BIND_IP}:8230:8080"
|
|
|
|
|
environment:
|
|
|
|
|
- KB_DSN=${KB_DSN}
|
feat(kb): aktywny fallback embeddingów SOLARIA→PIHA dla kb-query (faza 4 Krok 2)
Ostatni krok fazy 4 KB (plan §2 Decyzja 2, §5): kb-query przestaje być martwe
przez ~16 h/dobę, gdy SOLARIA (GPU) śpi — zapytania embeduje wtedy lokalna
Ollama CPU na PIHA (wolniej: ~790 ms+ vs ~207 ms na GPU, ale działa).
Nowy serwis services/ollama-piha (GitOps, owner_node: piha):
- ollama/ollama:latest (arm64 natywnie), OLLAMA_KEEP_ALIVE=0 — model zwalnia
RAM natychmiast po każdym wywołaniu (spike, nie rezydent; PIHA dzieli 8 GB z HA)
- bind wyłącznie 127.0.0.1 + LAN_BIND_IP (192.168.31.5), nigdy 0.0.0.0/Tailscale
- named volume ollama_piha_models (NVMe data-root) zamiast bind-mounta — obraz
biega jako root w kontenerze i bind łamałby wzorzec uid PIHA (oskar=1004,
kontenery uid 1000, setgid pi)
- override hosts/piha/runtime/ollama-piha: mem_limit 2560m (wartość startowa
z planu, do potwierdzenia kalibracją na żywo), świadomie bez mem_reservation
- pull bge-m3 to jawny, ręczny krok deployu (README) — obraz nie ma modeli
kb-query — maszyna stanów fallbacku (app/embed_router.py):
- health-check SOLARII (GET /api/tags, timeout 1.5 s) z cache 30 s — zero
sondowania per request; po powrocie SOLARII ruch wraca na GPU w ≤30 s
- primary up → embed na SOLARII z twardym timeoutem 3 s; błąd W TRAKCIE
zapytania = jednorazowe przełączenie (krok 3b planu): status down na 30 s
i TO SAMO zapytanie leci na fallback — user nie widzi błędu SOLARII
- primary down → embed prosto na ollama-piha (bez twardego timeoutu: CPU +
zimny load modelu to legalnie pojedyncze sekundy)
- 503 tylko gdy oba backendy padłe (lub fallback nieskonfigurowany)
- inwariant modelu, druga połowa: każdy backend weryfikowany raz, leniwie przy
pierwszym użyciu, że /api/tags zawiera EMBED_MODEL (bge-m3 — ta sama wartość
co startowy check przeciw document_chunk.model/document_summary.embedding_model);
niezgodność = ERROR log + 500, nigdy ciche liczenie dystansów między
różnymi przestrzeniami embeddingów; leniwie, bo śpiąca SOLARIA nie może
blokować startu serwisu
- odpowiedź /search: nowe pole embed_backend ("solaria"|"piha") + sol_status
wg realnego świata routera (UI już renderuje down jako "offline (fallback
embed)"); log INFO backend=... elapsed_ms=... per zapytanie
- /healthz: sol_status przez cache routera (spójny widok z routingiem) +
fallback_status (żywa, tania sonda /api/tags)
Konfiguracja spójnie przez env (compose + env.example + service.yaml + README):
EMBED_PRIMARY_URL (zastępuje OLLAMA_URL), EMBED_FALLBACK_URL (pusty = brak
fallbacku, zachowanie sprzed kroku 2), EMBED_{PRIMARY,FALLBACK}_NAME,
EMBED_HEALTH_TTL_S/EMBED_HEALTH_TIMEOUT_S/EMBED_PRIMARY_TIMEOUT_S.
Testy: 39 pass (14 nowych w test_embed_router.py: cache TTL, failover w trakcie
zapytania, powrót po TTL, oba padłe, mismatch modelu na primary i fallbacku,
tag "bge-m3:latest" vs "bge-m3"); docker build + smoke (importy + uvicorn do
guardu KB_DSN) OK; compose config OK dla obu stacków.
Deploy (Oskar, na PIHA z mastera po merge):
cd ~/homelab-codex-ws && git pull
# 1. ollama-piha
cp services/ollama-piha/env.example services/ollama-piha/.env
docker compose -f services/ollama-piha/docker-compose.yml \
-f hosts/piha/runtime/ollama-piha/docker-compose.override.yml \
--env-file services/ollama-piha/.env up -d
docker exec ollama-piha ollama pull bge-m3 # ręczny krok, obowiązkowy
services/ollama-piha/healthcheck.sh
# 2. kb-query (dopisać fallback do istniejącego .env)
echo 'EMBED_FALLBACK_URL=http://192.168.31.5:11434' >> services/kb-query/.env
docker compose -f services/kb-query/docker-compose.yml \
-f hosts/piha/runtime/kb-query/docker-compose.override.yml up -d --build
services/kb-query/healthcheck.sh
# (deploy-node.sh też podniesie oba serwisy z hosts/piha/services.yaml,
# ale pull bge-m3 i .env pozostają ręczne)
Weryfikacja: testy A/B/C w services/kb-query/README.md (backend=solaria przy
SOLARII online; backend=piha przy symulacji offline; powrót na GPU w ≤30 s).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-29 19:01:29 +02:00
|
|
|
# Embed backends (Krok 2, aktywny fallback — app/embed_router.py): primary is
|
|
|
|
|
# Ollama @ SOLARIA (GPU, duty-cycled), fallback is ollama-piha on this host
|
|
|
|
|
# (CPU, OLLAMA_KEEP_ALIVE=0). Empty EMBED_FALLBACK_URL disables the fallback
|
|
|
|
|
# leg (pre-Krok-2 behaviour: /search 503s while SOLARIA sleeps).
|
|
|
|
|
- EMBED_PRIMARY_URL=${EMBED_PRIMARY_URL:-http://solaria:11434}
|
|
|
|
|
- EMBED_FALLBACK_URL=${EMBED_FALLBACK_URL:-}
|
|
|
|
|
- EMBED_PRIMARY_NAME=${EMBED_PRIMARY_NAME:-solaria}
|
|
|
|
|
- EMBED_FALLBACK_NAME=${EMBED_FALLBACK_NAME:-piha}
|
|
|
|
|
- EMBED_HEALTH_TTL_S=${EMBED_HEALTH_TTL_S:-30}
|
|
|
|
|
- EMBED_HEALTH_TIMEOUT_S=${EMBED_HEALTH_TIMEOUT_S:-1.5}
|
|
|
|
|
- EMBED_PRIMARY_TIMEOUT_S=${EMBED_PRIMARY_TIMEOUT_S:-3}
|
feat(kb): add kb-query service skeleton (search API, no ingress yet)
Module 5 phase 4 step 1 (docs/kb/modules/05-faza4-plan.md, §4): first
user-facing HTTP entry point to the KB. FastAPI wrapping
kb_retrieval.cascade_query/flat_query — GET /search (query_text -> embed via
Ollama@SOLARIA -> cascade/flat -> envelope join -> JSON with per-source
links) and GET /healthz. Search API only, no answer synthesis (phase 5) and
no server-side dist filtering — the 0.45/0.55 colour thresholds are a
frontend concern (plan §7, a later step).
Hard startup invariant (plan §2 decision 2): refuses to start unless the
configured EMBED_MODEL is present in both document_chunk.model and
document_summary.embedding_model. Note the latter: document_summary.model is
the LLM that *wrote* the summary (claude-haiku-4-5/gemma3:12b), not the
embedder — checked live against kb-postgres@PIHA before writing this, see
app/startup.py's docstring. Verified end-to-end with a live docker run: the
invariant crash-loops on a mismatched EMBED_MODEL and passes through to a
real /search hit against the live corpus with a correct model.
Repo-only: no deploy, no npm/OIDC/DNS wiring (plan §8, later step), no local
embed fallback (plan §5, later step) — Ollama@SOLARIA is called directly and
a failure surfaces as 503, not a crash.
Also: scripts/deploy/deploy.sh's gate now builds each service via
`docker compose build` instead of a raw `docker build <svc_dir>`, so a
service whose docker-compose.yml declares a repo-root build context (needed
here to COPY packages/kb-retrieval/, the packages/ Dockerfile convention
already documented in CLAUDE.md) resolves the same way in the gate as it
does at real deploy time (deploy-node.sh's `docker compose ... up --build`).
No behavior change for existing single-context services — verified against
llm-gateway's compose file.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-22 16:06:18 +02:00
|
|
|
- EMBED_MODEL=${EMBED_MODEL:-bge-m3}
|
|
|
|
|
- SUMMARY_MODEL=${SUMMARY_MODEL:-claude-haiku-4-5}
|
|
|
|
|
# python:3.12-slim has no curl/wget; same in-container check pattern as llm-gateway.
|
|
|
|
|
healthcheck:
|
|
|
|
|
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8080/healthz', timeout=3).read()"]
|
|
|
|
|
interval: 30s
|
|
|
|
|
timeout: 10s
|
|
|
|
|
retries: 5
|
|
|
|
|
start_period: 10s
|