homelab-codex-ws/services/kb-query/docker-compose.yml

40 lines
2 KiB
YAML
Raw Normal View History

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