justin
fd376fab77
Phase 4/5 — adapt the template workflows to Justin's self-hosted Gitea
+ act_runner setup (see reference_gitea_server memory):
* PUSH via LAN endpoint 192.168.0.2:1234 (bypasses Cloudflare's 100 MB
request-body cap on the Free plan); PULL via git.jpaul.io.
* buildx with config-inline insecure-registry for the LAN endpoint —
docker/login-action can't be used there (host daemon rejects HTTP).
Auth is written into ~/.docker/config.json so buildx reads it
directly.
* docker/metadata-action labels org.opencontainers.image.source with
the PUBLIC URL so Gitea auto-links the package; explicit POST to
/api/v1/packages/.../-/link/{repo} as belt-and-suspenders (201 newly
linked, 400 already linked, both treated as success).
* deploy/docker-compose.yml: substitute <product> placeholders, point
image at git.jpaul.io/justin/hvm-docs:latest, set HYBRID_SEARCH=false
to match the eval winner (bm25+rerank), keep the llama.cpp + jina
GGUF reranker sidecar as the production target.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
118 lines
4.0 KiB
YAML
118 lines
4.0 KiB
YAML
# Hosting stack for a docs MCP server.
|
|
#
|
|
# Replace hvm below with your product name on first deploy.
|
|
# Volumes: usage logs are mounted to a host path so they survive
|
|
# Watchtower-driven container recreates.
|
|
#
|
|
# This template assumes a reverse proxy / Cloudflare Tunnel terminates
|
|
# TLS in front of port 8000. Adjust if your infra differs.
|
|
|
|
services:
|
|
|
|
# The MCP server. Watchtower auto-pulls on :latest changes.
|
|
hvm-docs-mcp:
|
|
image: git.jpaul.io/justin/hvm-docs:latest
|
|
container_name: hvm-docs-mcp
|
|
restart: unless-stopped
|
|
ports:
|
|
- "8000:8000"
|
|
environment:
|
|
PRODUCT_NAME: "hvm"
|
|
PRODUCT_DOCS_URL: "https://support.hpe.com/hpesc/public/docDisplay?docId=sd00007735en_us"
|
|
|
|
# Streamable-HTTP transport. Stateless mode is required for
|
|
# production: clients don't lose sessions when Watchtower
|
|
# recreates the container.
|
|
MCP_TRANSPORT: streamable-http
|
|
MCP_HOST: 0.0.0.0
|
|
MCP_PORT: "8000"
|
|
|
|
# If you run MetaMCP or another gateway in front and reach
|
|
# this container via its compose DNS name (e.g. hvm-docs-mcp:8000),
|
|
# add that hostname here. "*" disables the rebind check entirely.
|
|
MCP_ALLOWED_HOSTS: "hvm-docs-mcp,localhost,127.0.0.1"
|
|
|
|
# Phase 6 — reranker sidecar (jina-reranker-v2-base via llama.cpp).
|
|
RERANK_URL: http://hvm-rerank:8080
|
|
RERANK_POOL: "200"
|
|
RERANK_TIMEOUT: "30"
|
|
|
|
# Phase 8 — hybrid retrieval (BM25 + dense + RRF).
|
|
# Eval on the HVM corpus (eval/results/baseline.md, 2026-05-22) shows
|
|
# BM25-default + reranker beats hybrid on every metric (MRR 0.920 vs
|
|
# 0.875). Leaving HYBRID_SEARCH off so search_docs runs BM25-first +
|
|
# reranker; dense is the fallback when BM25 finds nothing.
|
|
HYBRID_SEARCH: "false"
|
|
|
|
# Phase 10 — usage telemetry.
|
|
USAGE_LOG_DIR: /app/var/logs
|
|
USAGE_LOG_KEEP_DAYS: "90"
|
|
|
|
# Phase 12 — doc-bug submission gate. Off by default; on only
|
|
# in production after you've verified the endpoint contract.
|
|
DOC_BUG_SUBMIT_ENABLED: "false"
|
|
# DOC_BUG_API_URL: "https://docs-be.example.com/api/feedback"
|
|
volumes:
|
|
# Usage logs persist across container recreates.
|
|
- ./hvm-docs-mcp-logs:/app/var/logs
|
|
depends_on:
|
|
- hvm-rerank
|
|
labels:
|
|
# Watchtower polls *only* containers with this label set true.
|
|
com.centurylinklabs.watchtower.enable: "true"
|
|
networks:
|
|
- mcp
|
|
|
|
# Reranker sidecar — llama.cpp serving jina-reranker-v2-base.
|
|
# Requires GPU access; adjust runtime/devices for your hardware.
|
|
#
|
|
# For dev / CPU-only hosts, swap this service for scripts/rerank_server.py
|
|
# (sentence-transformers ms-marco-MiniLM-L-6-v2). Same /v1/rerank shape,
|
|
# ~500ms/batch on CPU vs ~50ms on GPU with the jina GGUF.
|
|
hvm-rerank:
|
|
image: ghcr.io/ggml-org/llama.cpp:server-cuda
|
|
container_name: hvm-rerank
|
|
restart: unless-stopped
|
|
# Mount the GGUF model from the host. Download from huggingface
|
|
# (gguf-org/jina-reranker-v2-base-multilingual-GGUF) first.
|
|
volumes:
|
|
- /path/to/models:/models:ro
|
|
command: >
|
|
--model /models/jina-reranker-v2-base.Q8_0.gguf
|
|
--reranking
|
|
--host 0.0.0.0
|
|
--port 8080
|
|
--n-gpu-layers 99
|
|
--ctx-size 4096
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
networks:
|
|
- mcp
|
|
|
|
# Watchtower — auto-pulls :latest on push.
|
|
# Only watches containers labeled `com.centurylinklabs.watchtower.enable=true`.
|
|
watchtower:
|
|
image: containrrr/watchtower:latest
|
|
container_name: watchtower
|
|
restart: unless-stopped
|
|
volumes:
|
|
- /var/run/docker.sock:/var/run/docker.sock
|
|
environment:
|
|
WATCHTOWER_POLL_INTERVAL: "300" # 5 min
|
|
WATCHTOWER_LABEL_ENABLE: "true"
|
|
WATCHTOWER_CLEANUP: "true" # remove old images after pull
|
|
# If your registry requires auth, mount a docker config:
|
|
# volumes:
|
|
# - ./registry-auth.json:/config.json:ro
|
|
networks:
|
|
- mcp
|
|
|
|
networks:
|
|
mcp:
|
|
driver: bridge
|