justin/crop-chem-docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(deploy): make deploy/ describe the deployment that actually exists (#8)

Browse Source 
Co-authored-by: claude <[email protected]>
This commit was merged in pull request #8.
This commit is contained in:
claude
2026-09-10 21:45:01 -04:00
committed by claude
parent 254c4df71d
commit 053884f9fb
4 changed files with 135 additions and 250 deletions
Download Patch File Download Diff File Expand all files Collapse all files
deploy/docker-compose.yml
+106 -93
View File
@@ -1,106 +1,119 @@
# Hosting stack for a docs MCP server.
# crop-chem-docs service block to MERGE into Drawbar's parent compose
# file at /home/justin/drawbar/drawbar-backend/docker-compose.yml on
# trashpanda (10.10.1.65).
#
# Replace <product> 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 is NOT a standalone stack — do not `docker compose up` this file
# on its own. The MCP is one service inside the Drawbar backend stack,
# where it is reached over the internal docker network as
# `chem-mcp:8080` by drawbar-backend-api (CHEM_MCP_BASE_URL). Its tools
# land in the advisor's catalog under the `chem:` prefix via the
# mcp_client multiplex. Sibling seed-mcp sits alongside it.
#
# This template assumes a reverse proxy / Cloudflare Tunnel terminates
# TLS in front of port 8000. Adjust if your infra differs.
# Keep this block in sync with the parent compose. It is a copy of what
# actually runs, so that this repo's deploy/ documents reality rather
# than an aspiration.
services:
# The MCP server. Watchtower auto-pulls on :latest changes.
<product>-docs-mcp:
image: <registry>/<owner>/<product>-docs-mcp:latest
container_name: <product>-docs-mcp
restart: unless-stopped
ports:
- "8000:8000"
# crop-chem-docs — ~4.1K US row-crop pesticide / herbicide labels
# (EPA PPLS + Bayer), ~219K chunks. The advisor consults it for label
# rates, REI/PHI and rotation restrictions. Chroma + BM25 indexes are
# baked into the image, so there's no cold-start corpus build, no DB
# and no auth.
chem-mcp:
# :latest, NOT a corpus- tag. Watchtower only re-pulls the tag the
# container is already running, and corpus-YYYY.MM.DD tags are minted
# once and never re-pushed — so pinning one while keeping the
# watchtower label makes the opt-in silently inert. That is how prod
# sat on the May 2026 corpus through two refreshes until 2026-09-10
# (Drawbar/drawbar-backend#339). To freeze a snapshot deliberately,
# pin the corpus tag AND drop the watchtower label.
image: git.jpaul.io/justin/crop-chem-docs:latest
environment:
PRODUCT_NAME: "<product>"
PRODUCT_DOCS_URL: "https://docs.example.com"
# 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. <product>-docs-mcp:8000),
# add that hostname here. "*" disables the rebind check entirely.
MCP_ALLOWED_HOSTS: "<product>-docs-mcp,localhost,127.0.0.1"
# Phase 6 — reranker sidecar (jina-reranker-v2-base via llama.cpp).
RERANK_URL: http://<product>-rerank:8080
RERANK_POOL: "200"
RERANK_TIMEOUT: "30"
# Phase 8 — hybrid retrieval (BM25 + dense + RRF). Set true
# only after the eval harness shows the dense-only path
# missing technical-term queries that BM25 catches.
HYBRID_SEARCH: "true"
# Phase 10 — usage telemetry.
USAGE_LOG_DIR: /app/var/logs
USAGE_LOG_KEEP_DAYS: "90"
volumes:
# Usage logs persist across container recreates.
- ./<product>-docs-mcp-logs:/app/var/logs
depends_on:
- <product>-rerank
MCP_PORT: "8080"
# DNS-rebinding protection rejects any Host header that isn't in
# its (empty by default) allowlist, with a 421. On an internal
# docker network the caller's Host is `chem-mcp:8080` — exactly
# what gets rejected. Safe to disable here: the container is
# `expose`d only, never published to a host port, so it is only
# reachable from inside the compose network.
#
# NOTE: this is the only knob this server has for it. There is no
# MCP_ALLOWED_HOSTS — the code does not read such a variable.
MCP_DISABLE_DNS_REBINDING_PROTECTION: "1"
# Query-time embeddings hit Ollama. Drawbar's own `ollama` compose
# service is commented out, so the image default
# (OLLAMA_URL=http://ollama:11434) does NOT resolve in this stack —
# this override is load-bearing, not cosmetic. Without it every
# search_docs call fails to embed its query.
OLLAMA_URL: ${CHEM_OLLAMA_URL:-http://host.docker.internal:11434}
EMBED_MODEL: ${CHEM_EMBED_MODEL:-nomic-embed-text}
# Not set here on purpose — these come from the image's ENV
# defaults (see Dockerfile) and are correct for this stack:
# PRODUCT_NAME=crop_chem
# HYBRID_SEARCH=true
# RERANK_URL=http://llama-rerank:8080
# Override any of them here if the stack's service names differ.
# Hybrid + rerank is the eval-validated config (MRR 0.672 vs 0.544
# for BM25 alone; see eval/results/with_rerank.md). Hybrid WITHOUT
# rerank is worse than BM25 alone — don't ship that combination.
extra_hosts:
- "host.docker.internal:host-gateway"
expose:
- "8080"
restart: unless-stopped
labels:
# Watchtower polls *only* containers with this label set true.
# Watchtower auto-pulls :latest on push from CI. The label is
# required because the Drawbar stack's watchtower runs in
# label-mode (WATCHTOWER_LABEL_ENABLE=true); it polls every 60s.
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.
<product>-rerank:
image: ghcr.io/ggml-org/llama.cpp:server-cuda
container_name: <product>-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
# ─── llama-rerank ────────────────────────────────────────────────────
#
# The reranker is a SHARED sidecar (chem-mcp and seed-mcp both use it),
# and it is not declared in the parent compose — it runs as a standalone
# container. See deploy/rerank-docker.md for how to stand it up.
#
# The gotcha: it must be attached to the `drawbar-backend_default`
# network or `RERANK_URL=http://llama-rerank:8080` resolves via public
# DNS to an unrelated IP and connection-refuses. The MCP then falls back
# to dense+BM25 SILENTLY — retrieval quality craters with no error in
# the log. This bit chem-mcp through 2026-05-25. To fix or re-fix:
#
# docker network connect drawbar-backend_default llama-rerank
#
# It is idempotent, but it does NOT survive the container being
# recreated. Better: bring llama-rerank into the parent compose so the
# attachment is declarative.
#
# Confirm it is actually engaged — the header says which mode ran:
#
# docker exec drawbar-backend-chem-mcp-1 python -c \
# "from docs_mcp.server import search_docs; \
# print(search_docs('soybean herbicide for waterhemp', k=2))"
#
# Expect `mode=hybrid-rrf+rerank`. If it reads `mode=hybrid-rrf`, the
# sidecar is unreachable and you are serving degraded results.
networks:
mcp:
driver: bridge
# ─── verifying a deploy ──────────────────────────────────────────────
#
# docker exec drawbar-backend-chem-mcp-1 python -c \
# "from docs_mcp.server import corpus_status; print(corpus_status())"
#
# Expect the label/chunk counts and the active feature flags. To confirm
# the transport itself, from the api container:
#
# docker exec drawbar-backend-api-1 python -c \
# "import urllib.request, json; \
# req=urllib.request.Request('http://chem-mcp:8080/mcp', \
# data=json.dumps({'jsonrpc':'2.0','id':1,'method':'initialize', \
# 'params':{'protocolVersion':'2025-06-18','capabilities':{}, \
# 'clientInfo':{'name':'smoke','version':'0'}}}).encode(), \
# headers={'Content-Type':'application/json', \
# 'Accept':'application/json, text/event-stream'}); \
# print(urllib.request.urlopen(req, timeout=15).status)"
#
# Expect 200.
deploy/drawbar-compose-snippet.md
-148
View File
@@ -1,148 +0,0 @@
# Drawbar deploy — `crop-chem-docs` MCP server snippet
Drop these two services into Drawbar's `docker-compose.yml`. Targets
the trashpanda stack: shared Docker network with the existing
Drawbar services + the Cloudflare Tunnel.
## Pre-reqs (one-time on the deploy host)
1. **Docker login to the Gitea registry:**
```bash
docker login git.jpaul.io -u justin # PAT for password
```
2. **NVIDIA Container Toolkit** — already installed on trashpanda
(the existing standalone `llama-rerank` container ran with
`--gpus all` fine).
3. **If a standalone `llama-rerank` container is already running**
(left over from earlier setup), remove it so the compose service
can bind the same name:
```bash
docker rm -f llama-rerank
```
## Compose services
```yaml
services:
# ---- Reranker sidecar -----------------------------------------
# jina-reranker-v2-base-multilingual via llama.cpp on the Tesla P4.
# Internal port only (no host port mapping needed — the MCP reaches
# it via Docker DNS). ~280 MB GPU VRAM at idle, ~500 MB during a
# 50-doc rerank. Co-exists fine with any other GPU users on the P4.
llama-rerank:
image: ghcr.io/ggml-org/llama.cpp:server-cuda
container_name: llama-rerank
restart: unless-stopped
command:
- "-hf"
- "gpustack/jina-reranker-v2-base-multilingual-GGUF:Q8_0"
- "--reranking"
- "--host"
- "0.0.0.0"
- "--port"
- "8080"
- "-ngl"
- "99" # offload all layers to GPU
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
# Model cache survives container recreates; first start downloads
# the GGUF (~280 MB) from HuggingFace.
volumes:
- llama-rerank-cache:/root/.cache/huggingface
networks:
- default
# ---- MCP server ------------------------------------------------
crop-chem-docs:
image: git.jpaul.io/justin/crop-chem-docs:corpus-2026.05.24
# :latest for dev / Watchtower auto-pull
container_name: crop-chem-docs
restart: unless-stopped
ports:
- "8001:8000" # MCP server (streamable-http). Adjust host port.
# No environment block needed — the image's defaults handle it:
# OLLAMA_URL=http://ollama:11434
# RERANK_URL=http://llama-rerank:8080
# HYBRID_SEARCH=true
# PRODUCT_NAME=crop_chem
# Override here only if your services have different names.
depends_on:
- llama-rerank
networks:
- default
labels:
com.centurylinklabs.watchtower.enable: "true"
volumes:
llama-rerank-cache:
```
## Note on the existing `ollama` service
The Dockerfile default is `OLLAMA_URL=http://ollama:11434` — that
assumes there's an `ollama` service in the same compose stack. If
trashpanda's Ollama is a host-mode process (not a compose service),
override the env in the `crop-chem-docs` block:
```yaml
environment:
OLLAMA_URL: "http://host.docker.internal:11434"
extra_hosts:
- "host.docker.internal:host-gateway"
```
Or just add Ollama itself to the compose stack as a sibling service.
## Test once both are up
```bash
docker compose up -d llama-rerank crop-chem-docs
# Wait ~10s for both to come up, then:
docker exec crop-chem-docs python -c \
"from docs_mcp.server import corpus_status; print(corpus_status())"
```
Expect: `# crop-chem-docs corpus status`, 4,159 labels, 216,467
chunks, BM25 db present, `RERANK_URL=http://llama-rerank:8080`,
`HYBRID_SEARCH=on`.
Then a live search to verify hybrid+rerank:
```bash
docker exec crop-chem-docs python -c \
"from docs_mcp.server import search_docs; print(search_docs('soybean herbicide for waterhemp', k=2))"
```
Expect: 2 hits with Sencor/Tackle/Warrant in top-2, `mode=hybrid-rrf+rerank` in the header.
## What the MCP container exposes
| Tool | What it does |
|---|---|
| `search_docs` | Hybrid+rerank pesticide-label search with optional filters |
| `get_page` | Full label markdown + metadata by `(source, source_key)` |
| `list_versions` | Discover sources, product classes, signal words, registrants |
| `corpus_status` | Counts + freshness; useful for health probes |
| `crop_chem_api_lessons` | Curated agronomy / label-handling knowledge — call before recommending |
## Tag scheme
| Tag | When | Use for |
|---|---|---|
| `:latest` | Every monthly refresh + every code push | Dev / Watchtower auto-pull |
| `:<sha12>` | Every build | Rollback pin |
| `:corpus-YYYY.MM.DD` | Every build | **Production pin** (frozen corpus version) |
## Updating the corpus
- **Monthly cron** — 1st @ 06:00 UTC, full re-scrape of Bayer + EPA PPLS,
reindex, image push. Watchtower pulls the new `:latest` automatically.
- **Manual** — Gitea Actions UI → `Monthly corpus refresh` → `Run workflow`.
Optional `sources` input for single-source refresh (e.g., `bayer` only).
deploy/rerank-docker.md
+25 -5
View File
@@ -34,13 +34,33 @@ later co-host it.
## Configure the MCP server
```bash
export RERANK_URL=http://10.10.1.65:8082
# search_docs now reranks the hybrid pool through the GPU before returning
In production the MCP reaches this sidecar **over the Drawbar compose
network by service name**, not by host IP — `RERANK_URL` is baked into
the image as:
```
RERANK_URL=http://llama-rerank:8080
```
In production (the MetaMCP-fronted Drawbar deploy), this is baked
into the MCP server's container env.
so the deployed `chem-mcp` service sets nothing. See
`deploy/docker-compose.yml`.
That only resolves if the `llama-rerank` container is attached to
`drawbar-backend_default`. If it is on the default bridge network
instead, the name resolves via public DNS to an unrelated IP and
connection-refuses — and `search_docs` falls back to dense+BM25
**silently**. Attach it with:
```bash
docker network connect drawbar-backend_default llama-rerank
```
For local dev outside that network, point at the published port
directly:
```bash
export RERANK_URL=http://10.10.1.65:8082
```
## Verify