deploy: Drawbar compose snippet — first image is published

Image pushed to git.jpaul.io/justin/crop-chem-docs with three tags: :latest — Watchtower auto-pull target :a97107de4636 — commit-sha rollback pin :corpus-2026.05.24 — corpus-snapshot pin (prod-recommended) Drawbar compose snippet at deploy/drawbar-compose-snippet.md. Wires the container against the existing infra: - Ollama pool: 192.168.0.2:11434, 192.168.0.2:11435, 192.168.0.125:11434, 10.10.1.65:11434 - Reranker: http://10.10.1.65:8082 - HYBRID_SEARCH=true (production retrieval — BM25 + dense + rerank) - Exposes streamable-HTTP MCP on port 8000 Pull path uses git.jpaul.io (public hostname, CF-fronted; pull response bodies aren't capped). Push path uses 192.168.0.2:1234 (LAN endpoint, bypasses CF 100MB body cap). Same registry, different URLs — per the template gotcha doc. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 12:48:24 -04:00
parent 420b4fa2d8
commit 8766d73327
1 changed files with 102 additions and 0 deletions
@@ -0,0 +1,102 @@
+# Drawbar deploy — `crop-chem-docs` MCP server snippet
+
+Drop this into Drawbar's `docker-compose.yml`. Targets the existing
+trashpanda infra: Ollama pool on the LAN, `llama-rerank` container
+on Tesla P4, Cloudflare Tunnel out front.
+
+## Pre-reqs (one-time on the deploy host)
+
+1. **Login to the Gitea registry** so the host can pull:
+   ```bash
+   docker login git.jpaul.io -u justin   # PAT for password
+   ```
+2. **Ollama embed pool** reachable from this host (already up):
+   - `192.168.0.2:11434`, `192.168.0.2:11435` (Gitea-host GPUs)
+   - `192.168.0.125:11434` (Windows GPU)
+3. **Reranker** reachable (already up on trashpanda):
+   - `http://10.10.1.65:8082`
+
+## Compose service
+
+```yaml
+services:
+  crop-chem-docs:
+    image: git.jpaul.io/justin/crop-chem-docs:latest
+    # Or pin to an immutable tag for prod:
+    # image: git.jpaul.io/justin/crop-chem-docs:corpus-2026.05.24
+    container_name: crop-chem-docs
+    restart: unless-stopped
+    ports:
+      - "8001:8000"   # MCP server (streamable-http). Adjust host port.
+    environment:
+      # Embedder pool. Round-robined for parallel search.
+      OLLAMA_URL: "http://192.168.0.2:11434,http://192.168.0.2:11435,http://192.168.0.125:11434,http://10.10.1.65:11434"
+      # Reranker on trashpanda's Tesla P4.
+      RERANK_URL: "http://10.10.1.65:8082"
+      # Production retrieval: BM25 + dense fused, then reranked.
+      HYBRID_SEARCH: "true"
+      # Override docs URL shown to the LLM if needed (default is EPA PPLS portal).
+      # PRODUCT_DOCS_URL: "https://..."
+    labels:
+      # Watchtower auto-pulls :latest on update.
+      com.centurylinklabs.watchtower.enable: "true"
+
+  # Optional: if you want Watchtower to drive auto-updates of this
+  # container too, you already run watchtower elsewhere — just make
+  # sure this container has the label above set true.
+```
+
+## Test from the host
+
+```bash
+# Tool inventory (uses MCP's HTTP transport — adjust if you have a
+# different MCP client probe handy):
+curl -s http://localhost:8001/sse  # or whichever endpoint your
+                                   # client expects from streamable-http
+
+# Or exec into the container and run the stdio transport:
+docker exec -it crop-chem-docs \
+  python -m docs_mcp.server --transport stdio < /dev/null
+```
+
+## What the 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 |
+
+## Versioning
+
+Tags published by the Gitea Actions workflows:
+
+| 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 | Pin to a specific corpus snapshot in prod |
+
+The `:corpus-YYYY.MM.DD` tag is the right one for production —
+guarantees the running container has a known, frozen corpus that
+matches the labels you've validated against.
+
+## Updating the corpus
+
+Two paths:
+
+1. **Wait for the monthly cron** — 1st @ 06:00 UTC, full re-scrape
+   of Bayer + EPA PPLS, then reindex, then image push. Watchtower
+   pulls the new `:latest` automatically.
+2. **Trigger manually** in Gitea Actions UI → `Monthly corpus
+   refresh` → `Run workflow`. Optional `sources` input for
+   single-source refresh (e.g., `bayer` only).
+
+## Switching corpus scope
+
+The row-crop filter (corn/soybeans/wheat) is in
+`scrape/sources/epa_ppls.py` as `ROW_CROP_KEYWORDS`. Edit + push +
+let the next workflow run pick it up. Same for the registrant
+allowlist at `scrape/sources/epa_registrant_allowlist.json`.