Phase 4-5: deployable container + corpus snapshot + CI fixes

deploy/docker-compose.yml — replace <product>/<registry> placeholders
with concrete values for Drawbar's stack:
- image: git.jpaul.io/justin/seed-mcp:latest (CF tunnel for pulls; CI
  pushes via LAN 192.168.0.2:1234 to avoid 100 MB body cap)
- container_name: seed-mcp
- port 8001:8000 (8001 host-side to not collide with crop-chem-docs
  on 8000)
- PRODUCT_NAME=crop_seed, hybrid search enabled, stateless HTTP
- llama-rerank shared with crop-chem-docs (NOT redefined here —
  expected to already be in Drawbar's parent compose network)
- networks.drawbar-mcp external: true so seed-mcp joins the existing
  cross-MCP shared network

.gitignore — corpus/ is now COMMITTED, not ignored. The monthly
refresh workflow scrapes and commits corpus changes; the image-only
workflow rebuilds indexes from the committed corpus. Allowing the
corpus to flow through git means the :corpus-YYYY.MM.DD image tag
pins to a specific seed-catalog snapshot. chroma/ and bm25/ remain
ignored — those are deterministically derived from corpus.

Initial committed snapshot: 614 varieties.
- bayer_seeds: 475 (DEKALB 288 + Asgrow 102 + WestBred 85)
- golden_harvest: 139 (Syngenta corn + soy; 36 sitemap URLs
  302-redirected = discontinued)

rag/chunk.py — normalize brand and crop to uppercase/lowercase in
Chroma metadata so cross-vendor brand-filter lookups don't break on
casing inconsistency (Bayer stores "DEKALB", Golden Harvest stores
"Golden Harvest"; _build_where uppercases user-supplied brand which
matched the former but not the latter pre-fix). Sidecar JSON keeps
original casing for display.

Stub scrapers (nk, agripro, becks_pfr, becks_products) — change
return code from 2 to 0 so the monthly-refresh CI workflow doesn't
fail on deferred sources. Real implementations will return 0 on
success / 1 on failure when they ship.

Smoke-tested cross-vendor retrieval against the 614-chunk index:
- list_versions shows both vendors with correct facet counts
- broad "corn hybrid 100 RM" query returns both DEKALB and Golden
  Harvest hits in top 5
- brand='Golden Harvest' filter returns 3 GH-only varieties
- variety-code prefilter still works (E085Z5 → top hit on GH)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-25 13:40:05 -04:00
parent 9d4a490731
commit 75f714b454
1235 changed files with 284483 additions and 94 deletions
@@ -0,0 +1,151 @@
{
"source": "golden_harvest",
"source_key": "golden_harvest-gh1124xf",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"product_name": "GH1124XF",
"product_id": null,
"hybrid_prefix": "GH1124XF",
"hybrid_suffix": null,
"crop": "soybeans",
"release_year": null,
"relative_maturity": null,
"maturity_group": "1.1",
"wheat_class": null,
"trait_stack": [
"XF"
],
"trait_descriptions": [
"XtendFlex® (Roundup Ready 2 Xtend + dicamba + glufosinate)"
],
"positioning_statement": "Proven Genetics with a History of Stellar Performance",
"strengths": [],
"characteristics_groups": [
{
"label": "RECOMMENDED MANAGEMENT",
"type": "list",
"items": [
{
"characteristic": "Drought prone",
"value": "✓"
},
{
"characteristic": "High pH",
"value": "✓"
},
{
"characteristic": "Highly productive",
"value": "✓"
},
{
"characteristic": "Variable",
"value": "✓"
},
{
"characteristic": "Poorly drained",
"value": "✓"
}
]
},
{
"label": "PLANT CHARACTERISTICS",
"type": "table",
"items": [
{
"characteristic": "Plant height",
"value": "Medium-Tall"
},
{
"characteristic": "Canopy type",
"value": "Medium"
},
{
"characteristic": "Branching",
"value": "Moderate"
},
{
"characteristic": "Growth habit",
"value": "Indeterminate"
},
{
"characteristic": "Flower color",
"value": "Purple"
},
{
"characteristic": "Pubescence color",
"value": "Light Tawny"
},
{
"characteristic": "Pod color",
"value": "Tan"
},
{
"characteristic": "Hilum color",
"value": "Black"
},
{
"characteristic": "Chloride sensitivity",
"value": "Excluder"
}
]
},
{
"label": "AGRONOMIC CHARACTERISTICS",
"type": "table",
"items": [
{
"characteristic": "Seed size",
"value": "Large"
},
{
"characteristic": "Avg protein %",
"value": "36.1"
},
{
"characteristic": "Avg oil %",
"value": "19.0"
},
{
"characteristic": "Metribuzin response",
"value": "3"
},
{
"characteristic": "Sulfentrazone response",
"value": "3"
}
]
},
{
"label": "DISEASE AND PEST",
"type": "table",
"items": [
{
"characteristic": "Phytophthora root rot",
"value": "Rps3a"
},
{
"characteristic": "Soybean cyst nematode",
"value": "MR3"
},
{
"characteristic": "SCN source",
"value": "PI88788"
},
{
"characteristic": "RKNIncognita",
"value": "-"
}
]
}
],
"_scale_direction": "1-9 (9 = best)",
"regional_recommendations": [],
"image_url": null,
"techsheet_url": "https://assets.syngentaebiz.com/pdf/techsheets/GH1124XF_260310.pdf",
"source_urls": [
"https://www.goldenharvestseeds.com/products/soybean/gh1124xf"
],
"sitemap_last_modified": "2026-04-28",
"fetched_at": "2026-05-25T17:32:41.165765+00:00",
"scraper_version": "0.1.0"
}