justin
c737871c4c
This PR introduces TRIAL data — yield-performance results from real
field trials — as a SEPARATE data type alongside variety identity.
The two are complementary:
search_docs → "What's the disease resistance of DKC62-08RIB?"
(variety identity — what it IS)
search_trials → "Which corn hybrid won the IA 2024 trials?"
(performance data — how it PERFORMED)
scrape/sources/gh_plot_reports.py — Golden Harvest plot reports
- 4,618 expected (2024+2025; 2023 deferred to a backfill pass).
- URL: /<crop>/plot-report/<state>/<year>/<plot_id>
- Cross-vendor: each plot lists products from multiple brands
(NK / DEKALB / Golden Harvest / Enogen / Pioneer / Channel) side
by side at one cooperator's field — the kind of independent
comparison data Bayer doesn't publish itself.
- Generic per-column metrics dict (Yield/MST/Test Weight/$/Ac for
corn+soy, Ton/Acre + Milk + Beef columns for silage).
- Politeness: 1 req/sec, retries on 429/5xx, no redirect-follow.
scrape/sources/agripro_trials.py — AgriPro regional trial PDFs
- 14 unique PDFs (38 sitemap links deduped) at /trials-data
- pdfplumber text extraction, region/year detection from filename
- Verbatim PDF text preserved in chunk body so variety + yield
number adjacency drives retrieval (AP Iliad's Aberdeen ID yield
matches a query about "AP Iliad Idaho yield")
rag/chunk.py — chunks_from_trial() dispatching by source
- Plot reports: identity preamble + Top-5 by primary metric + full
ranking table. Metric labels chosen from the data (corn/soy use
"Yield", silage uses "Ton/Acre").
- AgriPro PDFs: identity preamble + verbatim trial body inline so
per-location yields surface for region+variety queries.
- Variety chunks get data_type="variety" metadata; trial chunks get
data_type="trial". Single Chroma collection; the tool router
filters by data_type rather than maintaining two collections.
rag/index.py — dispatch by sidecar's data_type field
rag/bm25.py — new filter columns (data_type, year, state)
docs_mcp/server.py — sixth MCP tool: search_trials(crop?, state?,
year?, product?, k=10)
- Filters trial chunks via where={"data_type": "trial", ...}
- Optional product substring post-filter for "DKC62-08RIB Iowa 2024"
style searches
- search_docs now defaults to data_type="variety" so trial chunks
don't bleed into variety identity queries
- Tool docstring routes the agent: "use lookup_variety to verify
identity details on any trial winner you surface"
NK trial endpoint (/NKSeeds/wsProxy.asmx/GetPlotResult) is documented
as deferred — the ASMX-SOAP shape returned empty XML on initial
probe. Bayer per-variety yield data is not publicly indexed at all
— documented in the trial-scope note (DEKALB/Asgrow trial data flows
through Channel reps, not the web). AgRevival research books exist
as 10 large annual PDFs but are deferred (low ROI per parse).
Initial corpus shipped in this PR: 14 AgriPro trial PDFs. The 4,618
Golden Harvest plot reports are scraping in background and will be
added in a follow-up corpus-snapshot PR (~70 min ETA).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2.4 KiB
2.4 KiB
2025 Montana Summary, Three-Year Data
- Source: AgriPro (Syngenta) regional trial PDF
- Vendor: Syngenta
- Brand: AgriPro
- Crop: Wheat
- Data type: trial
- Region: Montana
- Year: 2025
- PDF: https://agriprowheat.com/sites/default/files/2025-08/Montana%202025%20web.pdf
- Index page: https://agriprowheat.com/trials-data
- Varieties listed: AP Solid, SY Monument, AP Sunbird, SY, LCS Steel AX, LCS Julep
Trial data (verbatim from PDF)
2025 Montana Summary, Three-Year Data
Syngenta Commercial Variety Wheat Performance Test, 2023-2025
3-Yr Combined 2-Yr Combined Combined Fort Benton, Conrad, Billings, Sawfly
Variety (2023-2025) (2024-2025) (2025) MT MT MT Protein Damage
Hard Red Yield Yield Yield TWT Yield Yield Yield % 1-9
Winter Wheat Bu/A Bu/A Bu/A Lb/Bu Bu/A Bu/A Bu/A
AP24 AX 63.4 62.1 71.8 61.3 59.5 47.0 109.0 12.2 5
AP Solid 63.4 61.9 71.6 63.9 58.7 43.0 113.1 13.4 4
SY Monument 62.5 62.5 72.9 61.6 58.9 42.4 117.3 12.1 5
AP Sunbird 61.5 61.8 70.7 61.1 61.7 38.9 111.4 12.6 6
AP18 AX 59.0 58.3 68.5 62.9 56.3 41.2 108.1 12.7 6
SY 517 CL2 53.4 53.1 63.4 56.3 55.4 33.7 101.2 13.9 5
Keldin 65.6 63.5 75.0 61.9 69.5 39.4 115.9 12.9 5
Bobcat 63.5 63.2 73.2 62.5 68.5 47.8 103.4 13.1 2
MT WarCat 61.4 59.5 69.7 62.9 58.6 42.3 108.4 13.2 3
Warhorse 57.9 55.3 64.5 54.8 57.1 32.8 103.6 14 2
WB4523 63.8 76.9 62.0 69.8 42.4 118.6 11.6 4
WB4483 60.0 68.4 54.8 61.0 35.9 108.1 13.8 5
StandClear CLP 59.2 68.2 62.6 61.2 39.7 103.8 13.2 5
Scorpio 56.9 68.1 53.6 61.9 34.2 108.2 12.5 6
WB4733 CLP 56.3 64.5 62.3 55.2 38.3 99.9 13.9 4
DG Ramsay 76.9 62.0 73.4 37.5 119.9 13 5
LCS Steel AX 75.2 62.7 62.0 44.4 119.2 12.2 5
4739AX 73.9 62.8 67.6 43.2 110.8 13.3 4
WB4510CLP 72.3 63.2 64.1 34.5 118.4 12.2 6
LCS Julep 69.9 63.2 62.8 39.1 107.9 13.4 5
Sawfly: Locations
1-2 = Excellent 2023 — Conrad and Fort Benton, MT
3-4 = Very Good 2024 — Billings, Chester, Conrad, and Fort Benton, MT
5 = Good 2025 — Billings, Conrad, and Fort Benton, MT
6-7 = Fair
8-9 = Poor
© 2025 Syngenta. All rights reserved. Reproduction expressly prohibited without written permission. Some or all of the varieties may be protected under one or more of the following: Plant Variety Protection, United
States Plant Patents and/or Utility Patents and may not be propagated or reproduced without authorization. AgriPro® and the Syngenta logo are trademarks of a Syngenta Group Company.