justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
c737871c4ccb4f8f122354ac1bed3ef97bb036c6
seed-mcp/corpus/agripro_trials/agt-2025-np-perf-data-sd-web.md
T
justin c737871c4c Trial-data scrapers: gh_plot_reports + agripro_trials + search_trials tool 
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>
2026-05-25 15:19:03 -04:00

6.3 KiB
Raw Blame History

2025 Performance Summary, Syngenta Data

Trial data (verbatim from PDF)

2025 Performance Summary, Syngenta Data
South Dakota
2025 Yield bu/ac
South Dakota Protein Test Wt. Heading Height
Variety Avg. Agar Miller Northville Selby % lbs/bu 1-9 1-9
AgriPro HY141 59.4 35.8 57.6 72.0 72.1 15.9 57.1 5 6
SY Valda 56.8 35.3 63.3 61.2 67.3 16.0 58.2 5 5
AP Dagr 56.4 29.7 54.5 69.8 71.5 16.0 55.6 6 4
AgriPro HY155 56.2 31.1 57.3 65.6 70.9 16.9 57.6 5 6
AgriPro HY162 54.8 30.4 52.2 68.2 68.5 16.2 56.7 5 6
AP Iconic 54.1 29.0 52.0 68.9 66.4 17.0 56.3 5 6
AP Elevate 53.3 27.1 51.1 71.5 63.8 16.8 56.2 6 4
AP Murdock 48.5 29.8 46.6 51.0 66.7 17.5 57.1 4 4
AP Gunsmoke CL2 47.6 30.1 44.8 64.5 51.2 17.8 55.7 5 5
SY Ingmar 44.3 23.1 40.5 59.3 54.3 17.8 57.2 5 5
AP Revolution 43.0 31.5 35.7 38.9 66.1 17.3 57.9 4 4
LCS Trigger 63.5 34.0 67.6 77.8 74.6 15.2 58.1 6 6
ND Stampede 60.2 47.3 54.3 66.5 72.6 17.1 58.2 5 5
Brawn-SD 58.8 42.1 55.4 69.0 68.9 15.4 59.5 5 NA
WB9641 57.0 32.2 58.1 71.6 66.0 16.0 56.8 6 5
MN-Torgy 56.2 34.0 54.0 67.4 69.4 17.9 58.9 6 6
WB9645 55.9 37.5 51.3 67.2 67.6 16.1 56.8 7 6
Ascend-SD 54.7 33.2 51.1 66.3 68.3 16.9 57.7 6 8
Driver 52.0 30.9 44.4 70.2 62.5 16.7 57.4 5 7
WB9642 49.4 34.7 30.0 65.8 67.0 16.4 59.1 6 4
WB9590 42.6 41.3 25.8 50.4 52.9 17.9 57.1 4 4
Mean 53.7 33.7 50.3 64.4 66.3 16.7 57.4
LSD (5%) 8.4 7.1 9.9 5.8 1.0 2.4
CV (%) 9.7 9.9 9.0 13.0 4.3 2.6 1.2
No. of Locs. 4 2 2
Numbers in bold type are in the top yielding group and considered statistically similar.
Numerical ratings: Heading: 1= early; Height: 1 = short; Lodging: 1 = no lodging; Disease 1 = tolerant
These agronomic assessments are made by Syngenta scientists and reflect each variety’s relative performance within these characteristics through the 2025 crop year. Specific conditions may cause
variations within those characteristics. These relative protection values are based on current pest and disease populations. These have been known to shift periodically and may cause changes in specific
evaluations. Resistance to many other diseases and pests is sensitive to environmental conditions, plant development stages and the presence and intensity of other diseases which may result in specific
evaluation inconsistencies. This chart is updated annually to reflect the most current trends.
AgriPro hybrid wheat seed sold commercially contains 75-95% hybrid seed, as required by the Federal Seed Act. Plot trial data for AgriPro hybrids represents performance using seed lots with nearly
100% hybrid seed.
© 2025 Syngenta. AgriPro® and the Syngenta logo are trademarks of a Syngenta Group Company. 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. NP - 10/2025

Three-Year Performance Summary, Syngenta Data (2023-2025)
South Dakota
Yield Average bu/ac Economic Return1 Agronomics and Disease
Protein Test Wt. Gross Heading Height Lodging BLS FHB
Variety 3-yr 2-yr 2025 % lb/bu $/A Rank 1-9 1-9 1-9 1-9 1-9
AgriPro HY141 65.0 65.7 59.4 15.4 60.2 370.0 3 5 6 6 5 4
AP Dagr 63.1 62.5 56.4 15.6 59.8 364.2 10 6 4 5 4 5
AgriPro HY162 62.7 61.4 54.8 15.7 59.9 364.5 9 5 6 5 5 4
AP Iconic 62.2 62.1 54.1 16.2 60.1 368.4 5 5 6 3 4 4
SY Valda 62.2 62.5 56.8 16.1 60.5 368.3 6 5 5 5 4 4
AgriPro HY155 61.8 61.5 56.2 16.5 60.3 365.8 7 5 6 5 5 4
AP Elevate 61.6 60.9 53.3 16.3 60.2 364.9 8 6 4 3 4 4
AP Gunsmoke CL2 56.9 55.6 47.6 16.8 60.0 336.9 12 5 5 3 5 4
AP Murdock 53.1 54.7 48.5 16.9 60.2 314.3 13 4 4 4 4 4
AP Revolution 52.8 53.2 43.0 16.9 60.7 312.9 14 4 4 4 3 3
SY Ingmar 52.4 51.7 44.3 17.2 60.7 309.9 15 5 5 3 3 3
LCS Trigger 71.9 70.9 63.5 14.3 60.9 376.2 2 6 6 NA 4 NA
Brawn-SD 64.5 62.1 58.8 15.5 61.7 369.3 4 5 NA NA 4 5
Ascend-SD 64.4 62.5 54.7 16.7 60.8 381.2 1 6 8 7 3 4
Driver 60.5 58.5 52.0 16.3 60.5 358.1 11 5 7 NA NA NA
ND Stampede 60.2 5 5 5 4 5
WB9641 57.0 6 5 4 6 5
MN-Torgy 56.2 6 6 5 3 3
WB9645 55.9 7 6 5 6 5
WB9642 49.4 6 4 6 6 4
WB9590 42.6 4 4 2 6 6
Mean 61.0 60.4 53.7 16.2 60.4
LSD (5%) 4.3 4.5 8.4 0.7 0.4
CV (%) 7.7 7.9 9.74 0.8 2.2
No. of Locs. 10 8 4 6 6
Numbers in bold type are in the top yielding group and considered statistically similar.
Numerical ratings: Heading: 1= early; Height: 1 = short; Lodging: 1 = no lodging; Disease 1 = tolerant
2025 Locations: Agar, Miller, Northville, and Selby SD
2024 Locations: Agar, Roscoe, Northville, and Selby, SD
2023 Locations: Selby, and Webster, SD
1 Economic return calculated by using the three-year yield average multiplied by the average grain price ($5.12/bu). (+) 8 cents per 1/5th premium over 14% protein, (-) 10 cents
per 1/5 discount under 14% protein
These agronomic assessments are made by Syngenta scientists and reflect each variety’s relative performance within these characteristics through the 2025crop year. Specific conditions may cause variations
within those characteristics. These relative protection values are based on current pest and disease populations. These have been known to shift periodically and may cause changes in specific evaluations.
Resistance to many other diseases and pests is sensitive to environmental conditions, plant development stages and the presence and intensity of other diseases which may result in specific evaluation
inconsistencies. This chart is updated annually to reflect the most current trends.
AgriPro hybrid wheat seed sold commercially contains 75-95% hybrid seed, as required by the Federal Seed Act. Plot trial data for AgriPro hybrids represents performance using seed lots with nearly 100%
hybrid seed.
© 2025 Syngenta. AgriPro® and the Syngenta logo are trademarks of a Syngenta Group Company. 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. NP - 10/2025
Reference in New Issue View Git Blame Copy Permalink