justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add university-extension variety trials: Illinois VT + Iowa ICPT + Ohio OCPT (+123 trial docs)

Browse Source 
Independent third-party performance data — land-grant programs that test every
entered brand side-by-side with replication + LSD stats. This is the legitimate
way to get Pioneer / DEKALB / Brevant / Channel performance the corpus can't
scrape directly (data_type=trial, results[] shape; falls through the trial
chunker).

- illinois_vt_trials (30 docs, 1,392 rows) — U of Illinois VT. Per-region XLSX
  (openpyxl), corn + soy + WHEAT, 2024+2025. Rich per-site agronomic metadata;
  corn-following-corn vs -soybean kept distinct.
- iowa_icpt_trials (24 docs, 674 rows) — Iowa State ICPT. ASP.NET GridView
  (viewstate postback for year/district), corn + soy by district x season.
- ohio_ocpt_trials (69 docs, 4,647 rows) — OSU/CFAES OCPT. Report PDF
  (pdfplumber; per-site column groups split by header Yield-token count +
  x-coord footnote bucketing), corn + soy per site, 2024+2025.

91 distinct seed brands across the three; majors confirmed present in the
independent rankings: DEKALB 395, Golden Harvest 249, Channel 241, NK 212,
Xitavo 135, LG 103, Pioneer 88, Asgrow 59. (A brand only appears where it
ENTERED a given program — e.g. Brevant not in Iowa, DEKALB/Channel not in
Illinois — true negatives, not parse gaps.)

- rag/chunk.py: gated `include_region` on _render_gh_plot_chunk; the 3 university
  sources route through it so the region/district is in the embedded chunk +
  labeled "variety trial (cross-vendor, independent third-party)". Existing plot
  sources (gh/lg/agrigold/proharvest) unchanged.
- requirements.txt: openpyxl (Illinois XLSX; scrape-time only).
- sources.json + README/CLAUDE/lessons: registered + attributed; lessons
  trial-data + Pioneer entries updated (Pioneer/DEKALB performance now available
  indirectly via these trials).

Validation: all 123 chunk via rag.chunk.chunks_from_trial (0 errors), 0
out-of-range yields, 0 dup keys. Public land-grant data; attribution recorded in
each tos_note. CI rebuilds the index from the committed corpus.
This commit is contained in:
Claude (agent)
2026-06-10 08:35:50 -04:00
parent 0bac06b7b6
commit 54094a0d43
255 changed files with 105410 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -2
View File
@@ -10,7 +10,7 @@ vendors — **variety identity** (what each hybrid IS) plus **yield-trial data**
## What's in the corpus
**~9,200 indexed records** (one chunk each) across two complementary surfaces:
**~9,300 indexed records** (one chunk each) across two complementary surfaces:
### Variety identity — 2,398 records
@@ -30,7 +30,7 @@ vendors — **variety identity** (what each hybrid IS) plus **yield-trial data**
| `ebberts_seeds` | 29 | Ebbert's Seeds | Ebbert's (corn / soy / wheat) — independent E. Corn Belt breeder |
| `agripro` | 24 | Syngenta | AgriPro (wheat — HRW / HRS / HWS / SWW) |
### Yield-trial data — 6,787 documents
### Yield-trial data — 6,910 documents
| Source | Count | Notes |
|---|---|---|
@@ -38,8 +38,13 @@ vendors — **variety identity** (what each hybrid IS) plus **yield-trial data**
| `lg_plot_reports` | 1,307 | LG Seeds (AgReliant) cross-vendor plots, top-5 per site, 2024+2025. |
| `agrigold_plot_reports` | 1,006 | AgriGold (AgReliant) cross-vendor plots, full ranking + rich plot management, 2024+2025. |
| `proharvest_plots` | 161 | ProHarvest Seeds per-cooperator harvest reports (corn / soy, 2024+2025). Many are **cross-vendor** (ProHarvest / Apex vs Pioneer / DEKALB / Becks / Channel / Wyffels). Structured rank/yield/%H2O/test-wt where the PDF fits the template; off-template third-party reports kept verbatim. |
| `ohio_ocpt_trials` | 69 | **University-extension** trial (OSU/CFAES) — corn + soy per-site, 2024+2025. Independent third-party; ranks CHANNEL / DEKALB / NK / Golden Harvest / LG / AgriGold / Beck's etc. side-by-side. |
| `illinois_vt_trials` | 30 | **University-extension** trial (U of Illinois VT) — corn + soy + **wheat**, 2024+2025. Pioneer / NK + many regionals; rich per-site agronomic metadata. |
| `iowa_icpt_trials` | 24 | **University-extension** trial (Iowa State / ICPT) — corn + soy by district, 2024+2025. Pioneer / DEKALB / Asgrow / NK / Golden Harvest. |
| `agripro_trials` | 14 | Regional wheat trial PDF summaries (PNW, Western Plains, Northern Plains, etc.) |
> The three `*_trials` university sources are **independent third-party** performance data — land-grant programs that test every entered brand (incl. majors we can't catalog directly, like **Pioneer / DEKALB / Brevant**) side-by-side with replication + LSD stats. The publisher is the university; the seed brands live in each row's `brand`.
### Not in the corpus (documented in `docs_mcp/lessons.md`)
- **Pioneer / Corteva (all brands)** — ToS bans automation. This now covers the whole Corteva family — Pioneer, Brevant, **Hoegemeyer** (the consolidation brand absorbing Seed Consultants / Dairyland / Nu-Tech / Terral), and the upcoming Vylor spinoff — all share the same corteva.com ToU. Curated fallback lesson points the farmer at a local dealer; legitimate Corteva-data paths are an official license (openinnovation@corteva.com) or university-extension trial data.