justin
0e625553e5
CORPUS — 4,299 GH plot reports added (3,797 written + 502 from the
earlier slow run + 319 sitemap-listed URLs that 404'd as
discontinued). Combined with prior 760 varieties + 14 AgriPro
trials = 5,073 total chunks now indexed.
scrape/sources/gh_plot_reports.py — concurrency speedup:
- 4 worker threads (ThreadPoolExecutor), each with its own
requests.Session for connection-pool efficiency.
- Shared class-level rate limiter (0.25 sec between ANY two
requests across all threads). Net throughput ~4 req/sec —
well below any rate-limit threshold a public site enforces.
- Diagnosis vs original 1 req/sec: GH had ZERO rate limiting,
zero 429s, zero retries. The 1 sec self-throttle was just too
conservative. Bench:
1 worker / 1.0 sec throttle: ~0.4 plots/sec (190 min ETA)
4 workers / 0.25 sec throttle: ~3 plots/sec (~25 min actual)
rag/chunk.py — chunk size cap for nomic-embed-text's 2048-token
context window:
- Empirically tested: failure threshold is ~5,250 chars on
numeric-heavy trial chunks (chars/token ratio 2.4 vs 3.5 for
prose). Cap at 4,500 chars to be safely under at worst-case
2.2 chars/token.
- Applied to BOTH variety and trial chunks. Marked truncated
chunks with metadata.embed_truncated = True; FULL text stays
in the on-disk .md for get_page to return verbatim.
.gitea/workflows/{refresh,image-only}.yml — OLLAMA_URL pool
restructured for the 4 GPU-pinned endpoints. Bench (50-chunk
batches on nomic-embed-text):
.0.125:11434 (RTX 40-series) 242 embeds/sec ← weight ×4
.0.2:11436 (GPU-pinned) 108 embeds/sec ← weight ×2
.0.2:11435 (GPU-pinned) 72 embeds/sec ← weight ×1
localhost (TITAN X) 37 embeds/sec ← weight ×1
Weighting is done by listing the URL multiple times in
OLLAMA_URL since the embedder uses round-robin. .0.2:11434 is
explicitly EXCLUDED — it isn't pinned to a specific GPU.
Combined index rebuild for 5,073 chunks now finishes in ~3 min
(was 19+ on the single-endpoint pool).
Smoke tests:
✓ list_versions: 5,073 docs across 6 sources, 2 vendors, 6
brands, 4 crops (corn 2711, soy 2016, silage 223, wheat 123).
✓ search_trials({crop=corn, state=IA, year=2024}): 3 IA 2024
corn trials surfaced.
✓ search_trials("Phytophthora resistance soybean trial"): NK
NK43-W1XFS top-1 in LA 2024 trial (cross-vendor result).
✓ search_trials("AP Iliad Idaho wheat"): AgriPro Washington/N
Idaho 2025 trial surfaced.
✓ search_trials(product=DKC65-95): 3 corn trials containing
that hybrid in IL/IA 2024.
✓ search_trials(product=NK1701): 3 corn trials in AR/MS 2024.
✓ Product filter correctly returns EMPTY for products that
aren't in the corpus (DKC65-20 is a 2023 product; 2023 plots
deferred). Anti-hallucination contract preserved.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3.0 KiB
3.0 KiB
Soybean yield trial — Minnesota, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Minnesota (MN)
- Year: 2025
- Plot ID: 2467102
- Cooperator: Justin Tritz
- Planted: 2025-05-13
- Harvested: 2025-10-04
- Population: 145,000 seeds/acre
- Row width: 22"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mn/2025/2467102
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Golden Harvest | GH2292E3 | Enlist E3 ® | 67.6 | 10.3 | - | $709.80 |
| 2 | Dairyland | Seed | DSR-1505E | 66.2 | 10.4 | - | $695.10 |
| 3 | Asgrow | AG14XF4 | - | 65.2 | 10.0 | - | $684.60 |
| 4 | Golden Harvest | GH1124XF | XtendFlex ® | 65.1 | 10.1 | - | $683.55 |
| 5 | Golden Harvest | GH1323XF | XtendFlex ® | 65.0 | 10.3 | - | $682.50 |
| 5 | Golden Harvest | GH1762XF | XtendFlex ® | 65.0 | 10.2 | - | $682.50 |
| 7 | Brevant | B144EE | - | 63.9 | 9.9 | - | $670.95 |
| 8 | Golden Harvest | GH2004XF | XtendFlex ® | 63.8 | 10.0 | - | $669.90 |
| 9 | Dairyland | Seed | DSR-1601E | 63.6 | 10.4 | - | $667.80 |
| 10 | Golden Harvest | GH1762XF | XtendFlex ® | 63.4 | 10.6 | - | $665.70 |
| 11 | NK | NK08-Z4E3 | Enlist E3 ® | 62.5 | 10.0 | - | $656.25 |
| 12 | Golden Harvest | GH1886XF | XtendFlex ® | 62.4 | 10.2 | - | $655.20 |
| 12 | Golden Harvest | GH1614E3 | Enlist E3 ® | 62.4 | 10.1 | - | $655.20 |
| 12 | NK | NK16-Z6E3 | Enlist E3 ® | 62.4 | 10.1 | - | $655.20 |
| 15 | Golden Harvest | GH1762XF | XtendFlex ® | 62.3 | 10.3 | - | $654.15 |
| 16 | Dairyland | Seed | DSR-1150E | 62.2 | 10.4 | - | $653.10 |
| 16 | Golden Harvest | GH1006XF | XtendFlex ® | 62.2 | 10.5 | - | $653.10 |
| 18 | Dairyland | Seed | DSR-2067E | 61.9 | 10.9 | - | $649.95 |
| 19 | NK | NK11-A4E3 | Enlist E3 ® | 61.2 | 10.0 | - | $642.60 |
| 20 | Golden Harvest | GH1495E3 | Enlist E3 ® | 61.1 | 10.1 | - | $641.55 |
| 20 | Golden Harvest | GH1534E3S | Enlist E3 ® STS ® | 61.1 | 10.1 | - | $641.55 |
| 22 | Dairyland | Seed | DSR-1881E | 60.8 | 10.5 | - | $638.40 |
| 22 | Dairyland | Seed | DSR-1989E | 60.8 | 10.5 | - | $638.40 |
| 24 | Golden Harvest | GH1776E3 | Enlist E3 ® | 59.9 | 10.0 | - | $628.95 |
| 24 | NK | NK14-U5E3 | Enlist E3 ® | 59.9 | 10.0 | - | $628.95 |
| 26 | Golden Harvest | GH1194E3 | Enlist E3 ® | 59.7 | 10.2 | - | $626.85 |
| 27 | Xitavo | XO | 1632E | 58.5 | 10.0 | - | $614.25 |
| 27 | NK | NK07-G5E3 | Enlist E3 ® | 58.5 | 10.0 | - | $614.25 |
| 29 | Xitavo | XO | 1095E | 58.4 | 10.2 | - | $613.20 |
| 30 | Dairyland | Seed | DSR-1345E | 58.3 | 10.4 | - | $612.15 |
| 31 | Dairyland | Seed | DSR-1788E | 58.2 | 10.5 | - | $611.10 |
| 32 | Golden Harvest | GH0936E3 | Enlist E3 ® | 57.1 | 10.1 | - | $599.55 |
| 33 | Xitavo | XO | 1446E | 55.8 | 10.1 | - | $585.90 |
| 34 | Xitavo | XO | 1116E | 55.7 | 10.2 | - | $584.85 |
Top 5 by Yield: GH2292E3 (Golden Harvest) 67.6, Seed (Dairyland) 66.2, AG14XF4 (Asgrow) 65.2, GH1124XF (Golden Harvest) 65.1, GH1323XF (Golden Harvest) 65.0.