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>
2.6 KiB
2.6 KiB
Soybean yield trial — North Dakota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: North Dakota (ND)
- Year: 2024
- Plot ID: 2438066
- Cooperator: NDSU - North Central Research Extension Center (Mohall)
- Planted: 2024-05-16
- Harvested: 2024-10-08
- Population: 150,000 seeds/acre
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/nd/2024/2438066
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Legacy | Seeds | LS0098-23 XF | 37.9 | - | 55.3 | $397.95 |
| 2 | LG Seeds | LGS0125XF | - | 35.4 | - | 55.8 | $371.70 |
| 3 | Golden Harvest | GH00864XF | XtendFlex ® | 35.2 | - | 54.9 | $369.60 |
| 4 | NK | NK006-Z5XF | XtendFlex ® | 34.0 | - | 55.3 | $357.00 |
| 5 | Thunder | Seed | TX85008 | 33.6 | - | 54.5 | $352.80 |
| 6 | Fortus | 0165E | - | 33.3 | - | 55.2 | $349.65 |
| 7 | Integra | Fortified | Seed XF0115 | 32.8 | - | 55.4 | $344.40 |
| 8 | Golden Harvest | GH0225XF | XtendFlex ® | 32.6 | - | 55.3 | $342.30 |
| 8 | Dak-Sota | DE54007 | - | 32.6 | - | 55.9 | $342.30 |
| 10 | Proseed | XF | 30-062 | 32.3 | - | 54.3 | $339.15 |
| 11 | Proseed | XF | 40-12 | 32.2 | - | 55.4 | $338.10 |
| 12 | NK | NK006-U6E3 | Enlist E3 ® | 31.5 | - | 55.4 | $330.75 |
| 13 | Xitavo | XO | 0094E | 31.4 | - | 55.8 | $329.70 |
| 14 | Thunder | Seed | TX83006 | 30.8 | - | 54.8 | $323.40 |
| 15 | Integra | Fortified | Seed XF0212 | 30.5 | - | 55.2 | $320.25 |
| 15 | Proseed | XF | 30-092N | 30.5 | - | 55.4 | $320.25 |
| 17 | Legacy | Seeds | LS034-24 XF | 30.3 | - | 54.7 | $318.15 |
| 18 | Legacy | Seeds | LS12-23 E | 30.2 | - | 55.5 | $317.10 |
| 19 | NK | NK008-P8XF | XtendFlex ® | 30.1 | - | 54.7 | $316.05 |
| 20 | Thunder | Seed | TX8402N | 30.0 | - | 55.4 | $315.00 |
| 21 | Proseed | EL | 50-063N | 28.9 | - | 55.0 | $303.45 |
| 22 | Xitavo | XO | 0315E | 28.3 | - | 54.8 | $297.15 |
| 23 | Xitavo | XO | 0234E | 27.1 | - | 55.0 | $284.55 |
| 24 | NDSU | ND21008GT20 | - | 26.9 | - | 55.8 | $282.45 |
| 25 | Legacy | Seeds | LS014-23 XF | 26.8 | - | 55.2 | $281.40 |
| 26 | Integra | Fortified | Seed XF0082 | 26.4 | - | 55.5 | $277.20 |
| 27 | Xitavo | XO | 0554E | 25.9 | - | 54.7 | $271.95 |
| 28 | NK | NK02-Y2XF | XtendFlex ® | 25.5 | - | 55.2 | $267.75 |
| 29 | Legacy | Seeds | LS024-23 XF | 24.9 | - | 56.1 | $261.45 |
| 30 | NDSU | ND17009GT | - | 23.4 | - | 57.3 | $245.70 |
Top 5 by Yield: Seeds (Legacy) 37.9, LGS0125XF (LG Seeds) 35.4, GH00864XF (Golden Harvest) 35.2, NK006-Z5XF (NK) 34.0, Seed (Thunder) 33.6.