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>
3.1 KiB
3.1 KiB
Soybean yield trial — Missouri, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Missouri (MO)
- Year: 2024
- Plot ID: 2420181
- Cooperator: University of Missouri - Columbia
- Planted: 2024-05-31
- Harvested: 2024-10-07
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mo/2024/2420181
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Benson | Hill | BH39A232 | 63.6 | - | - | $667.80 |
| 2 | Lakeview | Farms | LVF3973 | 63.2 | - | - | $663.60 |
| 3 | AgVenture | AV39B2E | - | 62.9 | - | - | $660.45 |
| 4 | AgVenture | AV38A1E | - | 61.6 | - | - | $646.80 |
| 5 | Pioneer | P37A18E | - | 61.3 | - | - | $643.65 |
| 6 | Asgrow | AG36XF4 | - | 61.1 | - | - | $641.55 |
| 7 | Channel | 3823RXF | - | 60.9 | - | - | $639.45 |
| 8 | MCIA | 39C09 | - | 60.5 | - | - | $635.25 |
| 9 | Lakeview | Farms | Experimental | 59.7 | - | - | $626.85 |
| 10 | DonMario | Seeds | DM32F74 | 58.9 | - | - | $618.45 |
| 11 | DonMario | Seeds | DM38E54 | 58.8 | - | - | $617.40 |
| 12 | Asgrow | AG37XF1 | - | 58.6 | - | - | $615.30 |
| 13 | Benson | Hill | BH37Q218 | 58.5 | - | - | $614.25 |
| 14 | Benson | Hill | BX37C755 | 58.4 | - | - | $613.20 |
| 15 | NK | NK39-J2E3 | Enlist E3 ® | 58.3 | - | - | $612.15 |
| 16 | NuTech | Seed | 37N03E | 58.2 | - | - | $611.10 |
| 17 | Benson | Hill | BH35A233 | 58.0 | - | - | $609.00 |
| 18 | Pioneer | P34A98E | - | 57.8 | - | - | $606.90 |
| 19 | NuTech | Seed | 39N08E | 57.7 | - | - | $605.85 |
| 20 | Benson | Hill | BX38F550 | 57.6 | - | - | $604.80 |
| 21 | DonMario | Seeds | DM36F84S | 56.8 | - | - | $596.40 |
| 22 | Asgrow | AG38XF1 | - | 56.6 | - | - | $594.30 |
| 23 | Xitavo | XO | 3375E | 56.5 | - | - | $593.25 |
| 24 | Benson | Hill | BH37U221 | 56.4 | - | - | $592.20 |
| 25 | Benson | Hill | BH37U205 | 56.2 | - | - | $590.10 |
| 25 | Benson | Hill | BH37U222 | 56.2 | - | - | $590.10 |
| 27 | NuTech | Seed | 38N05E | 56.1 | - | - | $589.05 |
| 27 | Xitavo | XO | 3705E | 56.1 | - | - | $589.05 |
| 29 | Xitavo | XO | 3855E | 55.7 | - | - | $584.85 |
| 30 | Benson | Hill | BH35A231 | 55.6 | - | - | $583.80 |
| 30 | Asgrow | AG39XF3 | - | 55.6 | - | - | $583.80 |
| 32 | Lakeview | Farms | LVF3432 | 55.2 | - | - | $579.60 |
| 33 | NuTech | Seed | 36N06E | 54.7 | - | - | $574.35 |
| 34 | Xitavo | XO | 3655E | 54.6 | - | - | $573.30 |
| 35 | Brevant | B394EE | - | 54.1 | - | - | $568.05 |
| 35 | AgVenture | AV36B2E | - | 54.1 | - | - | $568.05 |
| 37 | Benson | Hill | BH37U206 | 53.4 | - | - | $560.70 |
| 38 | DonMario | Seeds | DM36E94 | 53.2 | - | - | $558.60 |
| 38 | Pioneer | P38A28E | - | 53.2 | - | - | $558.60 |
| 40 | NuTech | Seed | 34N02E | 52.5 | - | - | $551.25 |
| 41 | NuTech | Seed | 35N05E | 51.6 | - | - | $541.80 |
| 42 | Xitavo | XO | 3483E | 51.5 | - | - | $540.75 |
| 43 | Brevant | B364EE | - | 49.8 | - | - | $522.90 |
Top 5 by Yield: Hill (Benson) 63.6, Farms (Lakeview) 63.2, AV39B2E (AgVenture) 62.9, AV38A1E (AgVenture) 61.6, P37A18E (Pioneer) 61.3.