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>
5.0 KiB
5.0 KiB
Soybean yield trial — Delaware, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Delaware (DE)
- Year: 2024
- Plot ID: 2435168
- Cooperator: University of Delaware - Dagsboro Trial
- Planted: 2024-06-03
- Harvested: 2024-10-30
- Population: 150,000 seeds/acre
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/de/2024/2435168
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Revere | Seed | Revere 39-F94 XFS | 87.4 | 12.8 | 55.2 | $917.70 |
| 2 | AgVenture | AV38B2E | - | 87.0 | 11.3 | 55.3 | $913.50 |
| 3 | Xitavo | XO | 4255E | 85.2 | 12.5 | 56.0 | $894.60 |
| 3 | AgVenture | AV39B2E | - | 85.2 | 11.3 | 54.8 | $894.60 |
| 5 | Mid-Atlantic | Seeds | MAS4423E3 | 85.0 | 11.9 | 55.8 | $892.50 |
| 6 | Mid-Atlantic | Seeds | MAS4045E3 | 84.2 | 12.1 | 55.8 | $884.10 |
| 7 | NK | NK42-A6E3S | Enlist E3 ® STS ® | 84.0 | 12.6 | 55.5 | $882.00 |
| 8 | UniSouth | Genetics | USG 7435ET | 83.5 | 11.8 | 55.8 | $876.75 |
| 9 | APEX | AE3850 | - | 83.3 | 12.5 | 55.8 | $874.65 |
| 10 | UniSouth | Genetics | USG 7424ETS | 83.2 | 12.0 | 56.4 | $873.60 |
| 10 | AgVenture | AV47B2BE | - | 83.2 | 11.9 | 56.2 | $873.60 |
| 12 | NK | NK44-Q5E3S | Enlist E3 ® STS ® | 82.9 | 11.2 | 55.7 | $870.45 |
| 13 | Seed | Consultants | SC7465E | 82.6 | 11.5 | 55.9 | $867.30 |
| 13 | Xitavo | XO | 4522E | 82.6 | 12.2 | 55.1 | $867.30 |
| 15 | APEX | AE4341S | - | 82.5 | 12.4 | 56.5 | $866.25 |
| 16 | Seed | Consultants | SC7444E | 82.3 | 12.1 | 56.1 | $864.15 |
| 17 | Xitavo | XO | 4364E | 82.2 | 11.3 | 56.0 | $863.10 |
| 18 | Mid-Atlantic | Seeds | MAS3723STS | 82.1 | 12.2 | 56.2 | $862.05 |
| 19 | Catalyst | CT4413E3S | Enlist E3 ® STS ® | 81.7 | 12.0 | 55.7 | $857.85 |
| 19 | Mid-Atlantic | Seeds | MAS4215E3 | 81.7 | 12.0 | 56.3 | $857.85 |
| 21 | AgVenture | AV43B2BE | - | 81.3 | 11.8 | 56.1 | $853.65 |
| 22 | UniSouth | Genetics | USG 7434XF | 81.1 | 12.5 | 56.5 | $851.55 |
| 23 | Mid-Atlantic | Seeds | MAS4723E3 | 81.0 | 12.1 | 55.6 | $850.50 |
| 24 | AgVenture | AV48B2E | - | 80.7 | 11.7 | 56.3 | $847.35 |
| 25 | Revere | Seed | Revere 44-F44 XFS | 80.3 | 11.4 | 55.8 | $843.15 |
| 26 | APEX | AE4640S | - | 80.2 | 12.1 | 56.1 | $842.10 |
| 26 | AgVenture | AV45B2E | - | 80.2 | 11.4 | 56.1 | $842.10 |
| 28 | Xitavo | XO | 4132E | 80.0 | 12.0 | 55.4 | $840.00 |
| 29 | UniSouth | Genetics | USG 7415ET | 79.9 | 11.4 | 55.5 | $838.95 |
| 30 | Innvictis | Seed | Solutions B4904E | 78.3 | 11.7 | 55.7 | $822.15 |
| 31 | Benson | Hill | BX38C615 | 77.7 | 11.6 | 55.0 | $815.85 |
| 32 | Xitavo | XO | 4405E | 77.1 | 12.1 | 56.1 | $809.55 |
| 33 | UniSouth | Genetics | USG 7483XFS | 77.0 | 11.0 | 55.9 | $808.50 |
| 33 | AgVenture | AV44B2E | - | 77.0 | 11.4 | 55.5 | $808.50 |
| 35 | Seed | Consultants | SC7485E | 76.6 | 10.9 | 55.5 | $804.30 |
| 35 | Innvictis | Seed | Solutions B3934E | 76.6 | 12.7 | 55.9 | $804.30 |
| 37 | Benson | Hill | BH37Q218 | 76.4 | 11.0 | 55.7 | $802.20 |
| 37 | UniSouth | Genetics | USG 7494ETS | 76.4 | 12.4 | 56.1 | $802.20 |
| 39 | Mid-Atlantic | Seeds | MAS3923E3/STS | 76.0 | 12.5 | 55.7 | $798.00 |
| 40 | Mid-Atlantic | Seeds | MAS4021E3 | 75.3 | 12.8 | 56.0 | $790.65 |
| 41 | NK | NK47-G5E3S | Enlist E3 ® STS ® | 75.1 | 11.9 | 55.5 | $788.55 |
| 42 | Mid-Atlantic | Seeds | MAS4675E3/STS | 74.4 | 12.2 | 55.5 | $781.20 |
| 43 | Mid-Atlantic | Seeds | MAS4623E3/STS | 74.3 | 11.8 | 55.5 | $780.15 |
| 44 | Benson | Hill | N35D950S | 73.8 | 12.6 | 59.3 | $774.90 |
| 45 | Mid-Atlantic | Seeds | MAS4320E3/STS | 73.1 | 11.9 | 58.6 | $767.55 |
| 46 | UniSouth | Genetics | USG 7485ETS | 72.9 | 11.9 | 56.0 | $765.45 |
| 47 | Public | P41MO21 | - | 72.7 | 12.4 | 54.6 | $763.35 |
| 47 | Mid-Atlantic | Seeds | MAS4823E3/STS | 72.7 | 11.7 | 55.7 | $763.35 |
| 49 | Innvictis | Seed | Solutions B4553E | 72.6 | 12.2 | 55.6 | $762.30 |
| 50 | UniSouth | Genetics | USG 7495XFS | 72.2 | 11.2 | 56.3 | $758.10 |
| 51 | Benson | Hill | C44H054S | 71.8 | 12.8 | 55.9 | $753.90 |
| 52 | Benson | Hill | C38H052S | 71.6 | 11.9 | 55.9 | $751.80 |
| 52 | UniSouth | Genetics | USG 7474XFS | 71.6 | 12.0 | 55.7 | $751.80 |
| 54 | Innvictis | Seed | Solutions B4574E | 71.5 | 11.6 | 56.3 | $750.75 |
| 55 | Mid-Atlantic | Seeds | MAS3525E3 | 70.3 | 12.0 | 55.3 | $738.15 |
| 56 | Innvictis | Seed | Solutions A5284XF | 70.2 | 11.5 | 56.0 | $737.10 |
| 57 | Benson | Hill | N44D923S | 70.1 | 12.2 | 55.6 | $736.05 |
| 58 | Benson | Hill | BH43Q207 | 68.1 | 12.9 | 56.2 | $715.05 |
| 59 | Revere | Seed | Revere 46-F57 XFS | 66.1 | 11.7 | 56.2 | $694.05 |
| 60 | Public | P48MO21 | - | 64.5 | 11.3 | 55.3 | $677.25 |
| 61 | Innvictis | Seed | Solutions A5813XF | 63.8 | 12.7 | 57.4 | $669.90 |
| 62 | Innvictis | Seed | Solutions A6314XF | 58.0 | 12.2 | 57.7 | $609.00 |
| 63 | Innvictis | Seed | Solutions A5994XF | 55.3 | 12.6 | 55.7 | $580.65 |
Top 5 by Yield: Seed (Revere) 87.4, AV38B2E (AgVenture) 87.0, XO (Xitavo) 85.2, AV39B2E (AgVenture) 85.2, Seeds (Mid-Atlantic) 85.0.