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>
4.9 KiB
4.9 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: 2435169
- Cooperator: University of Delaware - Middletown Trial
- Planted: 2024-05-30
- Harvested: 2024-10-25
- Population: 150,000 seeds/acre
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/de/2024/2435169
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Revere | Seed | Revere 39-F94 XFS | 58.2 | 8.2 | 56.6 | $611.10 |
| 2 | AgVenture | AV39B2E | - | 53.0 | 7.9 | 56.6 | $556.50 |
| 3 | Xitavo | XO | 4364E | 51.5 | 8.4 | 58.0 | $540.75 |
| 4 | Mid-Atlantic | Seeds | MAS3723STS | 51.4 | 8.1 | 57.2 | $539.70 |
| 5 | APEX | AE3850 | - | 50.8 | 8.6 | 56.8 | $533.40 |
| 6 | UniSouth | Genetics | USG 7415ET | 50.4 | 8.4 | 57.7 | $529.20 |
| 7 | AgVenture | AV44B2E | - | 50.2 | 8.1 | 57.3 | $527.10 |
| 8 | Xitavo | XO | 4522E | 49.8 | 8.4 | 57.0 | $522.90 |
| 9 | UniSouth | Genetics | USG 7483XFS | 49.6 | 8.1 | 57.4 | $520.80 |
| 10 | Benson | Hill | N35D950S | 48.2 | 8.7 | 57.0 | $506.10 |
| 10 | UniSouth | Genetics | USG 7474XFS | 48.2 | 8.5 | 57.3 | $506.10 |
| 10 | Mid-Atlantic | Seeds | MAS3923E3/STS | 48.2 | 8.2 | 57.0 | $506.10 |
| 13 | UniSouth | Genetics | USG 7495XFS | 47.9 | 8.5 | 57.6 | $502.95 |
| 14 | NK | NK44-Q5E3S | Enlist E3 ® STS ® | 47.7 | 8.4 | 57.5 | $500.85 |
| 15 | Seed | Consultants | SC7485E | 47.6 | 8.1 | 57.4 | $499.80 |
| 16 | Benson | Hill | BH37Q218 | 47.5 | 8.9 | 57.6 | $498.75 |
| 16 | Mid-Atlantic | Seeds | MAS3525E3 | 47.5 | 7.9 | 56.1 | $498.75 |
| 18 | Seed | Consultants | SC7444E | 47.4 | 8.4 | 57.7 | $497.70 |
| 19 | Catalyst | CT4413E3S | Enlist E3 ® STS ® | 47.3 | 8.3 | 57.8 | $496.65 |
| 20 | UniSouth | Genetics | USG 7434XF | 46.7 | 8.2 | 58.1 | $490.35 |
| 21 | Innvictis | Seed | Solutions B4904E | 45.7 | 8.3 | 56.9 | $479.85 |
| 22 | Xitavo | XO | 4132E | 45.3 | 8.6 | 56.8 | $475.65 |
| 23 | Mid-Atlantic | Seeds | MAS4320E3/STS | 45.2 | 8.8 | 57.2 | $474.60 |
| 24 | Benson | Hill | BX38C615 | 44.9 | 8.4 | 56.6 | $471.45 |
| 25 | UniSouth | Genetics | USG 7424ETS | 44.7 | 8.4 | 58.3 | $469.35 |
| 26 | Benson | Hill | C38H052S | 44.4 | 8.2 | 56.8 | $466.20 |
| 27 | Seed | Consultants | SC7465E | 44.0 | 8.0 | 58.0 | $462.00 |
| 28 | Innvictis | Seed | Solutions B4553E | 43.8 | 8.2 | 57.3 | $459.90 |
| 28 | AgVenture | AV43B2BE | - | 43.8 | 8.0 | 57.7 | $459.90 |
| 30 | Innvictis | Seed | Solutions B4574E | 43.7 | 8.2 | 58.4 | $458.85 |
| 31 | Revere | Seed | Revere 44-F44 XFS | 43.6 | 8.5 | 57.3 | $457.80 |
| 31 | AgVenture | AV45B2E | - | 43.6 | 8.0 | 58.1 | $457.80 |
| 33 | Mid-Atlantic | Seeds | MAS4623E3/STS | 43.3 | 8.9 | 57.4 | $454.65 |
| 34 | Mid-Atlantic | Seeds | MAS4045E3 | 43.2 | 8.4 | 57.3 | $453.60 |
| 34 | AgVenture | AV48B2E | - | 43.2 | 8.0 | 57.6 | $453.60 |
| 36 | Xitavo | XO | 4255E | 43.1 | 8.1 | 57.9 | $452.55 |
| 37 | Innvictis | Seed | Solutions B3934E | 42.9 | 8.6 | 57.8 | $450.45 |
| 38 | UniSouth | Genetics | USG 7435ET | 42.8 | 8.4 | 58.6 | $449.40 |
| 39 | Public | P41MO21 | - | 42.6 | 8.3 | 58.1 | $447.30 |
| 39 | AgVenture | AV38B2E | - | 42.6 | 8.1 | 56.9 | $447.30 |
| 41 | AgVenture | AV47B2BE | - | 42.3 | 7.9 | 57.9 | $444.15 |
| 42 | APEX | AE4341S | - | 42.1 | 8.5 | 58.4 | $442.05 |
| 43 | Xitavo | XO | 4405E | 42.0 | 8.1 | 57.9 | $441.00 |
| 44 | NK | NK47-G5E3S | Enlist E3 ® STS ® | 41.7 | 8.2 | 57.9 | $437.85 |
| 44 | UniSouth | Genetics | USG 7494ETS | 41.7 | 8.5 | 58.2 | $437.85 |
| 46 | Mid-Atlantic | Seeds | MAS4021E3 | 41.6 | 8.5 | 57.1 | $436.80 |
| 47 | NK | NK42-A6E3S | Enlist E3 ® STS ® | 40.7 | 8.4 | 57.8 | $427.35 |
| 48 | Mid-Atlantic | Seeds | MAS4723E3 | 39.8 | 8.6 | 57.8 | $417.90 |
| 49 | Revere | Seed | Revere 46-F57 XFS | 39.1 | 8.4 | 57.6 | $410.55 |
| 50 | Benson | Hill | N44D923S | 38.8 | 8.9 | 57.8 | $407.40 |
| 51 | Benson | Hill | BH43Q207 | 38.5 | 8.8 | 57.4 | $404.25 |
| 52 | Mid-Atlantic | Seeds | MAS4423E3 | 37.5 | 8.6 | 57.9 | $393.75 |
| 53 | Mid-Atlantic | Seeds | MAS4675E3/STS | 37.3 | 8.6 | 57.8 | $391.65 |
| 54 | Benson | Hill | C44H054S | 36.8 | 8.7 | 57.1 | $386.40 |
| 55 | APEX | AE4640S | - | 36.6 | 8.5 | 58.0 | $384.30 |
| 56 | Mid-Atlantic | Seeds | MAS4215E3 | 36.0 | 7.8 | 58.5 | $378.00 |
| 57 | UniSouth | Genetics | USG 7485ETS | 35.8 | 8.3 | 58.4 | $375.90 |
| 58 | Innvictis | Seed | Solutions A5284XF | 34.8 | 8.6 | 57.8 | $365.40 |
| 58 | Mid-Atlantic | Seeds | MAS4823E3/STS | 34.8 | 8.6 | 58.3 | $365.40 |
| 60 | Public | P48MO21 | - | 29.5 | 9.0 | 58.2 | $309.75 |
| 61 | Innvictis | Seed | Solutions A5994XF | 27.6 | 11.0 | 57.9 | $289.80 |
| 62 | Innvictis | Seed | Solutions A6314XF | 25.8 | 10.1 | 58.4 | $270.90 |
| 63 | Innvictis | Seed | Solutions A5813XF | 23.9 | 10.8 | 57.4 | $250.95 |
Top 5 by Yield: Seed (Revere) 58.2, AV39B2E (AgVenture) 53.0, XO (Xitavo) 51.5, Seeds (Mid-Atlantic) 51.4, AE3850 (APEX) 50.8.