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>
3.2 KiB
3.2 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: 2420198
- Cooperator: University of Missouri - Dexter
- Planted: 2024-04-24
- Harvested: 2024-10-04
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mo/2024/2420198
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Delta | Grow | DG43XF65STS | 93.8 | - | - | $984.90 |
| 2 | Delta | Grow | DG48XF70STS | 92.2 | - | - | $968.10 |
| 3 | Golden Harvest | GH4452XFS | XtendFlex ® STS ® | 92.1 | - | - | $967.05 |
| 4 | Golden Harvest | GH4944XFS | XtendFlex ® STS ® | 91.9 | - | - | $964.95 |
| 5 | Pioneer | P45A70LX | - | 91.7 | - | - | $962.85 |
| 6 | UniSouth | Genetics | USG 7461XFS | 90.7 | - | - | $952.35 |
| 7 | Axis | Seed | 4815XFS | 90.4 | - | - | $949.20 |
| 8 | Pioneer | P48Z70BLX | - | 89.4 | - | - | $938.70 |
| 9 | Delta | Grow | DG46XF54STS | 89.0 | - | - | $934.50 |
| 10 | Axis | Seed | 4613XF | 88.8 | - | - | $932.40 |
| 11 | Axis | Seed | 4625XFS | 87.8 | - | - | $921.90 |
| 12 | Channel | 4720RXF/SR | - | 86.5 | - | - | $908.25 |
| 13 | UniSouth | Genetics | USG 7463XF | 85.8 | - | - | $900.90 |
| 14 | Asgrow | AG40XF1 | - | 84.8 | - | - | $890.40 |
| 15 | UniSouth | Genetics | USG 7495XFS | 84.0 | - | - | $882.00 |
| 16 | Pioneer | P46A90LX | - | 83.8 | - | - | $879.90 |
| 17 | Channel | 3823RXF | - | 81.2 | - | - | $852.60 |
| 18 | Channel | 4823RXF/SR | - | 79.0 | - | - | $829.50 |
| 19 | Golden Harvest | GH4864XFS | XtendFlex ® STS ® | 78.5 | - | - | $824.25 |
| 20 | UniSouth | Genetics | USG 7435XFS | 78.4 | - | - | $823.20 |
| 21 | Asgrow | AG36XF4 | - | 78.1 | - | - | $820.05 |
| 21 | Asgrow | AG38XF1 | - | 78.1 | - | - | $820.05 |
| 21 | Asgrow | AG47XF2 | - | 78.1 | - | - | $820.05 |
| 24 | UniSouth | Genetics | USG 7474XFS | 77.6 | - | - | $814.80 |
| 25 | Axis | Seed | 4105XF | 77.2 | - | - | $810.60 |
| 26 | Axis | Seed | 4905XF | 76.0 | - | - | $798.00 |
| 27 | Asgrow | AG39XF3 | - | 73.8 | - | - | $774.90 |
| 28 | Asgrow | AG37XF1 | - | 69.3 | - | - | $727.65 |
| 29 | AgVenture | AV48B2E | - | 68.0 | - | - | $714.00 |
| 30 | Asgrow | AG44XF4 | - | 66.4 | - | - | $697.20 |
| 31 | Pioneer | P37A18E | - | 65.4 | - | - | $686.70 |
| 32 | Delta | Grow | DG49XF85STS | 64.4 | - | - | $676.20 |
| 33 | Pioneer | P44A91E | - | 63.0 | - | - | $661.50 |
| 34 | Delta | Grow | DG47XF90STS | 62.3 | - | - | $654.15 |
| 35 | Pioneer | P34A98E | - | 60.6 | - | - | $636.30 |
| 36 | Pioneer | P40A23E | - | 60.2 | - | - | $632.10 |
| 37 | Pioneer | P46A09E | - | 60.1 | - | - | $631.05 |
| 38 | AgVenture | AV47Y6E | - | 59.4 | - | - | $623.70 |
| 39 | AgVenture | AV45B2E | - | 59.2 | - | - | $621.60 |
| 40 | Benson | Hill | BH43Q207 | 59.1 | - | - | $620.55 |
| 41 | AgVenture | AV44B2E | - | 58.8 | - | - | $617.40 |
| 42 | Pioneer | P38A28E | - | 58.7 | - | - | $616.35 |
| 43 | Brevant | B364EE | - | 55.2 | - | - | $579.60 |
| 44 | Brevant | B394EE | - | 50.3 | - | - | $528.15 |
Top 5 by Yield: Grow (Delta) 93.8, Grow (Delta) 92.2, GH4452XFS (Golden Harvest) 92.1, GH4944XFS (Golden Harvest) 91.9, P45A70LX (Pioneer) 91.7.