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: 2420199
- Cooperator: University of Missouri - Fisk
- Planted: 2024-04-25
- Harvested: 2024-10-03
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mo/2024/2420199
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Channel | 3823RXF | - | 93.4 | - | - | $980.70 |
| 2 | Asgrow | AG36XF4 | - | 92.5 | - | - | $971.25 |
| 3 | AgVenture | AV47Y6E | - | 88.1 | - | - | $925.05 |
| 4 | Delta | Grow | DG47XF90STS | 87.0 | - | - | $913.50 |
| 5 | AgVenture | AV48B2E | - | 85.4 | - | - | $896.70 |
| 5 | Channel | 4720RXF/SR | - | 85.4 | - | - | $896.70 |
| 7 | Delta | Grow | DG49XF85STS | 84.3 | - | - | $885.15 |
| 8 | Delta | Grow | DG48XF70STS | 82.5 | - | - | $866.25 |
| 9 | Asgrow | AG44XF4 | - | 82.2 | - | - | $863.10 |
| 10 | AgVenture | AV44B2E | - | 81.3 | - | - | $853.65 |
| 11 | UniSouth | Genetics | USG 7474XFS | 81.2 | - | - | $852.60 |
| 12 | Axis | Seed | 4815XFS | 81.0 | - | - | $850.50 |
| 13 | UniSouth | Genetics | USG 7463XF | 80.9 | - | - | $849.45 |
| 14 | AgVenture | AV45B2E | - | 79.1 | - | - | $830.55 |
| 14 | UniSouth | Genetics | USG 7461XFS | 79.1 | - | - | $830.55 |
| 16 | Pioneer | P48Z70BLX | - | 78.6 | - | - | $825.30 |
| 17 | Asgrow | AG37XF1 | - | 78.5 | - | - | $824.25 |
| 18 | Delta | Grow | DG46XF54STS | 78.4 | - | - | $823.20 |
| 19 | Asgrow | AG40XF1 | - | 77.9 | - | - | $817.95 |
| 20 | Brevant | B394EE | - | 77.5 | - | - | $813.75 |
| 21 | Pioneer | P45A70LX | - | 77.4 | - | - | $812.70 |
| 22 | Golden Harvest | GH4452XFS | XtendFlex ® STS ® | 77.0 | - | - | $808.50 |
| 23 | Pioneer | P44A91E | - | 76.8 | - | - | $806.40 |
| 24 | Pioneer | P40A23E | - | 76.7 | - | - | $805.35 |
| 25 | Pioneer | P37A18E | - | 76.4 | - | - | $802.20 |
| 26 | Axis | Seed | 4613XF | 76.3 | - | - | $801.15 |
| 27 | Pioneer | P46A90LX | - | 76.2 | - | - | $800.10 |
| 28 | UniSouth | Genetics | USG 7495XFS | 75.8 | - | - | $795.90 |
| 29 | Asgrow | AG38XF1 | - | 75.7 | - | - | $794.85 |
| 30 | Asgrow | AG47XF2 | - | 75.6 | - | - | $793.80 |
| 31 | Channel | 4823RXF/SR | - | 74.2 | - | - | $779.10 |
| 32 | Golden Harvest | GH4944XFS | XtendFlex ® STS ® | 73.3 | - | - | $769.65 |
| 33 | Golden Harvest | GH4864XFS | XtendFlex ® STS ® | 73.1 | - | - | $767.55 |
| 34 | Asgrow | AG39XF3 | - | 73.0 | - | - | $766.50 |
| 35 | Axis | Seed | 4105XF | 72.1 | - | - | $757.05 |
| 36 | Pioneer | P46A09E | - | 72.0 | - | - | $756.00 |
| 37 | Brevant | B364EE | - | 70.7 | - | - | $742.35 |
| 38 | Benson | Hill | BH43Q207 | 70.6 | - | - | $741.30 |
| 39 | UniSouth | Genetics | USG 7435XFS | 70.4 | - | - | $739.20 |
| 40 | Axis | Seed | 4905XF | 69.6 | - | - | $730.80 |
| 41 | Axis | Seed | 4625XFS | 68.5 | - | - | $719.25 |
| 42 | Pioneer | P34A98E | - | 64.2 | - | - | $674.10 |
| 43 | Delta | Grow | DG43XF65STS | 63.8 | - | - | $669.90 |
| 44 | Pioneer | P38A28E | - | 62.9 | - | - | $660.45 |
Top 5 by Yield: 3823RXF (Channel) 93.4, AG36XF4 (Asgrow) 92.5, AV47Y6E (AgVenture) 88.1, Grow (Delta) 87.0, AV48B2E (AgVenture) 85.4.