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>
2.4 KiB
2.4 KiB
Silage yield trial — Wisconsin, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Wisconsin (WI)
- Year: 2024
- Plot ID: 2419081
- Cooperator: Prairie Ag Services Inc
- Planted: 2024-05-06
- Harvested: 2024-09-12
- Population: 32,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2024/2419081
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | NK | NK0440-AT | - | 36.0 | 3501.0 | 37863.0 | 258.0 | 2471.0 |
| 2 | Enogen | E107C1-D | - | 35.1 | 3281.0 | 34585.0 | 234.0 | 2320.0 |
| 3 | NK | NK0440-AT | - | 34.7 | 3362.0 | 35001.0 | 235.0 | 2296.0 |
| 4 | Enogen | E095D3-D | - | 34.6 | 3631.0 | 37694.0 | 269.0 | 2416.0 |
| 5 | Enogen | E105Z5-D | - | 33.1 | 3679.0 | 36525.0 | 275.0 | 2331.0 |
| 6 | NK | NK9771-DV | - | 32.8 | 3494.0 | 34330.0 | 246.0 | 2204.0 |
| 7 | NK | NK9771-DV | - | 32.4 | 3521.0 | 34221.0 | 265.0 | 2246.0 |
| 8 | Enogen | E094Z4-D | - | 31.8 | 3252.0 | 30995.0 | 227.0 | 2073.0 |
| 9 | Enogen | E107C1-D | - | 31.0 | 3294.0 | 30634.0 | 239.0 | 2062.0 |
| 10 | Pioneer | P0275Q | - | 30.7 | 3428.0 | 31564.0 | 251.0 | 2082.0 |
| 11 | NK | NK0501-DV | - | 29.8 | 3488.0 | 31187.0 | 254.0 | 2032.0 |
| 12 | NK | NK0252-D | - | 29.7 | 3458.0 | 30770.0 | 243.0 | 1986.0 |
| 13 | NK | NK0252-D | - | 29.6 | 3453.0 | 30625.0 | 248.0 | 1997.0 |
| 14 | NK | NK0501-DV | - | 29.4 | 3320.0 | 29233.0 | 237.0 | 1946.0 |
| 15 | NK | NK9805-DV | - | 28.4 | 3285.0 | 28024.0 | 226.0 | 1854.0 |
| 16 | Enogen | E094Z4-D | - | 28.3 | 3186.0 | 27024.0 | 204.0 | 1777.0 |
| 17 | NK | NK9021-D | - | 27.3 | 3377.0 | 27617.0 | 253.0 | 1854.0 |
| 18 | Enogen | E095D3-D | - | 26.5 | 3270.0 | 25973.0 | 238.0 | 1758.0 |
| 19 | NK | NK9805-DV | - | 25.7 | 3449.0 | 26633.0 | 252.0 | 1749.0 |
| 20 | Enogen | E092W5-D | - | 25.0 | 3099.0 | 23267.0 | 199.0 | 1561.0 |
| 21 | Enogen | E105Z5-D | - | 24.6 | 3406.0 | 25163.0 | 250.0 | 1667.0 |
| 22 | NK | NK9021-D | - | 24.2 | 3335.0 | 24195.0 | 225.0 | 1574.0 |
| 23 | Pioneer | P0275Q | - | 22.3 | 3470.0 | 23192.0 | 255.0 | 1520.0 |
| 24 | Enogen | E092W5-D | - | 21.3 | 3242.0 | 20739.0 | 217.0 | 1371.0 |
Top 5 by Ton/Acre: NK0440-AT (NK) 36.0, E107C1-D (Enogen) 35.1, NK0440-AT (NK) 34.7, E095D3-D (Enogen) 34.6, E105Z5-D (Enogen) 33.1.