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>
2.7 KiB
2.7 KiB
Silage yield trial — Wisconsin, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Wisconsin (WI)
- Year: 2025
- Plot ID: 2465995
- Cooperator: Prairie Ag Services Inc
- Planted: 2025-05-07
- Harvested: 2025-09-17
- Population: 33,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2465995
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Enogen | E107C1-D | - | 32.1 | 3288.0 | 31694.0 | 239.0 | 2137.0 |
| 2 | NK | NK0025-DV | - | 29.4 | 3117.0 | 27478.0 | 211.0 | 1869.0 |
| 3 | NK | NK0604-DV | - | 28.9 | 3297.0 | 28583.0 | 218.0 | 1860.0 |
| 4 | NK | NK0604-DV | - | 28.6 | 3390.0 | 29080.0 | 244.0 | 1919.0 |
| 5 | Enogen | E105Z5-D | - | 27.9 | 3162.0 | 26466.0 | 221.0 | 1804.0 |
| 6 | DEKALB | DKC105-33 | - | 27.4 | 3055.0 | 25073.0 | 204.0 | 1720.0 |
| 7 | Enogen | E092W5-D | - | 27.3 | 3364.0 | 27544.0 | 251.0 | 1850.0 |
| 8 | Enogen | E095D3-D | - | 27.1 | 3053.0 | 24800.0 | 193.0 | 1672.0 |
| 8 | Enogen | E108K4-DV | - | 27.1 | 3141.0 | 25529.0 | 217.0 | 1741.0 |
| 10 | Enogen | E102K7-D | - | 26.9 | 3065.0 | 24755.0 | 205.0 | 1696.0 |
| 11 | Enogen | E107C1-D | - | 26.3 | 3303.0 | 26045.0 | 226.0 | 1712.0 |
| 12 | DEKALB | DKC105-33 | - | 26.2 | 3480.0 | 27362.0 | 263.0 | 1812.0 |
| 13 | NK | NK9771-DV | - | 26.1 | 3229.0 | 25284.0 | 229.0 | 1710.0 |
| 14 | Enogen | E102K7-D | - | 25.9 | 3159.0 | 24522.0 | 217.0 | 1663.0 |
| 14 | NK | NK0440-AT | - | 25.9 | 3285.0 | 25564.0 | 229.0 | 1699.0 |
| 16 | NK | NK0440-AT | - | 25.7 | 3196.0 | 24649.0 | 209.0 | 1631.0 |
| 17 | Enogen | E097K6-D | - | 25.6 | 3200.0 | 24578.0 | 240.0 | 1706.0 |
| 18 | Enogen | E105Z5-D | - | 24.8 | 3210.0 | 23919.0 | 209.0 | 1576.0 |
| 19 | NK | NK9771-DV | - | 23.9 | 3135.0 | 22472.0 | 211.0 | 1521.0 |
| 20 | Enogen | E094Z4-D | - | 23.3 | 2942.0 | 20604.0 | 181.0 | 1415.0 |
| 20 | NK | NK0025-DV | - | 23.3 | 3232.0 | 22576.0 | 248.0 | 1571.0 |
| 22 | Pioneer | P0275Q | - | 22.5 | 3325.0 | 22428.0 | 242.0 | 1503.0 |
| 23 | Enogen | E097K6-D | - | 22.3 | 3126.0 | 20887.0 | 209.0 | 1413.0 |
| 24 | Pioneer | P0275Q | - | 20.4 | 3293.0 | 20117.0 | 227.0 | 1329.0 |
| 25 | Enogen | E108K4-DV | - | 20.0 | 3374.0 | 20195.0 | 235.0 | 1320.0 |
| 26 | Enogen | E094Z4-D | - | 19.6 | 3147.0 | 18498.0 | 225.0 | 1274.0 |
| 27 | Enogen | E095D3-D | - | 19.3 | 3159.0 | 18300.0 | 230.0 | 1266.0 |
| 28 | Enogen | E092W5-D | - | 19.2 | 3165.0 | 18233.0 | 214.0 | 1227.0 |
Top 5 by Ton/Acre: E107C1-D (Enogen) 32.1, NK0025-DV (NK) 29.4, NK0604-DV (NK) 28.9, NK0604-DV (NK) 28.6, E105Z5-D (Enogen) 27.9.