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>
2.5 KiB
2.5 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: 2469663
- Cooperator: Lee Vandergeest
- Planted: 2025-05-15
- Harvested: 2025-10-02
- Population: 32,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2469663
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 | E085Z5-D | - | 27.5 | 3695.0 | 30514.0 | 272.0 | 1930.0 |
| 2 | Channel | 186-56STX | - | 27.1 | 3368.0 | 27357.0 | 232.0 | 1782.0 |
| 3 | DEKALB | DKC39-55 | - | 26.9 | 3442.0 | 27825.0 | 252.0 | 1832.0 |
| 4 | Pioneer | P87040PCE | - | 26.5 | 3484.0 | 27659.0 | 244.0 | 1776.0 |
| 5 | Brevant | B87D33Q | - | 26.3 | 3497.0 | 27610.0 | 258.0 | 1805.0 |
| 6 | Pioneer | P8602AM | - | 25.9 | 3279.0 | 25495.0 | 224.0 | 1683.0 |
| 7 | Pioneer | P90630AM | - | 25.4 | 3378.0 | 25791.0 | 242.0 | 1701.0 |
| 8 | DEKALB | DKC36-48 | - | 25.0 | 3398.0 | 25496.0 | 236.0 | 1656.0 |
| 8 | Brevant | B89A44PCE | - | 25.0 | 3703.0 | 27756.0 | 270.0 | 1746.0 |
| 10 | NK | NK9231-AA | - | 23.0 | 3684.0 | 25448.0 | 271.0 | 1610.0 |
| 11 | Brevant | B91K05Q | - | 22.9 | 3639.0 | 24986.0 | 260.0 | 1574.0 |
| 12 | Brevant | B86J43AM | - | 22.3 | 3753.0 | 25119.0 | 279.0 | 1582.0 |
| 13 | DEKALB | DKC093-05 | - | 21.9 | 3548.0 | 23265.0 | 254.0 | 1489.0 |
| 14 | NK | NK9400-V | - | 21.1 | 3508.0 | 22205.0 | 254.0 | 1437.0 |
| 15 | DEKALB | DKC45-74 | - | 20.9 | 3453.0 | 21604.0 | 277.0 | 1473.0 |
| 16 | Brevant | B92D25Q | - | 20.4 | 3502.0 | 21430.0 | 274.0 | 1434.0 |
| 17 | DEKALB | DKC092-13 | - | 20.1 | 3260.0 | 19676.0 | 272.0 | 1410.0 |
| 18 | Enogen | E092W5-D | - | 19.9 | 3591.0 | 21430.0 | 262.0 | 1372.0 |
| 18 | Enogen | E094Z4-D | - | 19.9 | 3777.0 | 22566.0 | 274.0 | 1399.0 |
| 20 | Channel | 192-10STX | - | 19.4 | 3404.0 | 19854.0 | 239.0 | 1293.0 |
| 20 | Enogen | E095D3-D | - | 19.4 | 3487.0 | 20330.0 | 250.0 | 1317.0 |
| 22 | Brevant | B96M56PCE | - | 18.0 | 3578.0 | 19283.0 | 256.0 | 1228.0 |
| 23 | Brevant | B95R21V | - | 17.7 | 3553.0 | 18831.0 | 260.0 | 1215.0 |
| 24 | Pioneer | P9624AM | - | 16.9 | 3576.0 | 18146.0 | 261.0 | 1166.0 |
Top 5 by Ton/Acre: E085Z5-D (Enogen) 27.5, 186-56STX (Channel) 27.1, DKC39-55 (DEKALB) 26.9, P87040PCE (Pioneer) 26.5, B87D33Q (Brevant) 26.3.