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: 2469877
- Cooperator: Abel Dairy Farms LLC
- Planted: 2025-05-07
- Harvested: 2025-09-29
- Population: 34,000 seeds/acre
- Row width: 20"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2469877
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 | - | 37.5 | 3402.0 | 38222.0 | 268.0 | 2608.0 |
| 2 | Enogen | E107C1-D | - | 36.8 | 3233.0 | 35738.0 | 247.0 | 2483.0 |
| 3 | Enogen | E107C1-D | - | 36.6 | 3250.0 | 35732.0 | 251.0 | 2485.0 |
| 3 | Enogen | E111V7-D | - | 36.6 | 3295.0 | 36163.0 | 245.0 | 2456.0 |
| 5 | Enogen | E111V7-D | - | 36.5 | 3381.0 | 37024.0 | 264.0 | 2527.0 |
| 6 | Enogen | E111V7-D | - | 36.4 | 3468.0 | 37864.0 | 276.0 | 2568.0 |
| 7 | Enogen | E105Z5-D | - | 36.2 | 3231.0 | 35119.0 | 250.0 | 2452.0 |
| 8 | Enogen | E107C1-D | - | 36.1 | 3071.0 | 33240.0 | 213.0 | 2302.0 |
| 9 | Enogen | E105Z5-D | - | 35.9 | 3073.0 | 33138.0 | 218.0 | 2311.0 |
| 10 | Enogen | E105Z5-D | - | 35.7 | 3243.0 | 34738.0 | 257.0 | 2445.0 |
| 11 | Enogen | E107C1-D | - | 35.6 | 3354.0 | 35870.0 | 234.0 | 2352.0 |
| 11 | Enogen | E111V7-D | - | 35.6 | 3286.0 | 35090.0 | 242.0 | 2380.0 |
| 13 | Enogen | E111V7-D | - | 35.5 | 3398.0 | 36203.0 | 258.0 | 2436.0 |
| 14 | Enogen | E105Z5-D | - | 35.2 | 3309.0 | 34947.0 | 253.0 | 2396.0 |
| 15 | Enogen | E107C1-D | - | 35.1 | 3423.0 | 36031.0 | 254.0 | 2390.0 |
| 16 | Enogen | E105Z5-D | - | 34.9 | 3388.0 | 35484.0 | 265.0 | 2421.0 |
| 17 | Enogen | E111V7-D | - | 34.8 | 3232.0 | 33727.0 | 232.0 | 2287.0 |
| 18 | Enogen | E105Z5-D | - | 34.7 | 3394.0 | 35334.0 | 266.0 | 2409.0 |
| 18 | Enogen | E105Z5-D | - | 34.7 | 3227.0 | 33582.0 | 242.0 | 2320.0 |
| 20 | Enogen | E105Z5-D | - | 34.5 | 3357.0 | 34793.0 | 259.0 | 2371.0 |
| 21 | Enogen | E107C1-D | - | 33.8 | 3242.0 | 32877.0 | 241.0 | 2258.0 |
| 22 | Enogen | E105Z5-D | - | 33.6 | 3508.0 | 35354.0 | 260.0 | 2311.0 |
| 23 | Enogen | E111V7-D | - | 33.4 | 3490.0 | 34990.0 | 265.0 | 2317.0 |
| 24 | Enogen | E107C1-D | - | 33.2 | 3352.0 | 33397.0 | 246.0 | 2235.0 |
| 24 | Enogen | E111V7-D | - | 33.2 | 3249.0 | 32343.0 | 239.0 | 2209.0 |
| 26 | Enogen | E111V7-D | - | 32.2 | 3521.0 | 34059.0 | 263.0 | 2230.0 |
| 27 | Enogen | E107C1-D | - | 32.0 | 3404.0 | 32716.0 | 245.0 | 2154.0 |
Top 5 by Ton/Acre: E107C1-D (Enogen) 37.5, E107C1-D (Enogen) 36.8, E107C1-D (Enogen) 36.6, E111V7-D (Enogen) 36.6, E111V7-D (Enogen) 36.5.