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, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Wisconsin (WI)
- Year: 2025
- Plot ID: 2466599
- Cooperator: Wayside Dairy Farms
- Planted: 2025-05-09
- Harvested: 2025-09-22
- Population: 32,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2466599
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Brevant | B96M56PCE | - | 29.6 | 3412.0 | 30319.0 | 249.0 | 2003.0 |
| 2 | Dairyland | Seed | HIDF-4545Q | 29.5 | 3363.0 | 29811.0 | 243.0 | 1980.0 |
| 3 | Brevant | B05D47V | - | 29.0 | 3398.0 | 29546.0 | 245.0 | 1946.0 |
| 4 | Enogen | E094Z4-D | - | 28.4 | 3590.0 | 30609.0 | 276.0 | 2006.0 |
| 5 | Dairyland | Seed | HIDF-4321V | 28.3 | 3269.0 | 27743.0 | 227.0 | 1848.0 |
| 6 | Beck's | 5212TCV2P | - | 28.0 | 3405.0 | 28586.0 | 246.0 | 1884.0 |
| 7 | Enogen | E097K6-D | - | 27.5 | 3274.0 | 27002.0 | 227.0 | 1794.0 |
| 8 | Pioneer | P9955V | - | 27.3 | 3505.0 | 28706.0 | 253.0 | 1858.0 |
| 9 | XL | 5324V | - | 27.0 | 3583.0 | 29000.0 | 267.0 | 1878.0 |
| 10 | Brevant | B99A24V | - | 26.8 | 3376.0 | 27192.0 | 244.0 | 1802.0 |
| 11 | Pioneer | P9884Q | - | 26.7 | 3422.0 | 27404.0 | 242.0 | 1785.0 |
| 11 | XL | 5332AM | - | 26.7 | 3326.0 | 26664.0 | 248.0 | 1803.0 |
| 13 | Pioneer | P96760V | - | 26.6 | 3426.0 | 27289.0 | 263.0 | 1836.0 |
| 13 | Dairyland | Seed | HIDF-4073Q | 26.6 | 3458.0 | 27558.0 | 257.0 | 1820.0 |
| 15 | Preceon | PR105-50 | - | 26.5 | 3362.0 | 26708.0 | 237.0 | 1756.0 |
| 16 | Preceon | PR102-50 | - | 26.3 | 3343.0 | 26413.0 | 238.0 | 1750.0 |
| 17 | Dairyland | Seed | HiDF-3522Q | 26.1 | 3351.0 | 26226.0 | 249.0 | 1765.0 |
| 17 | Preceon | PR104-60 | - | 26.1 | 3535.0 | 27729.0 | 265.0 | 1814.0 |
| 19 | Enogen | E107C1-D | - | 25.9 | 3083.0 | 23984.0 | 218.0 | 1668.0 |
| 20 | Dairyland | Seed | DB-4022Q | 25.8 | 3537.0 | 27346.0 | 269.0 | 1799.0 |
| 21 | Enogen | E102K7-D | - | 25.5 | 3564.0 | 27301.0 | 257.0 | 1748.0 |
| 22 | Enogen | E095D3-D | - | 25.1 | 3505.0 | 26418.0 | 257.0 | 1719.0 |
| 23 | Dairyland | Seed | DB-3434Q | 24.7 | 3569.0 | 26458.0 | 256.0 | 1690.0 |
Top 5 by Ton/Acre: B96M56PCE (Brevant) 29.6, Seed (Dairyland) 29.5, B05D47V (Brevant) 29.0, E094Z4-D (Enogen) 28.4, Seed (Dairyland) 28.3.