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 — Utah, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Utah (UT)
- Year: 2024
- Plot ID: 2452509
- Cooperator: Holt Farms (Newcastle)
- Planted: 2024-05-10
- Harvested: 2024-09-10
- Population: 40,000 seeds/acre
- Row width: 22"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/ut/2024/2452509
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Axis | Seed | Experimental | 35.5 | 3383.0 | 34921.0 | 223.0 | 2378.0 |
| 2 | DEKALB | DKC092-14 | - | 34.9 | 3152.0 | 33659.0 | 217.0 | 2265.0 |
| 3 | Western | Hybrids | 2199 | 32.8 | 3517.0 | 32952.0 | 227.0 | 2229.0 |
| 4 | Pioneer | P9845AM | - | 32.7 | 3365.0 | 32160.0 | 223.0 | 2190.0 |
| 5 | Legacy | Seeds | LC451-21 VT2P | 32.0 | 3407.0 | 33273.0 | 227.0 | 2176.0 |
| 6 | DEKALB | DKC44-80 | - | 31.7 | 3410.0 | 31901.0 | 223.0 | 2122.0 |
| 6 | PGS | Hybrids | 4295 | 31.7 | 3650.0 | 33825.0 | 237.0 | 2250.0 |
| 6 | Western | Hybrids | 2196 | 31.7 | 3554.0 | 32528.0 | 230.0 | 2191.0 |
| 9 | DEKALB | DKC093-05 | - | 31.4 | 3669.0 | 34698.0 | 240.0 | 2263.0 |
| 10 | Pioneer | P0035AM | - | 31.2 | 3663.0 | 33309.0 | 233.0 | 2185.0 |
| 11 | NK | NK9771-DV | - | 30.9 | 3696.0 | 33160.0 | 237.0 | 2191.0 |
| 11 | DEKALB | DKC098-55 | - | 30.9 | 3676.0 | 34825.0 | 240.0 | 2224.0 |
| 13 | NK | NK9400-V | - | 30.6 | 3485.0 | 32000.0 | 227.0 | 2081.0 |
| 14 | PGS | Hybrids | 5898 | 30.2 | 3450.0 | 30799.0 | 227.0 | 2057.0 |
| 15 | Western | Hybrids | 2290 | 29.2 | 3276.0 | 27557.0 | 217.0 | 1895.0 |
| 15 | Pioneer | P98533PCE | - | 29.2 | 3623.0 | 29465.0 | 230.0 | 2015.0 |
| 17 | Western | Hybrids | 2193 | 28.7 | 3638.0 | 29821.0 | 233.0 | 2008.0 |
| 17 | DEKALB | DKC48-56 | - | 28.7 | 3635.0 | 29957.0 | 233.0 | 2009.0 |
| 19 | Pioneer | P9466AML | - | 28.2 | 3584.0 | 29345.0 | 230.0 | 1943.0 |
| 20 | Pioneer | P96567AM | - | 27.0 | 3619.0 | 27593.0 | 233.0 | 1893.0 |
| 20 | Axis | Seed | 50J58 | 27.0 | 3504.0 | 27580.0 | 230.0 | 1865.0 |
| 22 | Pioneer | P9540AM | - | 25.9 | 3519.0 | 26897.0 | 227.0 | 1759.0 |
| 23 | Axis | Seed | Experimental | 23.5 | 3707.0 | 25757.0 | 240.0 | 1692.0 |
Top 5 by Ton/Acre: Seed (Axis) 35.5, DKC092-14 (DEKALB) 34.9, Hybrids (Western) 32.8, P9845AM (Pioneer) 32.7, Seeds (Legacy) 32.0.