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>
1.9 KiB
1.9 KiB
Silage yield trial — New York, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: New York (NY)
- Year: 2024
- Plot ID: 2420351
- Cooperator: Edelweiss Farms
- Planted: 2024-06-15
- Harvested: 2024-10-10
- Population: 32,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/ny/2024/2420351
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 | E092W5-D | - | 29.0 | 3771.0 | 32833.0 | 282.0 | 2068.0 |
| 2 | Enogen | E095D3-D | - | 28.8 | 3743.0 | 32349.0 | 290.0 | 2078.0 |
| 3 | Revere | Seed | Experimental | 28.5 | 3774.0 | 32225.0 | 271.0 | 1991.0 |
| 4 | NK | NK9400-V | - | 28.0 | 3415.0 | 28638.0 | 208.0 | 1769.0 |
| 4 | NK | NK9805-DV | - | 28.0 | 3639.0 | 30520.0 | 237.0 | 1854.0 |
| 6 | Enogen | E085Z5-D | - | 27.8 | 3760.0 | 31409.0 | 293.0 | 2018.0 |
| 7 | Enogen | E100A3-D | - | 27.5 | 3674.0 | 30304.0 | 245.0 | 1846.0 |
| 8 | Revere | Seed | Revere 9796 V | 26.8 | 3680.0 | 29597.0 | 248.0 | 1810.0 |
| 9 | NK | NK9771-DV | - | 26.7 | 3663.0 | 29317.0 | 250.0 | 1806.0 |
| 10 | Revere | Seed | Revere 9108 VT2P | 26.2 | 3654.0 | 28701.0 | 226.0 | 1706.0 |
| 11 | NK | NK9021-D | - | 25.4 | 3752.0 | 28614.0 | 262.0 | 1755.0 |
| 12 | Enogen | E094Z4-D | - | 24.5 | 3685.0 | 27085.0 | 264.0 | 1696.0 |
| 13 | Revere | Seed | Revere 9827 SSX | 23.2 | 3631.0 | 25309.0 | 256.0 | 1589.0 |
| 14 | NK | NK8711-V | - | 23.0 | 3631.0 | 25066.0 | 236.0 | 1523.0 |
| 15 | NK | NK8558-AA | - | 22.7 | 3577.0 | 24379.0 | 234.0 | 1499.0 |
| 16 | Revere | Seed | Revere 9916 VT2P | 21.7 | 3238.0 | 21051.0 | 196.0 | 1345.0 |
Top 5 by Ton/Acre: E092W5-D (Enogen) 29.0, E095D3-D (Enogen) 28.8, Seed (Revere) 28.5, NK9400-V (NK) 28.0, NK9805-DV (NK) 28.0.