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 — North Dakota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: North Dakota (ND)
- Year: 2024
- Plot ID: 2435297
- Cooperator: Perhus Farms
- Planted: 2024-05-15
- Harvested: 2024-09-20
- Population: 24,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/nd/2024/2435297
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 | E105Z5-D | - | 28.5 | 3490.0 | 29842.0 | 245.0 | 1915.0 |
| 2 | Enogen | E092W5-D | - | 27.5 | 3065.0 | 25260.0 | 228.0 | 1795.0 |
| 3 | Enogen | E085Z5-D | - | 27.2 | 2862.0 | 23338.0 | 187.0 | 1663.0 |
| 4 | Enogen | E105Z5-D | - | 27.0 | 3116.0 | 25266.0 | 201.0 | 1692.0 |
| 5 | Enogen | E094Z4-D | - | 25.4 | 3497.0 | 26639.0 | 271.0 | 1778.0 |
| 6 | Enogen | E095D3-D | - | 24.8 | 3256.0 | 24265.0 | 222.0 | 1609.0 |
| 7 | Enogen | E100A3-D | - | 24.2 | 3144.0 | 22803.0 | 223.0 | 1567.0 |
| 8 | Rea | Hybrids | 4A301-RHDS | 23.8 | 2927.0 | 20895.0 | 191.0 | 1484.0 |
| 9 | Enogen | E094Z4-D | - | 22.7 | 2691.0 | 18342.0 | 157.0 | 1354.0 |
| 10 | Enogen | E092W5-D | - | 22.5 | 3071.0 | 20774.0 | 210.0 | 1433.0 |
| 11 | Enogen | E100A3-D | - | 22.4 | 2693.0 | 18078.0 | 152.0 | 1331.0 |
| 12 | Enogen | E085Z5-D | - | 22.1 | 2770.0 | 18387.0 | 184.0 | 1357.0 |
| 13 | Enogen | E095D3-D | - | 21.8 | 2763.0 | 18029.0 | 150.0 | 1272.0 |
| 14 | Enogen | E107C1-D | - | 19.9 | 2672.0 | 15941.0 | 136.0 | 1179.0 |
| 15 | Enogen | E107C1-D | - | 18.6 | 2560.0 | 14257.0 | 140.0 | 1079.0 |
| 16 | Rea | Hybrids | 4A301-RHDS | 18.2 | 2423.0 | 13238.0 | 177.0 | 1123.0 |
Top 5 by Ton/Acre: E105Z5-D (Enogen) 28.5, E092W5-D (Enogen) 27.5, E085Z5-D (Enogen) 27.2, E105Z5-D (Enogen) 27.0, E094Z4-D (Enogen) 25.4.