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>
2.2 KiB
2.2 KiB
Silage yield trial — Minnesota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Minnesota (MN)
- Year: 2024
- Plot ID: 2419002
- Cooperator: Chs Herman
- Planted: 2024-05-15
- Harvested: 2024-09-19
- Population: 31,500 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/mn/2024/2419002
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 | B05D47V | - | 29.1 | 3538.0 | 30849.0 | 239.0 | 1934.0 |
| 2 | Pioneer | P0529Q | - | 28.6 | 3512.0 | 30083.0 | 235.0 | 1886.0 |
| 3 | DEKALB | DKC102-28 | - | 28.5 | 3415.0 | 29176.0 | 241.0 | 1901.0 |
| 4 | DEKALB | DKC098-88 | - | 28.4 | 3519.0 | 30004.0 | 247.0 | 1915.0 |
| 5 | Brevant | B99A24V | - | 27.4 | 3488.0 | 28707.0 | 232.0 | 1806.0 |
| 5 | Brevant | B01X44V | - | 27.4 | 3547.0 | 29177.0 | 249.0 | 1854.0 |
| 7 | NK | NK0007-AA | - | 27.2 | 3529.0 | 28838.0 | 258.0 | 1869.0 |
| 8 | Allegiant | Allegiant | 9884 DGVT2P | 27.0 | 3403.0 | 27575.0 | 216.0 | 1731.0 |
| 8 | NK | NK0440-AT | - | 27.0 | 3304.0 | 26744.0 | 217.0 | 1732.0 |
| 10 | Pioneer | P9955V | - | 26.7 | 3466.0 | 27741.0 | 238.0 | 1773.0 |
| 11 | Pioneer | P0075AM | - | 26.6 | 3491.0 | 27840.0 | 242.0 | 1778.0 |
| 12 | NK | NK0501-DV | - | 26.4 | 3402.0 | 26914.0 | 218.0 | 1696.0 |
| 13 | NK | NK9771-DV | - | 26.0 | 3506.0 | 27321.0 | 238.0 | 1726.0 |
| 14 | Allegiant | Allegiant | 9825 VT2P | 25.9 | 3481.0 | 27041.0 | 227.0 | 1690.0 |
| 15 | Enogen | E105Z5-D | - | 24.9 | 3365.0 | 25113.0 | 220.0 | 1607.0 |
| 16 | Enogen | E100A3-D | - | 24.6 | 3417.0 | 25183.0 | 248.0 | 1659.0 |
| 17 | NK | NK0123-AA | - | 24.5 | 3511.0 | 25770.0 | 240.0 | 1630.0 |
| 17 | DEKALB | DKC103-47 | - | 24.5 | 3238.0 | 23804.0 | 207.0 | 1550.0 |
| 19 | Pioneer | P05466V | - | 24.0 | 3060.0 | 22004.0 | 186.0 | 1465.0 |
| 20 | Brevant | B98Z37V | - | 23.3 | 3504.0 | 24505.0 | 245.0 | 1566.0 |
| 21 | DEKALB | DKC101-35 | - | 22.9 | 3381.0 | 23226.0 | 213.0 | 1461.0 |
Top 5 by Ton/Acre: B05D47V (Brevant) 29.1, P0529Q (Pioneer) 28.6, DKC102-28 (DEKALB) 28.5, DKC098-88 (DEKALB) 28.4, B99A24V (Brevant) 27.4.