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>
2.3 KiB
2.3 KiB
Silage yield trial — Illinois, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Illinois (IL)
- Year: 2025
- Plot ID: 2465983
- Cooperator: Prairie Ag Services Inc
- Planted: 2025-04-28
- Harvested: 2025-08-27
- Population: 35,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/il/2025/2465983
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 | E114C4-DV-LL | - | 32.8 | 3248.0 | 31996.0 | 220.0 | 2130.0 |
| 2 | Enogen | E107C1-D | - | 31.3 | 3433.0 | 32210.0 | 233.0 | 2062.0 |
| 3 | Enogen | E111V7-D | - | 30.7 | 3086.0 | 28385.0 | 182.0 | 1935.0 |
| 4 | NK | NK1480-DV | - | 30.2 | 3506.0 | 31794.0 | 246.0 | 2032.0 |
| 5 | Enogen | E114C4-DV-LL | - | 30.1 | 3206.0 | 28944.0 | 210.0 | 1913.0 |
| 6 | NK | NK1480-DV | - | 29.3 | 2975.0 | 26148.0 | 188.0 | 1797.0 |
| 7 | NK | NK0604-DV | - | 28.9 | 3492.0 | 30264.0 | 248.0 | 1951.0 |
| 8 | Enogen | E112S5-D | - | 28.8 | 3225.0 | 27888.0 | 215.0 | 1845.0 |
| 9 | Enogen | E108K4-DV | - | 28.7 | 2951.0 | 25445.0 | 144.0 | 1720.0 |
| 10 | DEKALB | DKC110-10 | - | 28.4 | 3412.0 | 29073.0 | 222.0 | 1840.0 |
| 11 | Enogen | E107C1-D | - | 28.2 | 3142.0 | 26561.0 | 190.0 | 1759.0 |
| 12 | NK | NK0440-AT | - | 27.8 | 3374.0 | 28102.0 | 236.0 | 1838.0 |
| 13 | NK | NK0604-DV | - | 27.7 | 3375.0 | 28015.0 | 229.0 | 1811.0 |
| 14 | Enogen | E112S5-D | - | 27.6 | 3252.0 | 26887.0 | 232.0 | 1813.0 |
| 14 | Enogen | E108K4-DV | - | 27.6 | 3498.0 | 28936.0 | 234.0 | 1819.0 |
| 16 | Pioneer | P1180XR | - | 27.4 | 3646.0 | 29972.0 | 277.0 | 1936.0 |
| 17 | Enogen | E105Z5-D | - | 27.0 | 3344.0 | 27041.0 | 232.0 | 1773.0 |
| 18 | Pioneer | P1180XR | - | 25.1 | 3255.0 | 24543.0 | 225.0 | 1636.0 |
| 18 | Enogen | E105Z5-D | - | 25.1 | 2809.0 | 21184.0 | 135.0 | 1492.0 |
| 20 | NK | NK0440-AT | - | 24.1 | 2816.0 | 20321.0 | 127.0 | 1406.0 |
| 21 | DEKALB | DKC110-10 | - | 23.9 | 3154.0 | 22616.0 | 187.0 | 1462.0 |
| 22 | Enogen | E111V7-D | - | 23.1 | 3213.0 | 22249.0 | 229.0 | 1511.0 |
Top 5 by Ton/Acre: E114C4-DV-LL (Enogen) 32.8, E107C1-D (Enogen) 31.3, E111V7-D (Enogen) 30.7, NK1480-DV (NK) 30.2, E114C4-DV-LL (Enogen) 30.1.