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>
2.5 KiB
2.5 KiB
Silage yield trial — Wisconsin, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Wisconsin (WI)
- Year: 2025
- Plot ID: 2465985
- Cooperator: Prairie Ag Services Inc
- Planted: 2025-05-05
- Harvested: 2025-09-03
- Population: 36,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2465985
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 | E112S5-D | - | 36.7 | 3272.0 | 36032.0 | 224.0 | 2384.0 |
| 2 | NK | NK0440-AT | - | 33.2 | 3528.0 | 35114.0 | 251.0 | 2251.0 |
| 3 | Enogen | E112S5-D | - | 32.6 | 3330.0 | 32572.0 | 222.0 | 2113.0 |
| 3 | Enogen | E107C1-D | - | 32.6 | 3334.0 | 32595.0 | 223.0 | 2112.0 |
| 5 | Enogen | E107C1-D | - | 31.6 | 3596.0 | 34108.0 | 254.0 | 2154.0 |
| 6 | NK | NK1480-DV | - | 29.8 | 3303.0 | 29534.0 | 214.0 | 1907.0 |
| 7 | DEKALB | DKC110-10 | - | 29.1 | 3321.0 | 28995.0 | 205.0 | 1838.0 |
| 8 | Enogen | E105Z5-D | - | 28.8 | 3409.0 | 29497.0 | 239.0 | 1920.0 |
| 9 | Enogen | E111V7-D | - | 28.6 | 3339.0 | 28621.0 | 224.0 | 1855.0 |
| 9 | Pioneer | P1180XR | - | 28.6 | 3564.0 | 30611.0 | 246.0 | 1928.0 |
| 11 | Enogen | E108K4-DV | - | 28.4 | 3367.0 | 28731.0 | 235.0 | 1882.0 |
| 12 | Enogen | E108K4-DV | - | 28.3 | 3431.0 | 29135.0 | 236.0 | 1875.0 |
| 13 | DEKALB | DKC110-10 | - | 27.9 | 3296.0 | 27588.0 | 214.0 | 1785.0 |
| 14 | Enogen | E111V7-D | - | 27.6 | 3574.0 | 29555.0 | 253.0 | 1875.0 |
| 15 | Enogen | E114C4-DV-LL | - | 27.5 | 3292.0 | 27198.0 | 222.0 | 1783.0 |
| 16 | NK | NK0604-DV | - | 26.0 | 3266.0 | 25498.0 | 216.0 | 1668.0 |
| 17 | Enogen | E105Z5-D | - | 25.8 | 3461.0 | 26824.0 | 247.0 | 1740.0 |
| 18 | NK | NK0604-DV | - | 25.4 | 3373.0 | 25732.0 | 240.0 | 1695.0 |
| 18 | Pioneer | P1180XR | - | 25.4 | 3593.0 | 27360.0 | 259.0 | 1745.0 |
| 20 | NK | NK1480-DV | - | 24.7 | 3488.0 | 25843.0 | 245.0 | 1659.0 |
| 21 | DEKALB | DKC105-33 | - | 24.5 | 3116.0 | 22947.0 | 191.0 | 1526.0 |
| 22 | DEKALB | DKC105-33 | - | 23.8 | 3371.0 | 24024.0 | 249.0 | 1605.0 |
| 23 | NK | NK0440-AT | - | 23.4 | 3173.0 | 22296.0 | 214.0 | 1497.0 |
| 24 | Enogen | E114C4-DV-LL | - | 20.8 | 3284.0 | 20530.0 | 213.0 | 1331.0 |
Top 5 by Ton/Acre: E112S5-D (Enogen) 36.7, NK0440-AT (NK) 33.2, E112S5-D (Enogen) 32.6, E107C1-D (Enogen) 32.6, E107C1-D (Enogen) 31.6.