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>
2.4 KiB
2.4 KiB
Silage yield trial — Wisconsin, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Wisconsin (WI)
- Year: 2024
- Plot ID: 2419091
- Cooperator: Prairie Ag Services Inc
- Planted: 2024-05-01
- Harvested: 2024-08-26
- Population: 34,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2024/2419091
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | NK | NK9771-DV | - | 27.6 | 3327.0 | 27588.0 | 235.0 | 1827.0 |
| 2 | NK | NK9805-DV | - | 27.4 | 3321.0 | 27299.0 | 221.0 | 1771.0 |
| 3 | Enogen | E105Z5-D | - | 26.7 | 3356.0 | 26896.0 | 233.0 | 1760.0 |
| 4 | NK | NK0252-D | - | 26.4 | 3428.0 | 27153.0 | 248.0 | 1783.0 |
| 5 | Pioneer | P0275Q | - | 26.2 | 3256.0 | 25627.0 | 211.0 | 1669.0 |
| 6 | Enogen | E092W5-D | - | 25.6 | 3757.0 | 28832.0 | 291.0 | 1846.0 |
| 7 | NK | NK9771-DV | - | 24.8 | 3608.0 | 26843.0 | 256.0 | 1696.0 |
| 8 | Pioneer | P0275Q | - | 24.7 | 3614.0 | 26811.0 | 265.0 | 1716.0 |
| 9 | NK | NK0501-DV | - | 24.6 | 3037.0 | 22425.0 | 220.0 | 1588.0 |
| 10 | NK | NK0440-AT | - | 24.2 | 3279.0 | 23789.0 | 222.0 | 1567.0 |
| 10 | Enogen | E094Z4-D | - | 24.2 | 3574.0 | 25944.0 | 266.0 | 1680.0 |
| 10 | Enogen | E105Z5-D | - | 24.2 | 3320.0 | 24081.0 | 226.0 | 1576.0 |
| 13 | Enogen | E107C1-D | - | 23.3 | 3101.0 | 21714.0 | 222.0 | 1511.0 |
| 14 | Enogen | E094Z4-D | - | 23.1 | 3723.0 | 25779.0 | 279.0 | 1636.0 |
| 15 | NK | NK0440-AT | - | 22.8 | 3195.0 | 21839.0 | 226.0 | 1485.0 |
| 16 | Enogen | E107C1-D | - | 22.5 | 3298.0 | 22227.0 | 244.0 | 1507.0 |
| 17 | Enogen | E092W5-D | - | 22.3 | 3328.0 | 22297.0 | 237.0 | 1481.0 |
| 18 | Enogen | E095D3-D | - | 21.6 | 3503.0 | 22722.0 | 244.0 | 1451.0 |
| 19 | NK | NK0501-DV | - | 21.3 | 3488.0 | 22280.0 | 244.0 | 1428.0 |
| 20 | NK | NK9021-D | - | 21.2 | 3470.0 | 22083.0 | 247.0 | 1429.0 |
| 21 | NK | NK9805-DV | - | 20.6 | 3508.0 | 21651.0 | 258.0 | 1411.0 |
| 22 | NK | NK9021-D | - | 20.4 | 3456.0 | 21105.0 | 242.0 | 1362.0 |
| 23 | Enogen | E095D3-D | - | 19.6 | 3286.0 | 19366.0 | 229.0 | 1286.0 |
| 24 | NK | NK0252-D | - | 18.9 | 3624.0 | 20534.0 | 260.0 | 1300.0 |
Top 5 by Ton/Acre: NK9771-DV (NK) 27.6, NK9805-DV (NK) 27.4, E105Z5-D (Enogen) 26.7, NK0252-D (NK) 26.4, P0275Q (Pioneer) 26.2.