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>
2.8 KiB
2.8 KiB
Silage yield trial — Georgia, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Georgia (GA)
- Year: 2024
- Plot ID: 2462608
- Cooperator: University of Georgia - Plains, GA
- Planted: 2024-04-10
- Harvested: 2024-07-21
- Population: 36,000 seeds/acre
- URL: https://www.goldenharvestseeds.com/silage/plot-report/ga/2024/2462608
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | DEKALB | DKC68-35 | - | 38.8 | 3269.0 | 38018.0 | 234.0 | 2722.0 |
| 2 | Innvictis | Seed | Solutions A1993T | 38.7 | 3393.0 | 39423.0 | 240.0 | 2793.0 |
| 3 | BH | Genetics | BH 8705VIP3110 | 38.6 | 3335.0 | 38659.0 | 237.0 | 2747.0 |
| 4 | BH | Genetics | BH 8690VIP3110 | 38.3 | 3295.0 | 37890.0 | 235.0 | 2706.0 |
| 5 | BH | Genetics | Experimental | 37.6 | 3436.0 | 38712.0 | 242.0 | 2723.0 |
| 6 | BH | Genetics | BH 8721VT2P | 37.2 | 3421.0 | 38175.0 | 241.0 | 2693.0 |
| 7 | Integra | Fortified | Seed 6915 TRE | 36.9 | 3345.0 | 37042.0 | 238.0 | 2632.0 |
| 8 | Revere | Seed | Revere 1839 TC | 36.7 | 3422.0 | 37711.0 | 241.0 | 2656.0 |
| 9 | DEKALB | DKC66-06 | - | 36.5 | 3371.0 | 36949.0 | 239.0 | 2620.0 |
| 10 | AgraTech | AT | 79VT2P | 36.1 | 3417.0 | 37022.0 | 241.0 | 2611.0 |
| 11 | Innvictis | Seed | Solutions A1792T | 36.0 | 3464.0 | 37437.0 | 243.0 | 2630.0 |
| 11 | Pioneer | P17677YHR | - | 36.0 | 3333.0 | 36022.0 | 237.0 | 2565.0 |
| 13 | Integra | Fortified | Seed 6891 AS3110 | 35.8 | 3133.0 | 33604.0 | 228.0 | 2449.0 |
| 14 | DEKALB | DKC70-45 | - | 35.7 | 3328.0 | 35650.0 | 237.0 | 2539.0 |
| 15 | Enogen | E114C4-DV-LL | - | 35.3 | 3373.0 | 35759.0 | 239.0 | 2537.0 |
| 16 | Integra | Fortified | Seed Experimental | 35.2 | 3491.0 | 36816.0 | 244.0 | 2577.0 |
| 17 | BH | Genetics | BH 8420VIP3110 | 35.0 | 3337.0 | 35069.0 | 237.0 | 2491.0 |
| 17 | Integra | Fortified | Seed 6493 VT2P | 35.0 | 3406.0 | 35809.0 | 241.0 | 2530.0 |
| 17 | Integra | Fortified | Seed 6641 SS | 35.0 | 3266.0 | 34275.0 | 234.0 | 2453.0 |
| 20 | Integra | Fortified | Seed 6709 VT2P | 34.9 | 3224.0 | 33736.0 | 232.0 | 2435.0 |
| 21 | NK | NK1402-DV | - | 34.1 | 3435.0 | 35167.0 | 243.0 | 2489.0 |
| 21 | Revere | Seed | Revere 1627 TC | 34.1 | 3174.0 | 32510.0 | 231.0 | 2370.0 |
| 21 | Integra | Fortified | Seed 6864 RR | 34.1 | 3421.0 | 35027.0 | 242.0 | 2474.0 |
| 24 | Enogen | E117Z7-D | - | 32.6 | 3241.0 | 31736.0 | 233.0 | 2285.0 |
| 25 | BH | Genetics | Experimental | 31.3 | 3306.0 | 31089.0 | 236.0 | 2219.0 |
| 26 | BH | Genetics | Experimental | 31.0 | 3436.0 | 31998.0 | 242.0 | 2257.0 |
Top 5 by Ton/Acre: DKC68-35 (DEKALB) 38.8, Seed (Innvictis) 38.7, Genetics (BH) 38.6, Genetics (BH) 38.3, Genetics (BH) 37.6.