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 — Tennessee, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Tennessee (TN)
- Year: 2024
- Plot ID: 2435174
- Cooperator: William Andrew Shipley
- Planted: 2024-06-12
- Harvested: 2024-10-14
- Population: 33,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/tn/2024/2435174
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 | DKC114-99 | - | 19.4 | 3000.0 | 17460.0 | 217.0 | 1246.0 |
| 2 | NK | NK1755-DV | - | 18.6 | 3071.0 | 17136.0 | 232.0 | 1225.0 |
| 3 | Augusta | Seed | A2464-DV | 16.9 | 3038.0 | 15403.0 | 218.0 | 1088.0 |
| 4 | Enogen | E114Z4-D | - | 16.6 | 3041.0 | 15144.0 | 205.0 | 1046.0 |
| 5 | Pioneer | P1380Q | - | 16.5 | 2855.0 | 14132.0 | 190.0 | 1015.0 |
| 6 | Pioneer | P1587Q | - | 16.3 | 3016.0 | 14748.0 | 214.0 | 1042.0 |
| 6 | Enogen | E117Z7-D | - | 16.3 | 2985.0 | 14597.0 | 203.0 | 1023.0 |
| 6 | Pioneer | P17677Q | - | 16.3 | 2937.0 | 14362.0 | 223.0 | 1057.0 |
| 6 | DEKALB | DKC113-62 | - | 16.3 | 3009.0 | 14714.0 | 216.0 | 1045.0 |
| 10 | Pioneer | P1742Q | - | 16.1 | 3082.0 | 14886.0 | 233.0 | 1062.0 |
| 10 | Augusta | Seed | A1964-DV | 16.1 | 2822.0 | 13630.0 | 188.0 | 987.0 |
| 12 | DEKALB | DKC115-81 | - | 16.0 | 3021.0 | 14501.0 | 196.0 | 994.0 |
| 13 | DEKALB | DKC67-66 | - | 15.7 | 2777.0 | 13080.0 | 173.0 | 939.0 |
| 14 | Augusta | Seed | A4465-DV | 15.6 | 2828.0 | 13235.0 | 185.0 | 951.0 |
| 15 | DEKALB | DKC70-64 | - | 15.4 | 2886.0 | 13333.0 | 206.0 | 971.0 |
| 16 | DEKALB | DKC70-94 | - | 15.2 | 2711.0 | 12362.0 | 176.0 | 914.0 |
| 17 | Pioneer | P17677Q | - | 14.7 | 3072.0 | 13548.0 | 238.0 | 976.0 |
| 18 | Pioneer | P14830Q | - | 14.5 | 2948.0 | 12824.0 | 212.0 | 924.0 |
| 19 | Augusta | Seed | A2064-D | 14.0 | 3004.0 | 12617.0 | 213.0 | 894.0 |
| 20 | DEKALB | Experimental | - | 13.7 | 2932.0 | 12051.0 | 207.0 | 866.0 |
| 21 | Pioneer | P13777PCUE | - | 13.4 | 3119.0 | 12538.0 | 240.0 | 893.0 |
| 22 | DEKALB | DKC105-25 | - | 13.0 | 3155.0 | 12305.0 | 237.0 | 862.0 |
| 23 | Enogen | E114C4-DV-LL | - | 11.9 | 2958.0 | 10560.0 | 204.0 | 748.0 |
| 24 | DEKALB | Experimental | - | 10.7 | 2861.0 | 9184.0 | 196.0 | 664.0 |
Top 5 by Ton/Acre: DKC114-99 (DEKALB) 19.4, NK1755-DV (NK) 18.6, Seed (Augusta) 16.9, E114Z4-D (Enogen) 16.6, P1380Q (Pioneer) 16.5.