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>
2.0 KiB
2.0 KiB
Soybean yield trial — Illinois, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Illinois (IL)
- Year: 2025
- Plot ID: 2466710
- Cooperator: Ken Beck
- Planted: 2025-05-08
- Harvested: 2025-10-03
- Population: 140,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/il/2025/2466710
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Xitavo | XO | 2366E | 86.3 | 9.4 | - | $906.15 |
| 1 | Xitavo | XO | 2556E | 86.3 | 9.0 | - | $906.15 |
| 1 | Asgrow | AG32XF6 | - | 86.3 | 8.7 | - | $906.15 |
| 4 | Brevant | B315EE | - | 85.8 | 8.9 | - | $900.90 |
| 5 | Alloy | A28E36 | - | 85.7 | 8.7 | - | $899.85 |
| 6 | Brevant | B275EE | - | 84.1 | 8.7 | - | $883.05 |
| 7 | Asgrow | AG26XF4 | - | 83.0 | 8.9 | - | $871.50 |
| 8 | Brevant | B252EE | - | 82.1 | 9.1 | - | $862.05 |
| 9 | Brevant | B243EE | - | 81.7 | 9.2 | - | $857.85 |
| 9 | NK | NK26-M6E3 | Enlist E3 ® | 81.7 | 9.2 | - | $857.85 |
| 11 | Brevant | B224EE | - | 80.8 | 9.2 | - | $848.40 |
| 11 | NK | NK26-Z1XF | XtendFlex ® | 80.8 | 9.2 | - | $848.40 |
| 13 | Xitavo | XO | 2832E | 80.7 | 9.0 | - | $847.35 |
| 14 | Alloy | A30E35 | - | 80.5 | 8.8 | - | $845.25 |
| 15 | Asgrow | AG29XF5 | - | 80.3 | 8.3 | - | $843.15 |
| 16 | Alloy | A27E35 | - | 79.6 | 8.8 | - | $835.80 |
| 17 | Asgrow | AG21XF2 | - | 79.5 | 9.6 | - | $834.75 |
| 17 | Xitavo | XO | 3105E | 79.5 | 8.9 | - | $834.75 |
| 19 | NK | NK29-Q3XF | XtendFlex ® | 79.4 | 8.7 | - | $833.70 |
| 20 | NK | NK28-G7E3S | Enlist E3 ® STS ® | 78.8 | 9.0 | - | $827.40 |
| 21 | NK | NK23-P1E3 | Enlist E3 ® | 77.6 | 9.6 | - | $814.80 |
| 22 | Xitavo | XO | 2865E | 76.2 | 8.7 | - | $800.10 |
| 23 | Asgrow | AG24XF1 | - | 76.1 | 9.5 | - | $799.05 |
| 24 | Brevant | B294EE | - | 75.4 | 8.9 | - | $791.70 |
Top 5 by Yield: XO (Xitavo) 86.3, XO (Xitavo) 86.3, AG32XF6 (Asgrow) 86.3, B315EE (Brevant) 85.8, A28E36 (Alloy) 85.7.