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>
2.7 KiB
2.7 KiB
Soybean yield trial — North Dakota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: North Dakota (ND)
- Year: 2024
- Plot ID: 2419810
- Cooperator: James River Ag
- Planted: 2024-05-23
- Harvested: 2024-10-02
- Population: 155,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/nd/2024/2419810
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Mustang | Seeds | XF01223 | 55.9 | 9.0 | 58.4 | $586.95 |
| 2 | Peterson | Farms | Seed 22XF06 | 55.1 | 13.4 | 57.7 | $578.55 |
| 3 | Peterson | Farms | Seed 25XF05 | 53.3 | 10.0 | 58.3 | $559.65 |
| 4 | NK | NK05-W3XF | XtendFlex ® | 51.3 | 13.4 | 56.8 | $538.65 |
| 5 | Xitavo | XO | 0602E | 51.2 | 15.2 | 54.3 | $537.60 |
| 6 | P3 | Genetics | 2406E | 50.7 | 16.0 | 56.2 | $532.35 |
| 7 | Midwest | Seed | Genetics MW F0152 | 50.5 | 9.5 | 58.4 | $530.25 |
| 8 | NK | NK06-C4XF | XtendFlex ® | 50.0 | 10.1 | 57.2 | $525.00 |
| 9 | NK | NK06-A1E3 | Enlist E3 ® | 49.9 | 10.6 | 57.8 | $523.95 |
| 10 | Mustang | Seeds | 06E434 | 49.7 | 12.8 | 56.5 | $521.85 |
| 11 | Ed | Seed | E0532 | 49.5 | 11.4 | 57.5 | $519.75 |
| 11 | Peterson | Farms | Seed 22XF06 | 49.5 | 13.3 | 56.7 | $519.75 |
| 13 | Midwest | Seed | Genetics MW F00951 | 48.9 | 8.8 | 58.3 | $513.45 |
| 14 | Peterson | Farms | Seed 24XF01 | 48.8 | 8.9 | 58.7 | $512.40 |
| 15 | Mustang | Seeds | XF04415 | 47.9 | 10.6 | 57.5 | $502.95 |
| 16 | Midwest | Seed | Genetics MW F0451 | 47.6 | 9.3 | 58.2 | $499.80 |
| 17 | Peterson | Farms | Seed 24XF04 | 47.3 | 9.9 | 57.6 | $496.65 |
| 18 | NK | NK02-Y2XF | XtendFlex ® | 46.8 | 9.0 | 57.8 | $491.40 |
| 18 | Xitavo | XO | 0315E | 46.8 | 10.9 | 57.5 | $491.40 |
| 20 | Peterson | Farms | Seed 23XF09 | 46.7 | 9.1 | 57.5 | $490.35 |
| 21 | Peterson | Farms | Seed 22XF03 | 46.5 | 9.6 | 58.3 | $488.25 |
| 22 | NK | NK03-V5E3 | Enlist E3 ® | 45.4 | 11.7 | 57.7 | $476.70 |
| 23 | P3 | Genetics | 2405E | 45.1 | 12.2 | 56.5 | $473.55 |
| 24 | Mustang | Seeds | 02E443 | 44.9 | 10.6 | 57.6 | $471.45 |
| 25 | NK | NK04-A9E3 | Enlist E3 ® | 44.5 | 11.5 | 56.8 | $467.25 |
| 26 | NK | NK008-P8XF | XtendFlex ® | 44.3 | 9.8 | 57.9 | $465.15 |
| 27 | Ed | Seed | E0234 | 43.9 | 10.7 | 57.6 | $460.95 |
| 28 | Mustang | Seeds | XF03314 | 43.8 | 8.8 | 58.1 | $459.90 |
| 29 | Xitavo | XO | 0234E | 43.1 | 12.4 | 57.6 | $452.55 |
| 30 | P3 | Genetics | 2401E | 42.7 | 11.2 | 58.0 | $448.35 |
| 31 | Ed | Seed | E0131 | 39.5 | 11.5 | 56.7 | $414.75 |
Top 5 by Yield: Seeds (Mustang) 55.9, Farms (Peterson) 55.1, Farms (Peterson) 53.3, NK05-W3XF (NK) 51.3, XO (Xitavo) 51.2.