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>
2.6 KiB
2.6 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: 2438064
- Cooperator: NDSU - North Central Research Extension Center (Minot)
- Planted: 2024-05-12
- Harvested: 2024-10-10
- Population: 150,000 seeds/acre
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/nd/2024/2438064
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Proseed | XF | 30-062 | 44.5 | - | 54.2 | $467.25 |
| 2 | NDSU | ND17009GT | - | 44.4 | - | 54.5 | $466.20 |
| 3 | Proseed | EL | 50-13N | 44.3 | - | 53.3 | $464.53 |
| 4 | Channel | 0225RXF | - | 43.0 | - | 53.4 | $450.98 |
| 5 | NDSU | ND21008GT20 | - | 41.9 | - | 55.1 | $439.95 |
| 6 | Integra | Fortified | Seed XF0212 | 40.6 | - | 54.0 | $426.30 |
| 7 | Fortus | 0165E | - | 39.9 | - | 53.8 | $418.79 |
| 8 | LG Seeds | LGS00820XF | - | 39.6 | - | 53.4 | $415.32 |
| 9 | NK | NK008-P8XF | XtendFlex ® | 39.5 | - | 53.6 | $414.43 |
| 10 | Proseed | XF | 30-092N | 39.1 | - | 53.4 | $410.08 |
| 11 | NK | NK02-W8E3 | Enlist E3 ® | 38.8 | - | 53.6 | $407.09 |
| 12 | Xitavo | XO | 0094E | 38.5 | - | 53.8 | $404.10 |
| 13 | Xitavo | XO | 0315E | 38.0 | - | 54.5 | $399.00 |
| 14 | Legacy | Seeds | LS014-23 XF | 37.8 | - | 54.1 | $396.90 |
| 15 | NK | NK03-J1XF | XtendFlex ® | 37.4 | - | 53.8 | $392.55 |
| 16 | Fortus | 0234E | - | 37.3 | - | 53.9 | $391.58 |
| 17 | Integra | Fortified | Seed XF0493 | 36.9 | - | 54.1 | $387.45 |
| 18 | Xitavo | XO | 0554E | 36.4 | - | 53.7 | $381.98 |
| 19 | Legacy | Seeds | LS034-24 XF | 36.0 | - | 53.5 | $377.64 |
| 20 | Channel | 00924RXF | - | 35.7 | - | 53.2 | $374.28 |
| 20 | LG Seeds | LGS0125XF | - | 35.7 | - | 54.2 | $374.85 |
| 22 | LG Seeds | LGS0139XF | - | 35.5 | - | 54.4 | $372.75 |
| 23 | Xitavo | XO | 0234E | 35.0 | - | 54.0 | $367.50 |
| 24 | Legacy | Seeds | LS12-23 E | 34.5 | - | 53.4 | $361.84 |
| 25 | NK | NK02-Y2XF | XtendFlex ® | 34.2 | - | 53.1 | $358.48 |
| 26 | Golden Harvest | GH00864XF | XtendFlex ® | 33.5 | - | 53.7 | $351.55 |
| 27 | Legacy | Seeds | LS0098-23 XF | 33.3 | - | 54.4 | $349.65 |
| 27 | Proseed | XF | 40-12 | 33.3 | - | 54.6 | $349.65 |
| 29 | Golden Harvest | GH0225XF | XtendFlex ® | 26.3 | - | 54.5 | $276.15 |
| 30 | Legacy | Seeds | LS024-23 XF | 25.4 | - | 54.1 | $266.70 |
Top 5 by Yield: XF (Proseed) 44.5, ND17009GT (NDSU) 44.4, EL (Proseed) 44.3, 0225RXF (Channel) 43.0, ND21008GT20 (NDSU) 41.9.