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>
1.9 KiB
1.9 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: 2419522
- Cooperator: Chs Dakota Plains Ag
- Planted: 2024-05-13
- Harvested: 2024-10-07
- Population: 160,000 seeds/acre
- Row width: 22"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/nd/2024/2419522
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Asgrow | AG04XF4 | - | 66.0 | 7.8 | - | $693.00 |
| 2 | NK | NK08-Z4E3 | Enlist E3 ® | 64.2 | 8.0 | - | $674.10 |
| 3 | Asgrow | AG03XF2 | - | 62.6 | 8.1 | - | $657.30 |
| 4 | NK | NK03-V5E3 | Enlist E3 ® | 62.4 | 7.7 | - | $655.20 |
| 5 | Asgrow | AG09XF3 | - | 61.2 | 8.1 | - | $642.60 |
| 6 | Attain | Attain | 06A5N | 61.1 | 8.2 | - | $641.55 |
| 7 | Brevant | B054EE | - | 60.8 | 7.9 | - | $638.40 |
| 8 | Asgrow | AG05XF4 | - | 59.0 | 8.0 | - | $619.50 |
| 9 | NK | NK04-A9E3 | Enlist E3 ® | 58.9 | 8.1 | - | $618.45 |
| 10 | Allegiant | Allegiant | 04F85N XF | 58.7 | 7.9 | - | $616.35 |
| 11 | Attain | Attain | 03A5N | 58.1 | 7.6 | - | $610.05 |
| 12 | Asgrow | AG07XF4 | - | 57.7 | 7.8 | - | $605.85 |
| 13 | Brevant | B074EE | - | 56.9 | 8.0 | - | $597.45 |
| 14 | Allegiant | Allegiant | 07F5 XF | 56.0 | 7.9 | - | $588.00 |
| 15 | Asgrow | AG10XF4 | - | 54.7 | 8.1 | - | $574.35 |
| 16 | Allegiant | Allegiant | 05F54N XF | 54.4 | 8.1 | - | $571.20 |
| 16 | Asgrow | AG06XF3 | - | 54.4 | 7.9 | - | $571.20 |
| 18 | NK | NK11-A4E3 | Enlist E3 ® | 54.2 | 7.9 | - | $569.10 |
| 19 | Attain | Attain | 09A5N | 50.1 | 7.9 | - | $526.05 |
| 20 | Attain | Attain | 11A3N | 44.2 | 8.8 | - | $464.10 |
| 21 | Brevant | B053EE | - | 39.6 | 8.0 | - | $415.80 |
Top 5 by Yield: AG04XF4 (Asgrow) 66.0, NK08-Z4E3 (NK) 64.2, AG03XF2 (Asgrow) 62.6, NK03-V5E3 (NK) 62.4, AG09XF3 (Asgrow) 61.2.