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 — Wisconsin, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Wisconsin (WI)
- Year: 2024
- Plot ID: 2419291
- Cooperator: Joe Dudkiewicz
- Planted: 2024-05-18
- Harvested: 2024-10-10
- Population: 115,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/wi/2024/2419291
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Pioneer | P13Z28E | - | 47.6 | 14.5 | 55.3 | $499.80 |
| 2 | Stine | 13EG23 | - | 46.4 | 14.5 | 56.1 | $487.20 |
| 3 | Pioneer | P11Z72E | - | 44.1 | 14.2 | 54.7 | $463.05 |
| 4 | Pioneer | P14Z16E | - | 43.6 | 18.0 | 53.7 | $457.54 |
| 5 | NK | NK15-G9E3S | Enlist E3 ® STS ® | 42.7 | 14.0 | 56.2 | $448.35 |
| 6 | Pioneer | P15Z80E | - | 42.2 | 18.4 | 55.0 | $443.10 |
| 7 | NK | NK11-A4E3 | Enlist E3 ® | 40.1 | 13.2 | 55.8 | $421.05 |
| 7 | NK | NK11-U2XF | XtendFlex ® | 40.1 | 12.6 | 55.8 | $421.05 |
| 9 | Alloy | A10E35 | - | 38.1 | 13.2 | 55.8 | $400.05 |
| 10 | NK | NK09-H7E3 | Enlist E3 ® | 37.2 | 10.5 | 56.5 | $390.60 |
| 10 | Pioneer | P11T36E | - | 37.2 | 11.9 | 56.0 | $390.60 |
| 12 | Stine | 11EC02 | - | 36.5 | 12.9 | 56.3 | $383.25 |
| 13 | Pioneer | P09Z79E | - | 36.4 | 10.8 | 56.5 | $382.20 |
| 14 | Alloy | A13E35 | - | 35.5 | 14.5 | 55.8 | $372.75 |
| 15 | Stine | 08EC32 | - | 33.6 | 11.9 | 56.3 | $352.80 |
| 16 | Stine | 10EG20 | - | 31.1 | 10.8 | 57.6 | $326.55 |
| 17 | Pioneer | P06Z90E | - | 30.5 | 10.4 | 56.1 | $320.25 |
| 18 | NK | NK08-R3XF | XtendFlex ® | 30.1 | 11.2 | 56.5 | $316.05 |
| 19 | Pioneer | P05Z60E | - | 26.5 | 10.7 | 56.9 | $278.25 |
| 20 | NK | NK08-Z4E3 | Enlist E3 ® | 22.1 | 10.2 | 57.1 | $232.05 |
| 21 | Pioneer | P04Z49E | - | 18.0 | 11.6 | 54.9 | $189.00 |
Top 5 by Yield: P13Z28E (Pioneer) 47.6, 13EG23 (Stine) 46.4, P11Z72E (Pioneer) 44.1, P14Z16E (Pioneer) 43.6, NK15-G9E3S (NK) 42.7.