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 — Minnesota, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Minnesota (MN)
- Year: 2025
- Plot ID: 2469767
- Cooperator: Bauer Countryside Ag Service Inc
- Planted: 2025-05-02
- Harvested: 2025-10-05
- Population: 155,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mn/2025/2469767
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Brevant | B194EE | - | 47.2 | - | - | $495.60 |
| 2 | NK | NK21-C2E3 | Enlist E3 ® | 43.1 | - | - | $452.55 |
| 3 | Genesis | G1560E | - | 40.1 | - | - | $421.05 |
| 4 | NK | NK14-U5E3 | Enlist E3 ® | 38.8 | - | - | $407.40 |
| 5 | Peterson | Farms | Seed 26EN14 | 38.5 | - | - | $404.25 |
| 6 | Genesis | G1760E | - | 38.0 | - | - | $399.00 |
| 7 | Genesis | G1090E | - | 37.9 | - | - | $397.95 |
| 8 | Peterson | Farms | Seed 25EN13 | 36.7 | - | - | $385.35 |
| 9 | NK | NK16-Z6E3 | Enlist E3 ® | 36.1 | - | - | $379.05 |
| 10 | NK | NK17-H1E3 | Enlist E3 ® | 35.7 | - | - | $374.85 |
| 11 | Xitavo | XO | 1116E | 35.3 | - | - | $370.65 |
| 12 | Brevant | B144EE | - | 35.0 | - | - | $367.50 |
| 13 | Genesis | G0800E | - | 34.7 | - | - | $364.35 |
| 14 | Genesis | G1390E | - | 33.8 | - | - | $354.90 |
| 15 | Genesis | G1690E | - | 33.0 | - | - | $346.50 |
| 16 | Genesis | Experimental | - | 31.4 | - | - | $329.70 |
| 17 | Peterson | Farms | Seed Experimental | 31.3 | - | - | $328.65 |
| 18 | P3 | Genetics | 2515E | 30.9 | - | - | $324.45 |
| 19 | P3 | Genetics | 2510E | 30.8 | - | - | $323.40 |
| 20 | Brevant | B095EE | - | 30.6 | - | - | $321.30 |
| 21 | P3 | Genetics | 2414E | 29.0 | - | - | $304.50 |
| 22 | NK | NK08-Z4E3 | Enlist E3 ® | 27.1 | - | - | $284.55 |
| 23 | Peterson | Farms | Seed 25EN09 | 24.1 | - | - | $253.05 |
Top 5 by Yield: B194EE (Brevant) 47.2, NK21-C2E3 (NK) 43.1, G1560E (Genesis) 40.1, NK14-U5E3 (NK) 38.8, Farms (Peterson) 38.5.