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>
2.2 KiB
2.2 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: 2469714
- Cooperator: Bauer Countryside Ag Service Inc
- Planted: 2025-04-29
- Harvested: 2025-10-01
- Population: 155,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mn/2025/2469714
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Brevant | B194EE | - | 65.0 | - | - | $682.50 |
| 2 | Genesis | G1760E | - | 59.9 | - | - | $628.95 |
| 3 | NK | NK11-A4E3 | Enlist E3 ® | 59.4 | - | - | $623.70 |
| 4 | Genesis | G0700E | - | 59.3 | - | - | $622.65 |
| 5 | Peterson | Farms | Seed 26EN14 | 59.2 | - | - | $621.60 |
| 6 | NK | NK17-H1E3 | Enlist E3 ® | 59.0 | - | - | $619.50 |
| 7 | NK | NK14-U5E3 | Enlist E3 ® | 58.8 | - | - | $617.40 |
| 8 | Brevant | B144EE | - | 58.5 | - | - | $614.25 |
| 9 | NK | NK16-Z6E3 | Enlist E3 ® | 58.0 | - | - | $609.00 |
| 10 | Brevant | B135EE | - | 57.4 | - | - | $602.70 |
| 11 | Genesis | G0800E | - | 56.6 | - | - | $594.30 |
| 12 | P3 | Genetics | 2414E | 56.5 | - | - | $593.25 |
| 13 | Genesis | G1690E | - | 54.5 | - | - | $572.25 |
| 13 | Genesis | G1290E | - | 54.5 | - | - | $572.25 |
| 15 | Genesis | G0800E | - | 53.7 | - | - | $563.85 |
| 16 | Xitavo | XO | 1446E | 53.0 | - | - | $556.50 |
| 17 | Peterson | Farms | Seed 25EN13 | 51.7 | - | - | $542.85 |
| 17 | Genesis | G1090E | - | 51.7 | - | - | $542.85 |
| 19 | Brevant | B095EE | - | 51.6 | - | - | $541.80 |
| 20 | Genesis | G1260E | - | 51.5 | - | - | $540.75 |
| 21 | P3 | Genetics | 2515E | 50.3 | - | - | $528.15 |
| 22 | NK | NK08-Z4E3 | Enlist E3 ® | 49.7 | - | - | $521.85 |
| 23 | Genesis | G0880E | - | 47.5 | - | - | $498.75 |
| 24 | Xitavo | XO | 0806E | 47.0 | - | - | $493.50 |
| 25 | P3 | Genetics | 2510E | 46.4 | - | - | $487.20 |
| 26 | Xitavo | XO | 1116E | 45.1 | - | - | $473.55 |
| 27 | Peterson | Farms | Seed 25EN09 | 44.5 | - | - | $467.25 |
Top 5 by Yield: B194EE (Brevant) 65.0, G1760E (Genesis) 59.9, NK11-A4E3 (NK) 59.4, G0700E (Genesis) 59.3, Farms (Peterson) 59.2.