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>
2.1 KiB
2.1 KiB
Soybean yield trial — South Dakota, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: South Dakota (SD)
- Year: 2025
- Plot ID: 2466489
- Cooperator: Helena Agri-Enterprises Llc
- Planted: 2025-05-08
- Harvested: 2025-10-02
- Population: 140,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/sd/2025/2466489
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Brevant | B155EE | - | 60.9 | 10.9 | 56.4 | $639.45 |
| 2 | Stine | 13EG23 | - | 59.6 | 9.9 | 55.9 | $625.80 |
| 3 | Mustang | Seeds | 16E725 | 59.3 | 10.1 | 57.4 | $622.65 |
| 4 | Brevant | B144EE | - | 59.0 | 10.2 | 57.2 | $619.50 |
| 5 | NK | NK17-H1E3 | Enlist E3 ® | 58.5 | 10.6 | 56.6 | $614.25 |
| 6 | Mustang | Seeds | 18E825 | 58.4 | 10.5 | 56.4 | $613.20 |
| 7 | NK | NK16-Z6E3 | Enlist E3 ® | 58.1 | 10.2 | 56.7 | $610.05 |
| 8 | Brevant | B173EE | - | 57.4 | 10.6 | 57.8 | $602.70 |
| 9 | Mustang | Seeds | 13E335 | 56.2 | 9.9 | 57.6 | $590.10 |
| 10 | Stine | 12EH02 | - | 56.0 | 9.8 | 56.8 | $588.00 |
| 11 | NK | NK14-U5E3 | Enlist E3 ® | 55.9 | 10.4 | 57.1 | $586.95 |
| 11 | Stine | 15EE32 | - | 55.9 | 10.4 | 56.3 | $586.95 |
| 13 | Mustang | Seeds | 14E535 | 55.5 | 11.1 | 57.4 | $582.75 |
| 14 | Stine | 12EH02 | - | 55.4 | 10.4 | 56.5 | $581.70 |
| 15 | Brevant | B134EE | - | 55.3 | 10.2 | 56.4 | $580.65 |
| 16 | Stine | 13EH62 | - | 55.1 | 9.8 | 56.9 | $578.55 |
| 17 | NK | NK11-A4E3 | Enlist E3 ® | 54.1 | 10.4 | 57.3 | $568.05 |
| 18 | Stine | 10EH02 | - | 51.6 | 9.5 | 58.8 | $541.80 |
| 19 | Stine | 11EH06 | - | 50.6 | 10.4 | 56.9 | $531.30 |
| 20 | Mustang | Seeds | 10E125 | 50.5 | 9.3 | 57.9 | $530.25 |
| 21 | Stine | 12EG32 | - | 49.4 | 9.7 | 56.9 | $518.70 |
| 22 | Stine | 10EG20 | - | 44.6 | 10.1 | 56.7 | $468.30 |
| 23 | Stine | 10EG20 | - | 37.5 | 9.2 | 55.4 | $393.75 |
Top 5 by Yield: B155EE (Brevant) 60.9, 13EG23 (Stine) 59.6, Seeds (Mustang) 59.3, B144EE (Brevant) 59.0, NK17-H1E3 (NK) 58.5.