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>
2.5 KiB
2.5 KiB
Soybean yield trial — Minnesota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Minnesota (MN)
- Year: 2024
- Plot ID: 2418987
- Cooperator: Helena Agri-Enterprises Llc
- Planted: 2024-05-13
- Harvested: 2024-10-03
- Population: 140,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mn/2024/2418987
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Brevant | B214EE | - | 72.9 | 8.6 | 57.4 | $765.45 |
| 2 | Brevant | B164EE | - | 69.9 | 8.5 | 55.2 | $733.95 |
| 2 | Mustang | Seeds | 20E723 | 69.9 | 8.5 | 56.7 | $733.95 |
| 4 | Mustang | Seeds | 18E825 | 68.5 | 8.4 | 55.0 | $719.25 |
| 4 | Mustang | Seeds | 22E435 | 68.5 | 8.4 | 57.6 | $719.25 |
| 6 | Alloy | A18E35 | - | 68.1 | 8.6 | 54.2 | $715.05 |
| 7 | APEX | AE1520 | - | 67.0 | 8.5 | 55.8 | $703.50 |
| 8 | NK | NK14-U5E3 | Enlist E3 ® | 66.3 | 8.7 | 55.7 | $696.15 |
| 8 | Brevant | B224EE | - | 66.3 | 9.9 | 55.6 | $696.15 |
| 10 | Mustang | Seeds | 13E335 | 66.1 | 8.2 | 53.9 | $693.92 |
| 11 | APEX | AE1710 | - | 65.4 | 8.4 | 54.5 | $686.70 |
| 12 | NK | NK15-G9E3S | Enlist E3 ® STS ® | 65.3 | 8.5 | 53.7 | $685.26 |
| 13 | APEX | AE1220 | - | 64.8 | 8.4 | 55.5 | $680.40 |
| 13 | Mustang | Seeds | 14E535 | 64.8 | 8.1 | 55.6 | $680.40 |
| 15 | Alloy | A21E34 | - | 64.4 | 8.6 | 53.2 | $675.17 |
| 16 | Mustang | Seeds | 22E441 | 64.1 | 9.5 | 54.4 | $673.05 |
| 17 | NK | NK19-T8E3S | Enlist E3 ® STS ® | 64.0 | 8.4 | 51.4 | $668.67 |
| 18 | NK | NK18-R4E3 | Enlist E3 ® | 63.8 | 9.1 | 54.2 | $669.90 |
| 19 | Mustang | Seeds | 16E634 | 63.3 | 8.6 | 56.9 | $664.65 |
| 20 | NK | NK16-Z6E3 | Enlist E3 ® | 62.9 | 8.7 | 55.0 | $660.45 |
| 21 | NK | NK21-C2E3 | Enlist E3 ® | 62.6 | 8.7 | 55.3 | $657.30 |
| 22 | Brevant | B173EE | - | 62.2 | 8.5 | 50.7 | $648.99 |
| 23 | Mustang | Seeds | 23E824 | 61.9 | 8.6 | 56.0 | $649.95 |
| 24 | Brevant | B144EE | - | 60.8 | 8.5 | 54.9 | $638.40 |
| 25 | APEX | AE1900 | - | 60.4 | 8.7 | 56.2 | $634.20 |
| 26 | Alloy | A16E34 | - | 59.9 | 8.2 | 54.6 | $628.95 |
| 27 | Mustang | Seeds | 16E725 | 58.9 | 8.4 | 55.0 | $618.45 |
| 28 | Alloy | A14E35 | - | 58.2 | 8.2 | 52.8 | $609.70 |
| 29 | Alloy | A13E35 | - | 57.5 | 8.8 | 53.9 | $603.64 |
Top 5 by Yield: B214EE (Brevant) 72.9, B164EE (Brevant) 69.9, Seeds (Mustang) 69.9, Seeds (Mustang) 68.5, Seeds (Mustang) 68.5.