Files
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-il-2025-2466429.md
T
justin 0e625553e5 gh_plot_reports corpus (4,299 plots) + concurrency + 4-GPU pool
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>
2026-05-25 16:46:35 -04:00

1.8 KiB

Soybean yield trial — Illinois, 2025


Results (top-down by rank)

Rank Brand Product Traits Yield %MST Test Weight Gross Revenue
1 Alloy A30E35 - 93.0 - - $976.50
2 Pioneer P21Z71E - 90.1 - - $946.05
3 Brevant B275EE - 86.1 - - $904.05
4 NK NK21-C2E3 Enlist E3 ® 85.4 - - $896.70
5 Alloy A23E36 - 85.1 - - $893.55
6 NK NK28-G7E3S Enlist E3 ® STS ® 84.4 - - $886.20
7 Xitavo XO 2366E 84.0 - - $882.00
8 Xitavo XO 2926E 83.0 - - $871.50
9 NK NK26-M6E3 Enlist E3 ® 81.3 - - $853.65
10 Alloy A28E36 - 80.7 - - $847.35
11 Alloy A25E36 - 80.4 - - $844.20
12 Xitavo XO 2556E 80.1 - - $841.05
12 NK NK23-P1E3 Enlist E3 ® 80.1 - - $841.05
14 Pioneer P27Z41E - 79.9 - - $838.95
15 Brevant B205EE - 78.7 - - $826.35
16 Pioneer P28Z30E - 77.7 - - $815.85
17 Alloy A29E36 - 76.9 - - $807.45
18 Alloy A27E35 - 76.5 - - $803.25
19 Alloy A31E36 - 76.4 - - $802.20
20 Alloy A29E35 - 73.7 - - $773.85

Top 5 by Yield: A30E35 (Alloy) 93.0, P21Z71E (Pioneer) 90.1, B275EE (Brevant) 86.1, NK21-C2E3 (NK) 85.4, A23E36 (Alloy) 85.1.