Files
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-mb-2025-2469564.md
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

1.7 KiB

Soybean yield trial — MB, 2025


Results (top-down by rank)

Rank Brand Product Traits Yield %MST Test Weight Gross Revenue
1 DEKALB DKB006-80 - 63.1 9.4 - $662.55
2 NK S007-A2XS - 62.7 10.1 - $658.35
3 DEKALB DKB006-80 - 61.9 9.8 - $649.95
4 DEKALB DKB004-04 - 60.2 10.1 - $632.10
4 Prograin Experimental - 60.2 9.4 - $632.10
6 Prograin Oslo XF 59.8 9.7 - $627.90
7 DEKALB DKB006-80 - 59.1 10.5 - $620.55
7 Prograin Melo XF 59.1 9.9 - $620.55
9 Brevant B0065EE - 58.8 9.6 - $617.40
10 Sevita International SI 00623XT 58.6 10.0 - $615.30
11 NK S007-C2E3 - 58.4 9.8 - $613.20
12 Maizex Moose R2X 58.0 10.0 - $609.00
13 Brevant B0045EE - 57.6 9.6 - $604.80
14 Thunder Seed TH82005 R2X 56.7 10.5 - $595.35
15 NK S003-B8XF - 54.2 9.5 - $569.10
16 Thunder Seed TH85003XF 53.6 10.4 - $562.80
16 Maizex Experimental - 53.6 10.2 - $562.80
18 Brett Young Experimental 51.2 10.1 - $537.60

Top 5 by Yield: DKB006-80 (DEKALB) 63.1, S007-A2XS (NK) 62.7, DKB006-80 (DEKALB) 61.9, DKB004-04 (DEKALB) 60.2, Experimental (Prograin) 60.2.