Files
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-il-2024-2426629.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

1.8 KiB

Soybean yield trial — Illinois, 2024


Results (top-down by rank)

Rank Brand Product Traits Yield %MST Test Weight Gross Revenue
1 Xitavo XO 3555E 96.9 10.8 57.6 $1017.45
2 Asgrow AG38XF3 - 90.8 11.3 58.9 $953.40
3 Brevant B364EE - 90.0 10.8 59.4 $945.00
4 Asgrow AG33XF3 - 89.4 10.9 58.6 $938.70
5 Xitavo XO 3795E 89.1 11.0 56.7 $935.55
6 Asgrow AG33XF3 - 88.7 10.9 56.5 $931.35
7 NK NK34-D4XF XtendFlex ® 87.5 11.4 57.6 $918.75
8 NK NK37-R5XF XtendFlex ® 87.3 11.3 57.4 $916.65
9 Xitavo XO 3224E 86.6 11.1 58.1 $909.30
10 Brevant B344EE - 86.0 11.2 58.8 $903.00
11 Asgrow AG36XF4 - 85.9 11.5 56.9 $901.95
12 NK NK30-B2E3 Enlist E3 ® 85.8 11.3 58.3 $900.90
13 Asgrow AG30XF4 - 85.4 11.7 58.0 $896.70
13 Asgrow AG39XF3 - 85.4 11.1 57.3 $896.70
15 Asgrow AG33XF3 - 84.2 11.9 55.6 $884.10
16 Asgrow AG33XF3 - 83.6 11.1 56.6 $877.80
17 Asgrow AG27XF3 - 82.7 11.7 57.0 $868.35
18 Xitavo XO 3655E 82.3 11.2 57.2 $864.15

Top 5 by Yield: XO (Xitavo) 96.9, AG38XF3 (Asgrow) 90.8, B364EE (Brevant) 90.0, AG33XF3 (Asgrow) 89.4, XO (Xitavo) 89.1.