Files
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-nc-2025-2469603.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

1.6 KiB

Soybean yield trial — North Carolina, 2025


Results (top-down by rank)

Rank Brand Product Traits Yield %MST Test Weight Gross Revenue
1 NK NK54-J9XFS XtendFlex ® STS ® 83.8 12.3 57.5 $879.90
2 NK NK52-D6E3 Enlist E3 ® 79.2 12.5 57.0 $831.60
2 NK NK47-U1XFS XtendFlex ® STS ® 79.2 12.2 56.5 $831.60
4 NK NK49-C2XFS XtendFlex ® STS ® 77.1 12.0 57.5 $809.55
4 NK NK49-N7XF XtendFlex ® 77.1 12.3 57.0 $809.55
6 NK NK50-W4E3S Enlist E3 ® STS ® 74.6 12.6 57.0 $783.30
7 NK NK47-G5E3S Enlist E3 ® STS ® 74.2 12.6 56.5 $779.10
8 NK NK58-B8E3S Enlist E3 ® STS ® 73.0 12.2 58.0 $766.50
9 NK NK58-Y9XF XtendFlex ® 71.9 11.7 57.5 $754.95
10 NK NK49-U9E3S Enlist E3 ® STS ® 71.4 12.9 56.5 $749.70
11 NK NK52-M2XFS XtendFlex ® STS ® 70.7 12.3 57.0 $742.35
12 NK NK46-D2E3 Enlist E3 ® 68.2 13.2 56.0 $716.10

Top 5 by Yield: NK54-J9XFS (NK) 83.8, NK52-D6E3 (NK) 79.2, NK47-U1XFS (NK) 79.2, NK49-C2XFS (NK) 77.1, NK49-N7XF (NK) 77.1.