Files
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-nd-2024-2420030.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 — North Dakota, 2024


Results (top-down by rank)

Rank Brand Product Traits Yield %MST Test Weight Gross Revenue
1 Attain Attain 03A5N 48.0 11.4 55.4 $504.00
2 Brevant B032EE - 46.1 17.9 53.7 $483.77
3 Allegiant Allegiant 01F24N XF 46.0 9.8 55.3 $483.00
4 Brevant B014EE - 45.8 13.1 54.6 $480.90
5 Asgrow AG02XF5 - 45.0 8.6 55.8 $472.50
6 Allegiant Allegiant 04F85N XF 44.4 10.4 54.3 $466.20
7 Attain Attain 01A5N 43.6 16.9 54.5 $457.80
8 Asgrow AG04XF4 - 42.6 9.8 55.9 $447.30
9 Asgrow AG05XF4 - 42.5 13.8 54.6 $446.25
9 Asgrow AG01XF3 - 42.5 9.4 57.1 $446.25
11 NK NK05-W3XF XtendFlex ® 40.1 10.3 56.3 $421.05
12 NK NK03-J1XF XtendFlex ® 39.6 8.2 55.3 $415.80
13 NK NK06-C4XF XtendFlex ® 39.5 10.2 56.5 $414.75
14 NK NK02-Y2XF XtendFlex ® 38.8 8.5 56.1 $407.40
15 Allegiant Allegiant 05F54N XF 38.6 10.8 55.8 $405.30
16 NK NK02-M4XF XtendFlex ® 37.6 9.1 55.5 $394.80

Top 5 by Yield: Attain (Attain) 48.0, B032EE (Brevant) 46.1, Allegiant (Allegiant) 46.0, B014EE (Brevant) 45.8, AG02XF5 (Asgrow) 45.0.