Files
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-il-2024-2418714.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

1.7 KiB

Soybean yield trial — Illinois, 2024


Results (top-down by rank)

Rank Brand Product Traits Yield %MST Test Weight Gross Revenue
1 AgriGold G2003E3 - 75.8 9.5 - $795.90
2 NK NK26-M6E3 Enlist E3 ® 73.4 9.4 - $770.70
3 AgriGold G2601E3 - 73.2 9.2 - $768.60
4 NK NK23-P1E3 Enlist E3 ® 72.4 9.8 - $760.20
4 Attain Attain 25A3NS 72.4 9.4 - $760.20
6 Attain Experimental - 72.2 9.0 - $758.10
7 NK NK21-C2E3 Enlist E3 ® 70.7 9.4 - $742.35
7 Alloy A27E35 - 70.7 9.0 - $742.35
9 AgriGold G2361E3 - 67.6 9.5 - $709.80
10 Alloy A26E33 - 67.4 9.6 - $707.70
11 AgriGold G3051E3 - 66.4 9.2 - $697.20
12 AgriGold G2893E3 - 66.0 8.9 - $693.00
13 NK NK27-J5E3 Enlist E3 ® 64.6 9.5 - $678.30
13 Alloy A28E34 - 64.6 9.5 - $678.30
15 NK NK28-B9E3S Enlist E3 ® STS ® 64.4 9.1 - $676.20
16 NK NK19-T8E3S Enlist E3 ® STS ® 59.1 10.0 - $620.55

Top 5 by Yield: G2003E3 (AgriGold) 75.8, NK26-M6E3 (NK) 73.4, G2601E3 (AgriGold) 73.2, NK23-P1E3 (NK) 72.4, Attain (Attain) 72.4.