Files
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-sd-2024-2419568.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 — South Dakota, 2024


Results (top-down by rank)

Rank Brand Product Traits Yield %MST Test Weight Gross Revenue
1 Stine 11EC02 - 66.2 9.1 - $695.10
2 Jacobsen J1710E3 - 64.3 10.1 - $675.15
3 Jacobsen J1520E3 - 63.8 9.9 - $669.90
4 Stine 15EE32 - 62.5 10.1 - $656.25
5 Stine 13EG23 - 60.4 9.7 - $634.20
6 Stine 11EH06 - 60.2 10.0 - $632.10
7 Stine 13EH62 - 59.5 9.3 - $624.75
8 LG Seeds LGS1832E3 - 58.9 10.1 - $618.45
8 Jacobsen J1930E3 - 58.9 12.0 - $618.45
10 Stine 14EE21 - 58.2 10.3 - $611.10
11 Golden Harvest GH1495E3 Enlist E3 ® 57.5 9.6 - $603.75
12 LG Seeds LGS1043E3 - 56.5 9.2 - $593.25
13 Golden Harvest GH1194E3 Enlist E3 ® 55.1 9.6 - $578.55
14 Stine 08EC32 - 54.1 9.2 - $568.05
14 LG Seeds LGS1206E3 - 54.1 9.2 - $568.05
16 Jacobsen J1250E3 - 53.5 9.2 - $561.75
17 LG Seeds LGS0830E3 - 52.4 9.0 - $550.20
18 LG Seeds LGS1551E3 - 52.1 9.6 - $547.05
19 Jacobsen J1643E3 - 49.5 10.0 - $519.75

Top 5 by Yield: 11EC02 (Stine) 66.2, J1710E3 (Jacobsen) 64.3, J1520E3 (Jacobsen) 63.8, 15EE32 (Stine) 62.5, 13EG23 (Stine) 60.4.