Files
seed-mcp/corpus/gh_plot_reports/ghpr-silage-mn-2025-2466550.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

Silage yield trial — Minnesota, 2025


Results (top-down by rank)

Rank Brand Product Traits Ton/Acre Milk Per Acre Milk Per Ton Beef Per Acre Beef Per Ton
1 DEKALB DKC094-67 - 33.7 3657.0 36928.0 266.0 2339.0
2 NK NK9044-AA - 30.6 3505.0 32159.0 266.0 2124.0
3 Brevant B96M56PCE - 29.2 3416.0 29969.0 252.0 1986.0
4 DEKALB DKC094-78 - 28.8 3555.0 30755.0 255.0 1967.0
5 NK NK9231-AA - 28.2 3511.0 29666.0 259.0 1934.0
6 Brevant B91W35AM - 27.4 3679.0 30239.0 287.0 1966.0
7 NK NK9771-DV - 27.3 3171.0 25979.0 220.0 1762.0
8 NK NK9021-D - 27.2 3483.0 28454.0 264.0 1885.0
9 Brevant B99A24V - 26.9 3576.0 28853.0 270.0 1879.0
10 NK NK9175-DV - 26.4 3484.0 27566.0 256.0 1802.0
11 NK NK9400-V - 26.1 3619.0 28381.0 271.0 1830.0
12 NK NK9805-DV - 25.0 3405.0 25579.0 250.0 1695.0
13 NK NK0007-AA - 23.5 3356.0 23645.0 268.0 1637.0

Top 5 by Ton/Acre: DKC094-67 (DEKALB) 33.7, NK9044-AA (NK) 30.6, B96M56PCE (Brevant) 29.2, DKC094-78 (DEKALB) 28.8, NK9231-AA (NK) 28.2.