justin
0e625553e5
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>
2.1 KiB
2.1 KiB
Silage yield trial — Wisconsin, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Wisconsin (WI)
- Year: 2025
- Plot ID: 2466165
- Cooperator: Destiny Farms
- Planted: 2025-05-09
- Harvested: 2025-10-02
- Population: 34,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2466165
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Pioneer | P9955AM | - | 36.5 | 3433.0 | 37569.0 | 231.0 | 2397.0 |
| 2 | Pioneer | P9466PCE | - | 35.5 | 3264.0 | 34801.0 | 207.0 | 2246.0 |
| 3 | Enogen | E094Z4-D | - | 34.7 | 3224.0 | 33555.0 | 219.0 | 2237.0 |
| 4 | Pioneer | P96760V | - | 34.5 | 3439.0 | 35600.0 | 212.0 | 2199.0 |
| 4 | Prairie | Estates | Genetics S3557-D | 34.5 | 3342.0 | 34631.0 | 204.0 | 2175.0 |
| 6 | Pioneer | P9823V | - | 33.1 | 3280.0 | 32577.0 | 215.0 | 2119.0 |
| 7 | Brevant | B96B29Q | - | 32.8 | 3569.0 | 35148.0 | 252.0 | 2230.0 |
| 8 | NK | NK9231-AA | - | 32.7 | 3232.0 | 31741.0 | 209.0 | 2075.0 |
| 9 | Enogen | E092W5-D | - | 32.5 | 3574.0 | 34844.0 | 243.0 | 2176.0 |
| 10 | NK | NK9771-DV | - | 30.9 | 3049.0 | 28264.0 | 180.0 | 1870.0 |
| 11 | Prairie | Estates | Genetics G3351-3110 | 30.4 | 3259.0 | 29754.0 | 204.0 | 1913.0 |
| 12 | Pioneer | P9884Q | - | 30.1 | 3487.0 | 31520.0 | 238.0 | 2001.0 |
| 13 | Pioneer | P0275Q | - | 29.7 | 3480.0 | 31013.0 | 224.0 | 1930.0 |
| 14 | Brevant | B01B36SXE | - | 29.2 | 3434.0 | 30038.0 | 214.0 | 1865.0 |
| 15 | Prairie | Estates | Genetics S3482-DV | 28.9 | 3002.0 | 26029.0 | 179.0 | 1744.0 |
| 16 | Brevant | B99B79SX | - | 28.7 | 3381.0 | 29151.0 | 219.0 | 1852.0 |
| 17 | Brevant | B95U78SXE | - | 28.6 | 3358.0 | 28829.0 | 215.0 | 1833.0 |
| 17 | Brevant | B97B73SX | - | 28.6 | 3285.0 | 28221.0 | 200.0 | 1791.0 |
Top 5 by Ton/Acre: P9955AM (Pioneer) 36.5, P9466PCE (Pioneer) 35.5, E094Z4-D (Enogen) 34.7, P96760V (Pioneer) 34.5, Estates (Prairie) 34.5.