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>
2.6 KiB
2.6 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: 2465991
- Cooperator: Prairie Ag Services Inc
- Planted: 2025-05-06
- Harvested: 2025-09-04
- Population: 34,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2465991
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | NK | NK0025-DV | - | 33.8 | 3404.0 | 34502.0 | 237.0 | 2240.0 |
| 2 | NK | NK0440-AT | - | 33.4 | 3314.0 | 33217.0 | 223.0 | 2166.0 |
| 3 | Enogen | E107C1-D | - | 32.7 | 3223.0 | 31618.0 | 226.0 | 2131.0 |
| 4 | NK | NK0604-DV | - | 32.2 | 3319.0 | 32030.0 | 233.0 | 2118.0 |
| 5 | Enogen | E107C1-D | - | 32.1 | 3009.0 | 29016.0 | 170.0 | 1954.0 |
| 6 | NK | NK0604-DV | - | 32.0 | 3334.0 | 31971.0 | 216.0 | 2049.0 |
| 7 | Enogen | E094Z4-D | - | 31.7 | 3401.0 | 32296.0 | 260.0 | 2177.0 |
| 8 | NK | NK9771-DV | - | 31.1 | 3136.0 | 29281.0 | 194.0 | 1946.0 |
| 9 | Enogen | E105Z5-D | - | 30.4 | 3262.0 | 29782.0 | 226.0 | 1985.0 |
| 10 | Pioneer | P0275Q | - | 30.1 | 3658.0 | 33071.0 | 278.0 | 2132.0 |
| 11 | Enogen | E097K6-D | - | 30.0 | 3429.0 | 30852.0 | 244.0 | 2012.0 |
| 11 | NK | NK0025-DV | - | 30.0 | 3455.0 | 31109.0 | 235.0 | 1984.0 |
| 13 | Enogen | E105Z5-D | - | 29.9 | 3588.0 | 32145.0 | 250.0 | 2022.0 |
| 14 | Enogen | E102K7-D | - | 29.7 | 3462.0 | 30835.0 | 235.0 | 1964.0 |
| 15 | Enogen | E095D3-D | - | 29.3 | 3317.0 | 29144.0 | 225.0 | 1905.0 |
| 16 | Enogen | E092W5-D | - | 29.2 | 3443.0 | 30172.0 | 239.0 | 1945.0 |
| 17 | NK | NK0440-AT | - | 28.7 | 3328.0 | 28668.0 | 237.0 | 1904.0 |
| 18 | DEKALB | DKC105-33 | - | 28.4 | 3176.0 | 27087.0 | 203.0 | 1802.0 |
| 19 | DEKALB | DKC105-33 | - | 28.3 | 3410.0 | 28958.0 | 241.0 | 1890.0 |
| 20 | NK | NK9771-DV | - | 27.8 | 3225.0 | 26919.0 | 206.0 | 1757.0 |
| 21 | Enogen | E095D3-D | - | 27.1 | 3209.0 | 26114.0 | 217.0 | 1742.0 |
| 22 | Enogen | E097K6-D | - | 26.7 | 3396.0 | 27163.0 | 236.0 | 1767.0 |
| 23 | Pioneer | P0275Q | - | 26.5 | 3509.0 | 27927.0 | 244.0 | 1779.0 |
| 24 | Enogen | E102K7-D | - | 26.4 | 3423.0 | 27149.0 | 243.0 | 1771.0 |
| 25 | Enogen | E094Z4-D | - | 25.7 | 3454.0 | 26626.0 | 251.0 | 1742.0 |
| 26 | Enogen | E092W5-D | - | 25.1 | 3323.0 | 25010.0 | 234.0 | 1656.0 |
Top 5 by Ton/Acre: NK0025-DV (NK) 33.8, NK0440-AT (NK) 33.4, E107C1-D (Enogen) 32.7, NK0604-DV (NK) 32.2, E107C1-D (Enogen) 32.1.