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>
2.3 KiB
2.3 KiB
Silage yield trial — Minnesota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Minnesota (MN)
- Year: 2024
- Plot ID: 2414836
- Cooperator: Chs Herman
- Planted: 2024-04-24
- Harvested: 2024-09-05
- Population: 31,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/mn/2024/2414836
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Allegiant | Allegiant | 9747 TRE | 32.8 | 3648.0 | 35853.0 | 257.0 | 2244.0 |
| 2 | NK | NK0440-AT | - | 30.7 | 3296.0 | 30380.0 | 235.0 | 2032.0 |
| 3 | Enogen | E094Z4-D | - | 30.2 | 3690.0 | 33392.0 | 266.0 | 2096.0 |
| 4 | DEKALB | DKC102-28 | - | 29.7 | 3358.0 | 29911.0 | 229.0 | 1944.0 |
| 5 | DEKALB | DKC103-47 | - | 29.5 | 3386.0 | 30002.0 | 234.0 | 1951.0 |
| 6 | Allegiant | Experimental | - | 29.4 | 3135.0 | 27669.0 | 205.0 | 1854.0 |
| 7 | Enogen | E105Z5-D | - | 29.2 | 3544.0 | 31092.0 | 259.0 | 2009.0 |
| 8 | Allegiant | Allegiant | 10050 VT2P | 28.9 | 3650.0 | 31629.0 | 269.0 | 2016.0 |
| 9 | NK | NK0501-DV | - | 28.2 | 3085.0 | 26127.0 | 191.0 | 1740.0 |
| 10 | Enogen | E107C1-D | - | 27.8 | 2516.0 | 20996.0 | 131.0 | 1571.0 |
| 11 | Brevant | B99B79SX | - | 26.9 | 3762.0 | 30353.0 | 273.0 | 1887.0 |
| 11 | Enogen | E095D3-D | - | 26.9 | 3637.0 | 29384.0 | 266.0 | 1869.0 |
| 13 | Allegiant | Allegiant | 10166 SSPro | 26.4 | 3211.0 | 25408.0 | 206.0 | 1664.0 |
| 14 | Enogen | E100A3-D | - | 26.1 | 3347.0 | 26227.0 | 227.0 | 1705.0 |
| 15 | Allegiant | Allegiant | 9884 DGVT2P | 25.4 | 2934.0 | 22319.0 | 184.0 | 1551.0 |
| 16 | NK | NK0007-AA | - | 24.3 | 3346.0 | 24403.0 | 228.0 | 1591.0 |
| 17 | Allegiant | Allegiant | 9825 VT2P | 23.7 | 2711.0 | 19248.0 | 112.0 | 1369.0 |
| 17 | Allegiant | Allegiant | 9611 SSP | 23.7 | 2659.0 | 18928.0 | 118.0 | 1341.0 |
| 19 | NK | NK9832-AA | - | 23.6 | 3339.0 | 23595.0 | 235.0 | 1559.0 |
| 20 | Brevant | B99B79SX | - | 21.9 | 3355.0 | 22027.0 | 233.0 | 1442.0 |
| 21 | NK | NK0252-D | - | 19.2 | 3434.0 | 19785.0 | 243.0 | 1286.0 |
Top 5 by Ton/Acre: Allegiant (Allegiant) 32.8, NK0440-AT (NK) 30.7, E094Z4-D (Enogen) 30.2, DKC102-28 (DEKALB) 29.7, DKC103-47 (DEKALB) 29.5.