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 — Minnesota, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Minnesota (MN)
- Year: 2025
- Plot ID: 2467237
- Cooperator: Parkview Acres
- Planted: 2025-05-12
- Harvested: 2025-09-05
- Population: 32,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/mn/2025/2467237
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 | P01851V | - | 32.5 | 3837.0 | 37411.0 | - | - |
| 2 | Brevant | B05D47V | - | 31.9 | 3876.0 | 37093.0 | - | - |
| 3 | Pioneer | P03951PCE | - | 30.9 | 3707.0 | 34364.0 | - | - |
| 4 | Channel | 201-07SSP | - | 30.8 | 3723.0 | 34401.0 | - | - |
| 5 | Channel | 197-99SSP | - | 30.7 | 3933.0 | 36223.0 | - | - |
| 5 | Channel | 201-40VT4P | - | 30.7 | 3761.0 | 34639.0 | - | - |
| 7 | Pioneer | P02405V | - | 30.4 | 3772.0 | 34401.0 | - | - |
| 8 | NK | NK0025-DV | - | 30.1 | 3734.0 | 33718.0 | - | - |
| 8 | Channel | 203-99SSP | - | 30.1 | 3837.0 | 34648.0 | - | - |
| 10 | Renk | Seed | RK583PCE | 29.7 | 3779.0 | 33671.0 | - | - |
| 11 | Brevant | B99R54V | - | 29.3 | 3764.0 | 33086.0 | - | - |
| 12 | DEKALB | DKC101-33 | - | 28.8 | 3727.0 | 32201.0 | - | - |
| 13 | Pioneer | P98125V | - | 28.7 | 3844.0 | 33097.0 | - | - |
| 13 | Enogen | E105Z5-D | - | 28.7 | 3629.0 | 31246.0 | - | - |
| 15 | Renk | Seed | RK586VT4P | 28.5 | 3764.0 | 32182.0 | - | - |
| 16 | Channel | 198-25SSP | - | 28.4 | 3813.0 | 32487.0 | - | - |
| 17 | Renk | Seed | RK579DGVT2P | 28.3 | 3855.0 | 32729.0 | - | - |
| 18 | DEKALB | DKC098-88 | - | 28.2 | 3852.0 | 32588.0 | - | - |
| 18 | NK | NK0440-AT | - | 28.2 | 3801.0 | 32156.0 | - | - |
| 20 | Renk | Seed | RK582SSTX | 27.4 | 3675.0 | 30208.0 | - | - |
| 21 | Enogen | E097K6-D | - | 26.7 | 3508.0 | 28099.0 | - | - |
| 22 | Enogen | E102K7-D | - | 26.4 | 3626.0 | 28718.0 | - | - |
Top 5 by Ton/Acre: P01851V (Pioneer) 32.5, B05D47V (Brevant) 31.9, P03951PCE (Pioneer) 30.9, 201-07SSP (Channel) 30.8, 197-99SSP (Channel) 30.7.