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>
2.5 KiB
2.5 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: 2467219
- Cooperator: Roerview Dairy LLC
- Planted: 2025-05-09
- Harvested: 2025-09-25
- Population: 31,500 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/mn/2025/2467219
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 | P02405V | - | 36.3 | 3235.0 | 35229.0 | - | - |
| 2 | Brevant | B99A24V | - | 35.4 | 3160.0 | 33559.0 | - | - |
| 3 | NK | NK0604-DV | - | 35.1 | 3262.0 | 34349.0 | - | - |
| 4 | DEKALB | DKC102-13 | - | 34.8 | 3097.0 | 32333.0 | - | - |
| 5 | DEKALB | DKC103-63 | - | 34.4 | 3111.0 | 32106.0 | - | - |
| 5 | Dairyland | Seed | HIDF-4321V | 34.4 | 3062.0 | 31600.0 | - | - |
| 7 | Brevant | B05D47V | - | 34.1 | 2969.0 | 30373.0 | - | - |
| 8 | Brevant | B05D47V | - | 33.8 | 3167.0 | 32113.0 | - | - |
| 9 | Pioneer | P0075Q | - | 33.4 | 3142.0 | 31483.0 | - | - |
| 10 | Pioneer | P98125PCE | - | 33.3 | 3240.0 | 32368.0 | - | - |
| 11 | DEKALB | DKC104-14 | - | 32.9 | 3121.0 | 30804.0 | - | - |
| 12 | Pioneer | P01851V | - | 32.6 | 3107.0 | 30386.0 | - | - |
| 13 | Brevant | B04J45V | - | 32.5 | 3196.0 | 31161.0 | - | - |
| 14 | NK | NK9771-DV | - | 32.3 | 3108.0 | 30117.0 | - | - |
| 14 | Dairyland | Seed | HIDF-3855Q | 32.3 | 3072.0 | 29768.0 | - | - |
| 16 | NK | NK0025-DV | - | 32.2 | 3128.0 | 30216.0 | - | - |
| 16 | DEKALB | DKC105-33 | - | 32.2 | 3086.0 | 29811.0 | - | - |
| 18 | DEKALB | DKC105-25 | - | 32.1 | 3127.0 | 30113.0 | - | - |
| 19 | Dairyland | Seed | HiDF-3802Q | 31.9 | 2987.0 | 28586.0 | - | - |
| 20 | Brevant | B05D47V | - | 31.8 | 3146.0 | 30013.0 | - | - |
| 21 | DEKALB | DKC104-08 | - | 31.6 | 3090.0 | 29293.0 | - | - |
| 21 | DEKALB | DKC105-25 | - | 31.6 | 3022.0 | 28649.0 | - | - |
| 23 | Brevant | B99R54V | - | 31.0 | 3200.0 | 29760.0 | - | - |
| 24 | Pioneer | P03115V | - | 30.1 | 3219.0 | 29068.0 | - | - |
| 25 | NK | NK0252-D | - | 29.9 | 2985.0 | 26775.0 | - | - |
| 26 | Brevant | B05D47V | - | 28.8 | 3078.0 | 26594.0 | - | - |
| 27 | NK | NK0440-AT | - | 28.1 | 2996.0 | 25256.0 | - | - |
| 28 | Brevant | B96M56PCE | - | 25.9 | 3109.0 | 24157.0 | - | - |
Top 5 by Ton/Acre: P02405V (Pioneer) 36.3, B99A24V (Brevant) 35.4, NK0604-DV (NK) 35.1, DKC102-13 (DEKALB) 34.8, DKC103-63 (DEKALB) 34.4.