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>
2.0 KiB
2.0 KiB
Silage yield trial — Wisconsin, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Wisconsin (WI)
- Year: 2024
- Plot ID: 2420287
- Cooperator: Lee Vandergeest
- Planted: 2024-05-24
- Harvested: 2024-10-09
- Population: 32,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2024/2420287
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 | NK9231-AA | - | 20.1 | 3716.0 | 22452.0 | 265.0 | 1396.0 |
| 2 | NK | NK9400-V | - | 19.5 | 3357.0 | 19688.0 | 232.0 | 1287.0 |
| 3 | Enogen | E092W5-D | - | 19.3 | 3579.0 | 20722.0 | 258.0 | 1324.0 |
| 4 | Pioneer | P90630AM | - | 19.2 | 3419.0 | 19702.0 | 229.0 | 1258.0 |
| 5 | Enogen | E085Z5-D | - | 18.9 | 3555.0 | 20194.0 | 248.0 | 1277.0 |
| 6 | Enogen | E094Z4-D | - | 18.8 | 3647.0 | 20609.0 | 260.0 | 1296.0 |
| 7 | Brevant | B91K05Q | - | 18.3 | 3488.0 | 19180.0 | 244.0 | 1230.0 |
| 8 | DEKALB | DKC45-74 | - | 18.1 | 3719.0 | 20155.0 | 266.0 | 1255.0 |
| 9 | Brevant | B87D33AM | - | 18.0 | 3758.0 | 20332.0 | 270.0 | 1261.0 |
| 10 | DEKALB | DKC093-05 | - | 17.9 | 3437.0 | 18477.0 | 258.0 | 1230.0 |
| 11 | NK | NK9021-D | - | 17.5 | 3588.0 | 18830.0 | 254.0 | 1192.0 |
| 12 | Pioneer | P8859AM | - | 17.2 | 3669.0 | 18927.0 | 258.0 | 1180.0 |
| 13 | Pioneer | P87040PCE | - | 16.7 | 3469.0 | 17341.0 | 242.0 | 1114.0 |
| 14 | Brevant | B92D25Q | - | 16.3 | 3764.0 | 18422.0 | 274.0 | 1147.0 |
| 15 | Pioneer | P9193AM | - | 15.6 | 3770.0 | 17662.0 | 266.0 | 1085.0 |
| 16 | Red | Tail | RT 41T14 | 12.8 | 3786.0 | 14573.0 | 289.0 | 924.0 |
| 17 | Red | Tail | RT 38T89 | 10.8 | 3679.0 | 11893.0 | 268.0 | 751.0 |
| 18 | Red | Tail | RT 43T48 | 10.4 | 3665.0 | 11466.0 | 267.0 | 725.0 |
Top 5 by Ton/Acre: NK9231-AA (NK) 20.1, NK9400-V (NK) 19.5, E092W5-D (Enogen) 19.3, P90630AM (Pioneer) 19.2, E085Z5-D (Enogen) 18.9.