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: 2418671
- Cooperator: Double S Dairy
- Planted: 2024-05-10
- Harvested: 2024-09-18
- Population: 36,000 seeds/acre
- Row width: 20"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2024/2418671
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 | P13777V | - | 40.3 | 3003.0 | 36280.0 | 196.0 | 2500.0 |
| 2 | Pioneer | P10625V | - | 39.7 | 2972.0 | 35435.0 | 172.0 | 2374.0 |
| 3 | Enogen | E107C1-D | - | 39.3 | 3249.0 | 38268.0 | 231.0 | 2581.0 |
| 4 | Enogen | E112S5-D | - | 39.0 | 3284.0 | 38425.0 | 221.0 | 2523.0 |
| 5 | Pioneer | P12065Q | - | 38.6 | 3195.0 | 37000.0 | 208.0 | 2443.0 |
| 6 | Enogen | E114C4-DV-LL | - | 37.5 | 3152.0 | 35481.0 | 206.0 | 2369.0 |
| 7 | Pioneer | P14830Q | - | 37.2 | 3182.0 | 35509.0 | 212.0 | 2369.0 |
| 8 | Pioneer | P1267Q | - | 36.9 | 3243.0 | 35865.0 | 216.0 | 2364.0 |
| 9 | Enogen | E110F4-D | - | 36.8 | 3279.0 | 36192.0 | 224.0 | 2388.0 |
| 10 | Pioneer | P08075V | - | 35.9 | 3258.0 | 35092.0 | 212.0 | 2289.0 |
| 11 | Pioneer | P09312V | - | 35.7 | 2994.0 | 32079.0 | 183.0 | 2171.0 |
| 12 | Enogen | E113Z5-D | - | 35.6 | 3169.0 | 33818.0 | 199.0 | 2220.0 |
| 12 | Enogen | E111V7-D | - | 35.6 | 3248.0 | 34718.0 | 215.0 | 2282.0 |
| 14 | Pioneer | P08133Q | - | 35.5 | 3045.0 | 32472.0 | 198.0 | 2214.0 |
| 15 | Pioneer | P08527V | - | 34.2 | 3014.0 | 30936.0 | 178.0 | 2065.0 |
| 16 | Pioneer | P0529Q | - | 34.0 | 3552.0 | 36238.0 | 250.0 | 2304.0 |
| 17 | Pioneer | P13968AMXT | - | 33.8 | 3303.0 | 33498.0 | 229.0 | 2212.0 |
| 18 | Brevant | B06U78SXE | - | 31.3 | 2798.0 | 26250.0 | 141.0 | 1836.0 |
Top 5 by Ton/Acre: P13777V (Pioneer) 40.3, P10625V (Pioneer) 39.7, E107C1-D (Enogen) 39.3, E112S5-D (Enogen) 39.0, P12065Q (Pioneer) 38.6.