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>
2.4 KiB
2.4 KiB
Silage yield trial — Illinois, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Illinois (IL)
- Year: 2024
- Plot ID: 2419102
- Cooperator: Prairie Ag Services Inc
- Planted: 2024-05-12
- Harvested: 2024-09-02
- Population: 35,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/il/2024/2419102
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 | NK1480-DV | - | 33.3 | 3350.0 | 33510.0 | 230.0 | 2186.0 |
| 2 | Enogen | E114C4-DV-LL | - | 31.9 | 3384.0 | 32400.0 | 244.0 | 2140.0 |
| 3 | NK | NK0440-AT | - | 31.5 | 3636.0 | 34409.0 | 255.0 | 2152.0 |
| 4 | Enogen | E114C4-DV-LL | - | 30.5 | 3141.0 | 28757.0 | 221.0 | 1974.0 |
| 5 | Enogen | E112S5-D | - | 30.4 | 3159.0 | 28852.0 | 193.0 | 1883.0 |
| 6 | NK | NK1239-D | - | 30.2 | 3193.0 | 28899.0 | 207.0 | 1907.0 |
| 7 | NK | NK1480-DV | - | 29.6 | 3372.0 | 29982.0 | 239.0 | 1974.0 |
| 7 | Enogen | E105Z5-D | - | 29.6 | 3196.0 | 28387.0 | 196.0 | 1838.0 |
| 7 | NK | NK1239-D | - | 29.6 | 3316.0 | 29440.0 | 219.0 | 1907.0 |
| 7 | NK | NK0440-AT | - | 29.6 | 3522.0 | 31296.0 | 248.0 | 1999.0 |
| 11 | Enogen | E107C1-D | - | 29.5 | 3370.0 | 29823.0 | 231.0 | 1938.0 |
| 12 | Enogen | E107C1-D | - | 29.4 | 3361.0 | 29676.0 | 237.0 | 1953.0 |
| 13 | Enogen | E111V7-D | - | 29.3 | 3361.0 | 29510.0 | 237.0 | 1941.0 |
| 14 | Enogen | E112S5-D | - | 28.8 | 2976.0 | 25703.0 | 169.0 | 1723.0 |
| 15 | Enogen | E110F4-D | - | 28.7 | 3415.0 | 29389.0 | 246.0 | 1930.0 |
| 16 | Enogen | E110F4-D | - | 28.5 | 3172.0 | 27141.0 | 201.0 | 1785.0 |
| 17 | Enogen | E105Z5-D | - | 27.3 | 3426.0 | 28050.0 | 243.0 | 1827.0 |
| 18 | NK | NK0501-DV | - | 27.2 | 3237.0 | 26427.0 | 221.0 | 1760.0 |
| 19 | Enogen | E111V7-D | - | 26.1 | 2867.0 | 22457.0 | 181.0 | 1583.0 |
| 20 | NK | NK0501-DV | - | 25.8 | 3242.0 | 25135.0 | 210.0 | 1641.0 |
| 21 | Pioneer | P0275Q | - | 25.5 | 3318.0 | 25389.0 | 236.0 | 1688.0 |
| 22 | Pioneer | P1180XR | - | 24.2 | 3627.0 | 26369.0 | 259.0 | 1664.0 |
| 22 | Pioneer | P1180XR | - | 24.2 | 3298.0 | 23958.0 | 231.0 | 1591.0 |
| 24 | Pioneer | P0275Q | - | 23.2 | 3243.0 | 22613.0 | 234.0 | 1534.0 |
Top 5 by Ton/Acre: NK1480-DV (NK) 33.3, E114C4-DV-LL (Enogen) 31.9, NK0440-AT (NK) 31.5, E114C4-DV-LL (Enogen) 30.5, E112S5-D (Enogen) 30.4.