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 — Wisconsin, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Wisconsin (WI)
- Year: 2024
- Plot ID: 2419049
- Cooperator: Prairie Ag Services Inc
- Planted: 2024-05-06
- Harvested: 2024-08-25
- Population: 35,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/wi/2024/2419049
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Enogen | E114C4-DV-LL | - | 25.3 | 3316.0 | 25195.0 | 248.0 | 1708.0 |
| 2 | NK | NK0440-AT | - | 25.1 | 3523.0 | 26559.0 | 249.0 | 1698.0 |
| 3 | Pioneer | P1180XR | - | 23.3 | 3443.0 | 24098.0 | 262.0 | 1609.0 |
| 4 | NK | NK1239-D | - | 22.7 | 3539.0 | 24106.0 | 258.0 | 1557.0 |
| 5 | Enogen | E112S5-D | - | 22.3 | 3446.0 | 23053.0 | 254.0 | 1519.0 |
| 6 | Enogen | E112S5-D | - | 21.9 | 3283.0 | 21572.0 | 249.0 | 1480.0 |
| 7 | Enogen | E114C4-DV-LL | - | 21.5 | 3347.0 | 21609.0 | 261.0 | 1483.0 |
| 8 | Enogen | E107C1-D | - | 21.3 | 3459.0 | 22099.0 | 259.0 | 1463.0 |
| 9 | Pioneer | P1180XR | - | 21.2 | 3811.0 | 24252.0 | 303.0 | 1560.0 |
| 10 | Enogen | E110F4-D | - | 21.1 | 3106.0 | 19618.0 | 252.0 | 1430.0 |
| 11 | Enogen | E107C1-D | - | 20.6 | 3732.0 | 23048.0 | 279.0 | 1458.0 |
| 12 | NK | NK1480-DV | - | 20.4 | 3053.0 | 18717.0 | 237.0 | 1356.0 |
| 12 | NK | NK0501-DV | - | 20.4 | 3513.0 | 21460.0 | 241.0 | 1360.0 |
| 14 | Enogen | E110F4-D | - | 20.2 | 3297.0 | 19993.0 | 248.0 | 1365.0 |
| 15 | Enogen | E105Z5-D | - | 20.0 | 3740.0 | 22404.0 | 287.0 | 1433.0 |
| 15 | NK | NK1239-D | - | 20.0 | 3173.0 | 19032.0 | 228.0 | 1306.0 |
| 17 | Enogen | E111V7-D | - | 19.9 | 3260.0 | 19506.0 | 234.0 | 1317.0 |
| 17 | NK | NK0440-AT | - | 19.9 | 3623.0 | 21604.0 | 268.0 | 1384.0 |
| 19 | NK | NK1480-DV | - | 19.8 | 3762.0 | 22306.0 | 287.0 | 1419.0 |
| 20 | Enogen | E111V7-D | - | 19.7 | 3310.0 | 19605.0 | 247.0 | 1330.0 |
| 21 | Pioneer | P0275Q | - | 19.3 | 3356.0 | 19405.0 | 207.0 | 1219.0 |
| 22 | Enogen | E105Z5-D | - | 18.9 | 3140.0 | 17765.0 | 240.0 | 1256.0 |
| 23 | NK | NK0501-DV | - | 18.8 | 3324.0 | 18785.0 | 237.0 | 1250.0 |
| 24 | Pioneer | P0275Q | - | 18.3 | 3530.0 | 19407.0 | 235.0 | 1213.0 |
Top 5 by Ton/Acre: E114C4-DV-LL (Enogen) 25.3, NK0440-AT (NK) 25.1, P1180XR (Pioneer) 23.3, NK1239-D (NK) 22.7, E112S5-D (Enogen) 22.3.