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>
3.0 KiB
3.0 KiB
Silage yield trial — Virginia, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Virginia (VA)
- Year: 2024
- Plot ID: 2426093
- Cooperator: William Shank
- Planted: 2024-05-29
- Harvested: 2024-10-09
- Population: 32,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/va/2024/2426093
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Chemgro | 7539D4Z | - | 33.1 | 3670.0 | 36407.0 | 261.0 | 2279.0 |
| 2 | Enogen | E117Z7-D | - | 32.4 | 3557.0 | 34558.0 | 262.0 | 2233.0 |
| 3 | Red | Tail | RT 67T79 | 31.5 | 3544.0 | 33541.0 | 253.0 | 2145.0 |
| 3 | Revere | Seed | Revere 1839 TC | 31.5 | 3420.0 | 32346.0 | 254.0 | 2149.0 |
| 5 | Seed | Consultants | SC1185V | 31.3 | 3475.0 | 32593.0 | 261.0 | 2154.0 |
| 6 | Pioneer | P13476Q | - | 31.1 | 3547.0 | 33089.0 | 285.0 | 2223.0 |
| 7 | Pioneer | P1903AM | - | 30.5 | 3557.0 | 32530.0 | 259.0 | 2093.0 |
| 8 | Revere | Seed | Experimental | 29.4 | 3338.0 | 29452.0 | 259.0 | 2019.0 |
| 9 | Enogen | E114C4-DV-LL | - | 28.7 | 3084.0 | 26547.0 | 230.0 | 1883.0 |
| 10 | Augusta | Seed | A1964-DV | 28.1 | 3458.0 | 29184.0 | 255.0 | 1921.0 |
| 10 | Augusta | Seed | A4465-DV | 28.1 | 3561.0 | 30063.0 | 258.0 | 1930.0 |
| 12 | Chemgro | 7539D4Z | - | 28.0 | 3480.0 | 29229.0 | 243.0 | 1873.0 |
| 12 | Seed | Consultants | SC1112Q | 28.0 | 3725.0 | 31267.0 | 275.0 | 1971.0 |
| 14 | Chemgro | 7259DVZ | - | 27.9 | 3188.0 | 26701.0 | 224.0 | 1814.0 |
| 14 | Seed | Consultants | SC1122Q | 27.9 | 3549.0 | 29727.0 | 268.0 | 1946.0 |
| 16 | NK | NK1402-DV | - | 27.8 | 3701.0 | 30821.0 | 272.0 | 1947.0 |
| 17 | Chemgro | 7539D4Z | - | 27.5 | 3482.0 | 28729.0 | 242.0 | 1840.0 |
| 17 | Chemgro | 7539D4Z | - | 27.5 | 3401.0 | 28062.0 | 236.0 | 1822.0 |
| 19 | Channel | 214-78DGVT2P | - | 27.4 | 3541.0 | 29147.0 | 265.0 | 1902.0 |
| 20 | Channel | 217-76VT2P | - | 27.3 | 3386.0 | 27767.0 | 238.0 | 1816.0 |
| 21 | Red | Tail | RT 64T39 | 26.9 | 3601.0 | 29026.0 | 268.0 | 1871.0 |
| 22 | Revere | Seed | Revere 0918 VT2P | 26.8 | 3718.0 | 29891.0 | 292.0 | 1938.0 |
| 23 | Channel | 209-39DGVT2P | - | 26.7 | 3739.0 | 29969.0 | 284.0 | 1910.0 |
| 24 | Pioneer | P1380Q | - | 26.6 | 3611.0 | 28856.0 | 243.0 | 1783.0 |
| 25 | Chemgro | 7789RSX | - | 26.5 | 3722.0 | 29592.0 | 278.0 | 1876.0 |
| 26 | Rob-See-Co | RC6401-AA | - | 25.1 | 3594.0 | 27051.0 | 256.0 | 1716.0 |
| 27 | Red | Tail | RT 61T99 | 24.6 | 3287.0 | 24267.0 | 218.0 | 1582.0 |
| 28 | Augusta | Seed | A6362-D | 24.0 | 3304.0 | 23831.0 | 220.0 | 1553.0 |
| 29 | Brevant | B06U78SXE | - | 19.4 | 3378.0 | 19649.0 | 244.0 | 1300.0 |
| 30 | Chemgro | 5389D5Z | - | 16.5 | 2808.0 | 13871.0 | 150.0 | 947.0 |
Top 5 by Ton/Acre: 7539D4Z (Chemgro) 33.1, E117Z7-D (Enogen) 32.4, Tail (Red) 31.5, Seed (Revere) 31.5, Consultants (Seed) 31.3.