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>
2.9 KiB
2.9 KiB
Silage yield trial — Ohio, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Ohio (OH)
- Year: 2025
- Plot ID: 2466168
- Cooperator: Stoller B&S Ltd.
- Planted: 2025-05-19
- Harvested: 2025-09-10
- Population: 33,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/oh/2025/2466168
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Golden Harvest | G10U97-V | - | 22.1 | 3383.0 | 22401.0 | 250.0 | 1495.0 |
| 2 | Golden Harvest | G14B32-DV | - | 22.0 | 3285.0 | 21637.0 | 242.0 | 1467.0 |
| 3 | Beck's | 6184V2P | - | 21.6 | 3449.0 | 22331.0 | 257.0 | 1477.0 |
| 4 | Beck's | 6473TCV2P | - | 21.4 | 3274.0 | 20991.0 | 235.0 | 1414.0 |
| 5 | Golden Harvest | G13U96-DV | - | 21.3 | 3291.0 | 20983.0 | 228.0 | 1390.0 |
| 6 | Beck's | 6280TCV2P | - | 21.2 | 3432.0 | 21811.0 | 255.0 | 1446.0 |
| 7 | Enogen | E105Z5-D | - | 21.1 | 3381.0 | 21373.0 | 253.0 | 1434.0 |
| 7 | Enogen | E107C1-D | - | 21.1 | 3072.0 | 19428.0 | 206.0 | 1330.0 |
| 9 | Golden Harvest | G13M31-AA | - | 20.9 | 3337.0 | 20905.0 | 243.0 | 1397.0 |
| 10 | Beck's | 6485SX | - | 20.8 | 3206.0 | 20043.0 | 233.0 | 1375.0 |
| 10 | XL | 6005VC | - | 20.8 | 3003.0 | 18741.0 | 178.0 | 1294.0 |
| 12 | Beck's | 5958TCV2P | - | 20.5 | 3184.0 | 19558.0 | 214.0 | 1308.0 |
| 13 | Beck's | 5794V2P | - | 20.3 | 3079.0 | 18739.0 | 214.0 | 1296.0 |
| 14 | Golden Harvest | G12U11-AA | - | 20.1 | 3203.0 | 19274.0 | 219.0 | 1293.0 |
| 14 | Beck's | 6235D1 | - | 20.1 | 3265.0 | 19708.0 | 235.0 | 1330.0 |
| 16 | Enogen | E108K4-DV | - | 19.9 | 3260.0 | 19426.0 | 230.0 | 1302.0 |
| 16 | Beck's | 5929D1 | - | 19.9 | 3102.0 | 18485.0 | 208.0 | 1257.0 |
| 16 | Enogen | E114C4-DV-LL | - | 19.9 | 3384.0 | 20189.0 | 243.0 | 1332.0 |
| 19 | Enogen | E111V7-D | - | 19.6 | 3380.0 | 19854.0 | 258.0 | 1342.0 |
| 20 | Beck's | 6574TCV2P | - | 19.5 | 3150.0 | 18463.0 | 200.0 | 1222.0 |
| 21 | XL | 5824AM | - | 19.4 | 3220.0 | 18746.0 | 224.0 | 1260.0 |
| 22 | XL | 6064AM | - | 19.3 | 3236.0 | 18715.0 | 232.0 | 1269.0 |
| 22 | Enogen | E117Z7-D | - | 19.3 | 3522.0 | 20382.0 | 281.0 | 1371.0 |
| 24 | Enogen | E112S5-D | - | 19.1 | 3155.0 | 18080.0 | 214.0 | 1222.0 |
| 25 | Beck's | 6374V2P | - | 19.0 | 3126.0 | 17864.0 | 211.0 | 1213.0 |
| 26 | Beck's | 6469V2P | - | 18.9 | 3165.0 | 17902.0 | 216.0 | 1210.0 |
| 26 | Beck's | 6361PCE | - | 18.9 | 3133.0 | 17744.0 | 191.0 | 1194.0 |
| 28 | XL | 6041Q | - | 18.8 | 3263.0 | 18355.0 | 231.0 | 1231.0 |
| 29 | Beck's | 6216PCE | - | 18.0 | 3294.0 | 17794.0 | 239.0 | 1198.0 |
| 30 | Enogen | E102K7-D | - | 16.9 | 2880.0 | 14595.0 | 163.0 | 1018.0 |
Top 5 by Ton/Acre: G10U97-V (Golden Harvest) 22.1, G14B32-DV (Golden Harvest) 22.0, 6184V2P (Beck's) 21.6, 6473TCV2P (Beck's) 21.4, G13U96-DV (Golden Harvest) 21.3.