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>
2.8 KiB
2.8 KiB
Silage yield trial — Minnesota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Minnesota (MN)
- Year: 2024
- Plot ID: 2435228
- Cooperator: Little Falls, MN
- Planted: 2024-05-14
- Harvested: 2024-09-13
- Population: 34,000 seeds/acre
- URL: https://www.goldenharvestseeds.com/silage/plot-report/mn/2024/2435228
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Channel | 213-99SSP | - | 35.5 | 4010.0 | 42723.0 | - | - |
| 2 | Brevant | B99A24V | - | 33.9 | 3779.0 | 38404.0 | - | - |
| 3 | Renk | Seed | RK593VT2P | 33.8 | 3873.0 | 39299.0 | - | - |
| 4 | Brevant | B05D47V | - | 33.1 | 3652.0 | 36262.0 | - | - |
| 5 | Channel | 201-07SSP | - | 33.0 | 3765.0 | 37237.0 | - | - |
| 6 | Pioneer | P98533PCE | - | 32.5 | 3799.0 | 37038.0 | - | - |
| 7 | Pioneer | P1185Q | - | 32.4 | 3867.0 | 37601.0 | - | - |
| 8 | Pioneer | P9955V | - | 32.1 | 3792.0 | 36558.0 | - | - |
| 9 | NK | NK0501-DV | - | 32.0 | 3555.0 | 34085.0 | - | - |
| 10 | Channel | 197-66VT2P | - | 31.9 | 3798.0 | 36374.0 | - | - |
| 11 | LG Seeds | LG55C32SSP | - | 31.5 | 3627.0 | 34219.0 | - | - |
| 11 | Renk | Seed | RK710DGVT2P | 31.5 | 3579.0 | 33838.0 | - | - |
| 13 | Channel | 200-23VT2P | - | 31.1 | 3756.0 | 35008.0 | - | - |
| 14 | Renk | Seed | RK609VT2P | 31.0 | 3676.0 | 34188.0 | - | - |
| 15 | Channel | 195-85DGVT2P | - | 30.9 | 3737.0 | 34854.0 | - | - |
| 16 | XL | 5413Q | - | 30.6 | 3589.0 | 32940.0 | - | - |
| 17 | Pioneer | P1185Q | - | 30.3 | 3722.0 | 33825.0 | - | - |
| 18 | LG Seeds | LG5525VT2P | - | 30.1 | 3669.0 | 33105.0 | - | - |
| 19 | Renk | Seed | RK710SSTX | 29.9 | 3686.0 | 33034.0 | - | - |
| 20 | Pioneer | P0529Q | - | 29.8 | 3678.0 | 32841.0 | - | - |
| 20 | DEKALB | DKC106-98 | - | 29.8 | 3518.0 | 31491.0 | - | - |
| 22 | Pioneer | P05466V | - | 29.4 | 3716.0 | 32783.0 | - | - |
| 23 | DEKALB | DKC103-47 | - | 29.1 | 3544.0 | 30949.0 | - | - |
| 24 | XL | 5508Q | - | 29.0 | 3690.0 | 32061.0 | - | - |
| 25 | NK | NK9771-DV | - | 28.9 | 3510.0 | 30454.0 | - | - |
| 26 | Beck's | 4720D2 | - | 28.8 | 3758.0 | 32495.0 | - | - |
| 26 | Pioneer | P04922Q | - | 28.8 | 3717.0 | 32094.0 | - | - |
| 28 | NK | NK0440-AT | - | 28.6 | 3607.0 | 30971.0 | - | - |
| 29 | Renk | Seed | RK642SSTX | 28.5 | 3790.0 | 32368.0 | - | - |
| 30 | XL | 5145Q | - | 28.2 | 3692.0 | 31203.0 | - | - |
| 30 | Brevant | B01X44V | - | 28.2 | 3722.0 | 31508.0 | - | - |
| 32 | Brevant | B98Z37V | - | 27.8 | 3889.0 | 32489.0 | - | - |
| 33 | Channel | 203-01STX | - | 26.9 | 3776.0 | 30446.0 | - | - |
Top 5 by Ton/Acre: 213-99SSP (Channel) 35.5, B99A24V (Brevant) 33.9, Seed (Renk) 33.8, B05D47V (Brevant) 33.1, 201-07SSP (Channel) 33.0.