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>
2.0 KiB
2.0 KiB
Soybean yield trial — Maryland, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Maryland (MD)
- Year: 2024
- Plot ID: 2426818
- Cooperator: University of Maryland - Wye Research & Education Center MG 4 (Early)
- Planted: 2024-05-31
- Harvested: 2024-10-25
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/md/2024/2426818
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Catalyst | CT4413E3S | Enlist E3 ® STS ® | 89.6 | - | 56.0 | $940.80 |
| 2 | Xitavo | XO | 4405E | 86.5 | - | 54.7 | $908.25 |
| 3 | Revere | Seed | Revere 44-F44 XFS | 82.7 | - | 56.8 | $868.35 |
| 4 | UniSouth | Genetics | USG 7415ET | 82.5 | - | 56.5 | $866.25 |
| 5 | NK | NK43-W1XFS | XtendFlex ® STS ® | 81.1 | - | 55.3 | $851.55 |
| 5 | UniSouth | Genetics | USG 7435ET | 81.1 | - | 54.4 | $851.55 |
| 7 | Mid-Atlantic | Seeds | MAS4423E3 | 79.2 | - | 53.8 | $831.28 |
| 8 | Mid-Atlantic | Seeds | MAS4045E3 | 78.5 | - | 55.6 | $824.25 |
| 9 | Mid-Atlantic | Seeds | MAS4021E3 | 77.0 | - | 52.7 | $806.50 |
| 10 | Xitavo | XO | 4255E | 76.1 | - | 53.8 | $798.75 |
| 11 | UniSouth | Genetics | USG 7434XF | 75.3 | - | 57.4 | $790.65 |
| 12 | Pioneer | P42A84E | - | 75.0 | - | 54.0 | $787.50 |
| 13 | APEX | AE4341S | - | 74.1 | - | 54.8 | $778.05 |
| 14 | Southern | Harvest | SH4024 E3 | 73.7 | - | 53.2 | $772.67 |
| 15 | Xitavo | XO | 4132E | 73.6 | - | 55.5 | $772.80 |
| 16 | NK | NK42-A6E3S | Enlist E3 ® STS ® | 73.5 | - | 55.4 | $771.75 |
| 17 | Mid-Atlantic | Seeds | MAS4320E3/STS | 73.2 | - | 53.7 | $768.16 |
| 18 | UniSouth | Genetics | USG 7435XFS | 72.8 | - | 53.6 | $763.82 |
| 19 | Mid-Atlantic | Seeds | MAS4215E3 | 71.6 | - | 54.6 | $751.80 |
| 20 | Xitavo | XO | 4364E | 68.2 | - | 56.7 | $716.10 |
Top 5 by Yield: CT4413E3S (Catalyst) 89.6, XO (Xitavo) 86.5, Seed (Revere) 82.7, Genetics (UniSouth) 82.5, NK43-W1XFS (NK) 81.1.