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>
2.3 KiB
2.3 KiB
Soybean yield trial — Ohio, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Ohio (OH)
- Year: 2024
- Plot ID: 2452473
- Cooperator: Southwest Ohio Corn Growers Assoc - Chillicothe Early
- Planted: 2024-05-02
- Harvested: 2024-10-08
- Population: 160,000 seeds/acre
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/oh/2024/2452473
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Axis | Seed | 3514ES | 42.5 | 8.9 | - | $446.25 |
| 2 | NK | NK36-H9E3S | Enlist E3 ® STS ® | 42.0 | 8.2 | - | $441.00 |
| 3 | Seed | Genetics | Direct ET-3735E3 | 41.0 | 9.1 | - | $430.50 |
| 4 | Seed | Genetics | Direct ET-3729E3S | 40.4 | 8.3 | - | $424.20 |
| 5 | Asgrow | AG30XF4 | - | 40.1 | 8.7 | - | $421.05 |
| 6 | Stine | 33EG02 | - | 39.9 | 8.2 | - | $418.95 |
| 7 | Beck's | 3560E3 | - | 39.4 | 8.6 | - | $413.70 |
| 8 | Seed | Genetics | Direct ET-4732E3 Enlist E3 ® | 39.0 | 7.8 | - | $409.50 |
| 9 | Axis | Seed | Experimental | 37.4 | 8.6 | - | $392.70 |
| 9 | Beck's | 3460E3 | - | 37.4 | 8.6 | - | $392.70 |
| 11 | NK | NK33-W2E3S | Enlist E3 ® STS ® | 36.7 | 8.3 | - | $385.35 |
| 12 | Seed | Genetics | Direct ET-0733E3 | 36.5 | 8.5 | - | $383.25 |
| 13 | Seed | Consultants | SC7364E | 36.2 | 7.6 | - | $380.10 |
| 14 | Seed | Genetics | Direct ET-4736E3 Enlist E3 ® | 35.6 | 8.2 | - | $373.80 |
| 15 | Stine | 36EE12 | - | 35.2 | 8.6 | - | $369.60 |
| 15 | Seed | Consultants | SC7315E | 35.2 | 6.8 | - | $369.60 |
| 17 | NK | NK34-Z8E3S | Enlist E3 ® STS ® | 34.8 | 8.7 | - | $365.40 |
| 18 | Seed | Consultants | SC7293E | 33.1 | 7.4 | - | $347.55 |
| 19 | Seed | Consultants | SC7355E | 32.8 | 7.6 | - | $344.40 |
| 20 | Seed | Genetics | Direct ET-4734E3S | 32.6 | 7.8 | - | $342.30 |
| 21 | Asgrow | AG36XF4 | - | 32.2 | 8.0 | - | $338.10 |
| 22 | Axis | Seed | 3605XF | 31.6 | 7.9 | - | $331.80 |
| 23 | Seed | Genetics | Direct ET-3731E3S | 31.5 | 7.6 | - | $330.75 |
| 24 | Beck's | 3650E3 | - | 29.1 | 7.4 | - | $305.55 |
| 25 | Asgrow | AG33XF3 | - | 28.9 | 7.5 | - | $303.45 |
Top 5 by Yield: Seed (Axis) 42.5, NK36-H9E3S (NK) 42.0, Genetics (Seed) 41.0, Genetics (Seed) 40.4, AG30XF4 (Asgrow) 40.1.