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>
2.5 KiB
2.5 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: 2420169
- Cooperator: Ohio State University - Clinton County (Early)
- Planted: 2024-05-20
- Harvested: 2024-10-08
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/oh/2024/2420169
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Ebberts | G3690E | - | 86.5 | - | - | $908.25 |
| 2 | Seed | Genetics | Direct ET-4736E3 Enlist E3 ® | 85.4 | - | - | $896.70 |
| 3 | Axis | Seed | 3314E | 83.6 | - | - | $877.80 |
| 4 | DonMario | Seeds | DM36E94 | 83.5 | - | - | $876.75 |
| 5 | Xitavo | XO | 3555E | 82.2 | - | - | $863.10 |
| 6 | Xitavo | XO | 3014E | 81.3 | - | - | $853.65 |
| 7 | Asgrow | AG33XF3 | - | 80.7 | - | - | $847.35 |
| 8 | Ebberts | G3171ES | - | 80.3 | - | - | $843.15 |
| 9 | Ebberts | G3380E | - | 79.7 | - | - | $836.85 |
| 10 | Seed | Consultants | SC7355E | 78.9 | - | - | $828.45 |
| 11 | Asgrow | AG30XF4 | - | 78.7 | - | - | $826.35 |
| 12 | Axis | Seed | 3514ES | 78.6 | - | - | $825.30 |
| 13 | Asgrow | AG27XF3 | - | 77.9 | - | - | $817.95 |
| 14 | Ebberts | G3580ES | - | 77.8 | - | - | $816.90 |
| 15 | Xitavo | XO | 3224E | 77.5 | - | - | $813.75 |
| 16 | Xitavo | XO | 3655E | 77.2 | - | - | $810.60 |
| 17 | Benson | Hill | BH35A231 | 77.0 | - | - | $808.50 |
| 18 | Seed | Genetics | Direct ET-4732E3 Enlist E3 ® | 76.0 | - | - | $798.00 |
| 19 | Seed | Consultants | SC7364E | 75.8 | - | - | $795.90 |
| 20 | Asgrow | AG36XF4 | - | 75.2 | - | - | $789.60 |
| 21 | Seed | Genetics | Direct ET-3735E3 | 74.9 | - | - | $786.45 |
| 22 | Seed | Genetics | Direct ET-3733E3S | 74.7 | - | - | $784.35 |
| 23 | Seed | Consultants | SC7332E | 74.4 | - | - | $781.20 |
| 24 | Seed | Genetics | Direct ET-0733E3 | 74.1 | - | - | $778.05 |
| 25 | Xitavo | XO | 3375E | 74.0 | - | - | $777.00 |
| 26 | Benson | Hill | BH35A233 | 73.8 | - | - | $774.90 |
| 27 | Xitavo | XO | 3105E | 73.7 | - | - | $773.85 |
| 28 | Benson | Hill | N35D950S | 72.6 | - | - | $762.30 |
| 29 | Axis | Seed | 3605XF | 72.3 | - | - | $759.15 |
| 30 | NK | NK36-Q6E3S | Enlist E3 ® STS ® | 71.0 | - | - | $745.50 |
| 31 | Benson | Hill | BX36Q861 | 65.2 | - | - | $684.60 |
| 32 | Seed | Genetics | Direct ET-4734E3S | 64.5 | - | - | $677.25 |
Top 5 by Yield: G3690E (Ebberts) 86.5, Genetics (Seed) 85.4, Seed (Axis) 83.6, Seeds (DonMario) 83.5, XO (Xitavo) 82.2.