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>
2.7 KiB
2.7 KiB
Soybean yield trial — Illinois, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Illinois (IL)
- Year: 2024
- Plot ID: 2435270
- Cooperator: Gateway Fs Inc-Woodlawn
- Planted: 2024-06-10
- Harvested: 2024-10-21
- Population: 150,000 seeds/acre
- Row width: 15"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/il/2024/2435270
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Asgrow | AG48XF5 | - | 77.8 | 9.5 | - | $816.90 |
| 2 | Asgrow | AG43XF5 | - | 77.5 | 10.0 | - | $813.75 |
| 3 | Asgrow | AG36XF4 | - | 77.4 | 11.0 | - | $812.70 |
| 4 | NK | NK37-R5XF | XtendFlex ® | 75.7 | 10.0 | - | $794.85 |
| 5 | Asgrow | AG39XF3 | - | 75.4 | 10.4 | - | $791.70 |
| 6 | Xitavo | XO | 4255E | 74.9 | 9.0 | - | $786.45 |
| 7 | NK | NK39-M8XF | XtendFlex ® | 74.5 | 10.3 | - | $782.25 |
| 8 | Asgrow | AG37XF5 | - | 74.4 | 10.7 | - | $781.20 |
| 9 | Asgrow | AG40XF1 | - | 74.1 | 10.3 | - | $778.05 |
| 10 | Asgrow | AG47XF5 | - | 73.8 | 9.7 | - | $774.90 |
| 11 | Asgrow | AG33XF3 | - | 73.2 | 10.1 | - | $768.60 |
| 11 | NK | NK44-J4XFS | XtendFlex ® STS ® | 73.2 | 9.5 | - | $768.60 |
| 13 | Asgrow | AG44XF4 | - | 72.9 | 9.5 | - | $765.45 |
| 13 | Pioneer | P40A23E | - | 72.9 | 9.7 | - | $765.45 |
| 13 | Xitavo | XO | 4405E | 72.9 | 8.9 | - | $765.45 |
| 16 | Xitavo | XO | 4894E | 72.7 | 9.2 | - | $763.35 |
| 17 | NK | NK48-A8XFS | XtendFlex ® STS ® | 72.6 | 9.3 | - | $762.30 |
| 18 | NK | NK40-P5E3 | Enlist E3 ® | 72.3 | 10.5 | - | $759.15 |
| 19 | NK | NK42-T5XF | XtendFlex ® | 71.5 | 9.4 | - | $750.75 |
| 20 | Xitavo | XO | 4522E | 71.2 | 9.7 | - | $747.60 |
| 20 | Xitavo | XO | 4772E | 71.2 | 9.3 | - | $747.60 |
| 22 | NK | NK39-J2E3 | Enlist E3 ® | 70.7 | 10.2 | - | $742.35 |
| 23 | NK | NK46-B4XFS | XtendFlex ® STS ® | 70.4 | 9.1 | - | $739.20 |
| 24 | NK | NK44-Q5E3S | Enlist E3 ® STS ® | 70.1 | 9.5 | - | $736.05 |
| 25 | NK | NK42-A6E3S | Enlist E3 ® STS ® | 69.8 | 9.7 | - | $732.90 |
| 26 | NK | NK43-W1XFS | XtendFlex ® STS ® | 67.3 | 9.8 | - | $706.65 |
| 27 | Xitavo | XO | 3105E | 65.1 | 9.6 | - | $683.55 |
| 28 | NK | NK49-U9E3S | Enlist E3 ® STS ® | 64.5 | 9.4 | - | $677.25 |
| 29 | Xitavo | XO | 3375E | 63.5 | 10.3 | - | $666.75 |
| 30 | Xitavo | XO | 4132E | 61.5 | 9.7 | - | $645.75 |
| 31 | Xitavo | XO | 3922E | 55.8 | 10.1 | - | $585.90 |
| 32 | Xitavo | XO | 3752E | 52.7 | 10.1 | - | $553.35 |
| 33 | Xitavo | XO | 3655E | 50.9 | 10.7 | - | $534.45 |
| 34 | Xitavo | XO | 3855E | 50.7 | 9.9 | - | $532.35 |
Top 5 by Yield: AG48XF5 (Asgrow) 77.8, AG43XF5 (Asgrow) 77.5, AG36XF4 (Asgrow) 77.4, NK37-R5XF (NK) 75.7, AG39XF3 (Asgrow) 75.4.