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>
2.2 KiB
2.2 KiB
Soybean yield trial — Nebraska, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Nebraska (NE)
- Year: 2024
- Plot ID: 2419665
- Cooperator: Mark Knobel
- Planted: 2024-05-01
- Harvested: 2024-10-18
- Population: 140,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ne/2024/2419665
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Golden Harvest | GH2884XF | XtendFlex ® | 93.0 | 7.8 | 56.1 | $976.50 |
| 2 | Golden Harvest | GH2925XF | XtendFlex ® | 91.2 | 7.5 | 55.8 | $957.60 |
| 3 | Golden Harvest | GH3043E3 | Enlist E3 ® | 90.5 | 7.5 | 57.9 | $950.25 |
| 4 | Golden Harvest | GH2922E3 | Enlist E3 ® | 88.0 | 7.9 | 56.6 | $924.00 |
| 4 | Golden Harvest | GH3445XF | XtendFlex ® | 88.0 | 7.9 | 54.3 | $924.00 |
| 6 | Golden Harvest | GH3913XF | XtendFlex ® | 86.1 | 7.6 | 56.8 | $904.05 |
| 7 | Golden Harvest | GH3582E3 | Enlist E3 ® | 85.9 | 7.9 | 54.5 | $901.95 |
| 8 | Prairie | Valley | PV3022XF | 85.6 | 8.2 | 55.2 | $898.80 |
| 9 | Golden Harvest | GH3023XF | XtendFlex ® | 85.4 | 7.6 | 56.2 | $896.70 |
| 10 | Golden Harvest | GH3225XF | XtendFlex ® | 85.3 | 7.8 | 55.7 | $895.65 |
| 11 | Golden Harvest | GH3765XF | XtendFlex ® | 84.6 | 7.7 | 56.1 | $888.30 |
| 12 | Golden Harvest | GH3774E3 | Enlist E3 ® | 83.8 | 7.8 | 53.7 | $879.40 |
| 13 | Prairie | Valley | PV3223XF | 83.3 | 7.6 | 56.3 | $874.65 |
| 14 | Golden Harvest | GH4093E3 | Enlist E3 ® | 82.7 | 7.5 | 58.4 | $868.35 |
| 15 | Golden Harvest | GH3994E3 | Enlist E3 ® | 82.3 | 7.9 | 56.3 | $864.15 |
| 16 | Golden Harvest | GH3373E3S | Enlist E3 ® STS ® | 81.6 | 7.9 | 54.8 | $856.80 |
| 17 | Golden Harvest | GH3415E3S | Enlist E3 ® STS ® | 79.6 | 7.8 | 56.3 | $835.80 |
| 18 | Golden Harvest | GH3655E3S | Enlist E3 ® STS ® | 78.9 | 7.8 | 56.6 | $828.45 |
| 19 | Golden Harvest | GH3035E3 | Enlist E3 ® | 78.2 | 7.8 | 55.2 | $821.10 |
Top 5 by Yield: GH2884XF (Golden Harvest) 93.0, GH2925XF (Golden Harvest) 91.2, GH3043E3 (Golden Harvest) 90.5, GH2922E3 (Golden Harvest) 88.0, GH3445XF (Golden Harvest) 88.0.