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 — South Dakota, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: South Dakota (SD)
- Year: 2025
- Plot ID: 2467118
- Cooperator: Seed Mill
- Planted: 2025-05-12
- Harvested: 2025-10-02
- Population: 160,000 seeds/acre
- Row width: 20"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/sd/2025/2467118
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Golden Harvest | GH1762XF | XtendFlex ® | 69.2 | 9.4 | 54.5 | $726.60 |
| 2 | Golden Harvest | GH3035E3 | Enlist E3 ® | 68.7 | 10.9 | 55.1 | $721.35 |
| 3 | Golden Harvest | GH2626XF | XtendFlex ® | 68.5 | 9.8 | 54.7 | $719.25 |
| 4 | Golden Harvest | GH2406XF | XtendFlex ® | 67.5 | 9.8 | 54.8 | $708.75 |
| 5 | Golden Harvest | GH3023XF | XtendFlex ® | 66.2 | 12.9 | 51.0 | $691.13 |
| 6 | Golden Harvest | GH2004XF | XtendFlex ® | 65.9 | 9.3 | 54.8 | $691.95 |
| 7 | Golden Harvest | GH2925XF | XtendFlex ® | 65.1 | 10.4 | 54.2 | $683.55 |
| 8 | Pioneer | P21Z71E | - | 64.8 | 9.3 | 54.3 | $680.40 |
| 9 | Golden Harvest | GH2292E3 | Enlist E3 ® | 64.6 | 9.6 | 53.3 | $677.40 |
| 10 | Golden Harvest | GH2674E3 | Enlist E3 ® | 64.5 | 9.8 | 54.7 | $677.25 |
| 11 | Golden Harvest | GH1776E3 | Enlist E3 ® | 63.8 | 9.4 | 53.7 | $669.52 |
| 12 | Golden Harvest | GH2313XF | XtendFlex ® | 63.6 | 9.6 | 54.5 | $667.80 |
| 13 | Golden Harvest | GH1886XF | XtendFlex ® | 63.0 | 9.1 | 54.5 | $661.50 |
| 14 | Golden Harvest | GH1973E3S | Enlist E3 ® STS ® | 62.8 | 9.3 | 54.5 | $659.40 |
| 15 | Asgrow | AG20XF4 | - | 62.7 | 9.3 | 52.2 | $656.09 |
| 16 | Golden Harvest | GH2315E3 | Enlist E3 ® | 61.5 | 9.8 | 54.8 | $645.75 |
| 17 | Golden Harvest | GH2856E3S | Enlist E3 ® STS ® | 61.3 | 10.1 | 53.4 | $642.91 |
Top 5 by Yield: GH1762XF (Golden Harvest) 69.2, GH3035E3 (Golden Harvest) 68.7, GH2626XF (Golden Harvest) 68.5, GH2406XF (Golden Harvest) 67.5, GH3023XF (Golden Harvest) 66.2.