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>
2.6 KiB
2.6 KiB
Soybean yield trial — Minnesota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Minnesota (MN)
- Year: 2024
- Plot ID: 2426476
- Cooperator: Nathan Hagen
- Planted: 2024-05-15
- Harvested: 2024-09-26
- Population: 141,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mn/2024/2426476
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | NK | NK11-U2XF | XtendFlex ® | 54.5 | 10.0 | - | $572.25 |
| 2 | Allegiant | Experimental | - | 54.1 | 10.8 | - | $568.05 |
| 3 | NK | NK05-W3XF | XtendFlex ® | 51.6 | 10.2 | - | $541.80 |
| 3 | NK | NK08-Z4E3 | Enlist E3 ® | 51.6 | 10.2 | - | $541.80 |
| 3 | Dahlman | 7512XF | - | 51.6 | 10.3 | - | $541.80 |
| 6 | NK | NK08-R3XF | XtendFlex ® | 51.3 | 10.7 | - | $538.65 |
| 7 | NK | NK07-G5E3 | Enlist E3 ® | 51.2 | 9.8 | - | $537.60 |
| 7 | NK | NK11-A4E3 | Enlist E3 ® | 51.2 | 11.0 | - | $537.60 |
| 9 | Pioneer | P06Z90E | - | 50.1 | 10.5 | - | $526.05 |
| 10 | Genesis | G0880E | - | 49.7 | 9.9 | - | $521.85 |
| 11 | NK | NK06-C4XF | XtendFlex ® | 49.5 | 10.2 | - | $519.75 |
| 12 | Genesis | G1260E | - | 49.1 | 12.3 | - | $515.55 |
| 13 | Dahlman | 7508XF | - | 48.9 | 10.1 | - | $513.45 |
| 14 | Genesis | G0570E | - | 48.8 | 10.2 | - | $512.40 |
| 15 | Allegiant | Allegiant | 09F82N | 48.6 | 10.6 | - | $510.30 |
| 16 | APEX | AE0710 | - | 48.2 | 10.1 | - | $506.10 |
| 17 | Pioneer | P05Z60E | - | 48.1 | 10.2 | - | $505.05 |
| 17 | Attain | Attain | 06A5N | 48.1 | 10.2 | - | $505.05 |
| 19 | Allegiant | Allegiant | 04F85N XF | 48.0 | 10.5 | - | $504.00 |
| 20 | NK | NK09-B5XF | XtendFlex ® | 47.5 | 10.1 | - | $498.75 |
| 21 | NK | NK06-A1E3 | Enlist E3 ® | 46.7 | 10.3 | - | $490.35 |
| 22 | Attain | Attain | 09A5N | 46.6 | 10.4 | - | $489.30 |
| 23 | Genesis | G0750E | - | 45.4 | 10.1 | - | $476.70 |
| 23 | Dahlman | AE1350 | - | 45.4 | 11.4 | - | $476.70 |
| 25 | Allegiant | Allegiant | 07F5 XF | 44.6 | 10.2 | - | $468.30 |
| 26 | Renk | Seed | G0380E | 44.5 | 10.5 | - | $467.25 |
| 27 | NK | NK09-H7E3 | Enlist E3 ® | 43.7 | 10.8 | - | $458.85 |
| 28 | Genesis | G0180E | - | 43.3 | 10.2 | - | $454.65 |
| 29 | Genesis | G1070E | - | 42.6 | 10.2 | - | $447.30 |
| 29 | Attain | Attain | 11A3N | 42.6 | 10.2 | - | $447.30 |
| 31 | Attain | Attain | 03A5N | 36.7 | 10.8 | - | $385.35 |
Top 5 by Yield: NK11-U2XF (NK) 54.5, Experimental (Allegiant) 54.1, NK05-W3XF (NK) 51.6, NK08-Z4E3 (NK) 51.6, 7512XF (Dahlman) 51.6.