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 — Nebraska, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Nebraska (NE)
- Year: 2024
- Plot ID: 2465840
- Cooperator: Servi-Tech Soybean Plot
- Planted: 2024-05-16
- Harvested: 2024-10-11
- Population: 172,000 seeds/acre
- Row width: 36"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ne/2024/2465840
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Hoegemeyer | 2855 | E | 93.7 | 9.2 | - | $983.85 |
| 2 | Pioneer | P31Z03E | - | 93.2 | 9.0 | - | $978.60 |
| 3 | Pioneer | P28A65E | - | 92.6 | 8.4 | - | $972.30 |
| 4 | Stine | 30EG32 | - | 92.4 | 9.0 | - | $970.20 |
| 5 | Channel | 3025RXF | - | 91.9 | 9.0 | - | $964.95 |
| 6 | Pioneer | P28A65E | - | 91.7 | 9.7 | - | $962.85 |
| 7 | Golden Harvest | GH3035E3 | Enlist E3 ® | 91.6 | 8.8 | - | $961.80 |
| 8 | Beck's | 3140E3 | - | 91.5 | 8.8 | - | $960.75 |
| 9 | Pioneer | P33Z17E | - | 91.3 | 8.9 | - | $958.65 |
| 10 | Golden Harvest | GH3043E3 | Enlist E3 ® | 91.1 | 8.7 | - | $956.55 |
| 11 | Pioneer | P28A65E | - | 90.4 | 9.0 | - | $949.20 |
| 12 | Beck's | 2997XF | - | 90.3 | 8.9 | - | $948.15 |
| 12 | Hoegemeyer | 3185 | E | 90.3 | 9.4 | - | $948.15 |
| 14 | Stine | 27EG22 | - | 89.8 | 8.7 | - | $942.90 |
| 15 | Connect | CT3324E | - | 88.5 | 9.0 | - | $929.25 |
| 16 | Beck's | 3441XF | - | 88.4 | 9.9 | - | $928.20 |
| 17 | Stine | 33EG02 | - | 88.3 | 9.7 | - | $927.15 |
| 18 | Pioneer | P28A65E | - | 86.8 | 9.6 | - | $911.40 |
| 19 | Golden Harvest | GH2925XF | XtendFlex ® | 86.7 | 9.5 | - | $910.35 |
| 20 | Pioneer | P28A65E | - | 86.6 | 8.6 | - | $909.30 |
| 21 | Channel | 3322RXF | - | 86.4 | 9.9 | - | $907.20 |
| 22 | Xitavo | XO | 3014E | 85.6 | 8.9 | - | $898.80 |
| 23 | Channel | 2725RXF | - | 85.5 | 8.9 | - | $897.75 |
| 24 | Channel | 2824RXF | - | 85.3 | 9.5 | - | $895.65 |
| 24 | Pioneer | P30A75E | - | 85.3 | 8.8 | - | $895.65 |
| 24 | Connect | CT2824E | - | 85.3 | 8.7 | - | $895.65 |
| 27 | Golden Harvest | GH3023XF | XtendFlex ® | 84.9 | 9.4 | - | $891.45 |
| 28 | Pioneer | P27Z41E | - | 84.2 | 9.0 | - | $884.10 |
| 29 | Hoegemeyer | 2763 | E | 84.1 | 8.7 | - | $883.05 |
| 29 | Hoegemeyer | 2645 | E | 84.1 | 8.5 | - | $883.05 |
| 31 | Xitavo | XO | 2832E | 80.5 | 9.1 | - | $845.25 |
| 32 | Beck's | 2830E3 | - | 79.9 | 9.0 | - | $838.95 |
| 33 | Stine | 25EG20 | - | 78.1 | 8.7 | - | $820.05 |
Top 5 by Yield: 2855 (Hoegemeyer) 93.7, P31Z03E (Pioneer) 93.2, P28A65E (Pioneer) 92.6, 30EG32 (Stine) 92.4, 3025RXF (Channel) 91.9.