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>
2.5 KiB
2.5 KiB
Soybean yield trial — South Dakota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: South Dakota (SD)
- Year: 2024
- Plot ID: 2432360
- Cooperator: Renald Tank
- Planted: 2024-05-09
- Harvested: 2024-10-08
- Population: 140,000 seeds/acre
- Row width: 20"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/sd/2024/2432360
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Golden Harvest | GH1323XF | XtendFlex ® | 69.8 | 7.3 | - | $732.90 |
| 2 | Golden Harvest | GH1124XF | XtendFlex ® | 68.9 | 7.2 | - | $723.45 |
| 3 | Golden Harvest | GH0983XF | XtendFlex ® | 66.9 | 7.4 | - | $702.45 |
| 4 | Golden Harvest | GH1555XF | XtendFlex ® | 65.1 | 7.3 | - | $683.55 |
| 5 | Golden Harvest | GH1194E3 | Enlist E3 ® | 65.0 | 7.4 | - | $682.50 |
| 6 | Golden Harvest | GH0815E3 | Enlist E3 ® | 64.0 | 7.5 | - | $672.00 |
| 7 | Beck's | Experimental | - | 63.7 | 8.0 | - | $668.85 |
| 8 | Golden Harvest | GH0885XF | XtendFlex ® | 63.2 | 7.3 | - | $663.60 |
| 9 | Beck's | 1447XF | - | 63.1 | 7.5 | - | $662.55 |
| 10 | Beck's | 1001XF | - | 62.8 | 7.9 | - | $659.40 |
| 11 | Beck's | 1229XF | - | 62.0 | 7.7 | - | $651.00 |
| 12 | Golden Harvest | GH1762XF | XtendFlex ® | 60.4 | 7.2 | - | $634.20 |
| 13 | Golden Harvest | GH0933E3 | Enlist E3 ® | 60.3 | 7.4 | - | $633.15 |
| 14 | Golden Harvest | GH1614E3 | Enlist E3 ® | 59.4 | 7.3 | - | $623.70 |
| 15 | Golden Harvest | GH1534E3S | Enlist E3 ® STS ® | 58.6 | 7.1 | - | $615.30 |
| 16 | Asgrow | AG11XF4 | - | 58.1 | 7.9 | - | $610.05 |
| 17 | Beck's | 1050E3 | - | 58.0 | 8.1 | - | $609.00 |
| 18 | Beck's | 1250E3 | - | 57.4 | 7.6 | - | $602.70 |
| 18 | Golden Harvest | GH1875E3 | Enlist E3 ® | 57.4 | 7.5 | - | $602.70 |
| 20 | Beck's | 1771XF | - | 56.5 | 7.4 | - | $593.25 |
| 21 | Golden Harvest | GH0734E3 | Enlist E3 ® | 55.6 | 7.4 | - | $583.80 |
| 22 | Golden Harvest | GH1495E3 | Enlist E3 ® | 54.7 | 7.4 | - | $574.35 |
| 23 | Pioneer | P14A12E | - | 50.8 | 7.5 | - | $533.40 |
| 24 | Golden Harvest | GH0675E3 | Enlist E3 ® | 41.4 | 7.6 | - | $434.70 |
| 25 | Golden Harvest | GH0502XF | XtendFlex ® | 41.3 | 7.8 | - | $433.65 |
| 26 | Golden Harvest | GH0655XF | XtendFlex ® | 32.0 | 7.4 | - | $336.00 |
Top 5 by Yield: GH1323XF (Golden Harvest) 69.8, GH1124XF (Golden Harvest) 68.9, GH0983XF (Golden Harvest) 66.9, GH1555XF (Golden Harvest) 65.1, GH1194E3 (Golden Harvest) 65.0.