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>
3.0 KiB
3.0 KiB
Soybean yield trial — Illinois, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Illinois (IL)
- Year: 2024
- Plot ID: 2419041
- Cooperator: Reuben Koehler
- Planted: 2024-04-24
- Harvested: 2024-10-07
- Population: 120,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/il/2024/2419041
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Brevant | B263EE | - | 93.9 | 9.8 | - | $985.95 |
| 1 | Pioneer | P26Z78E | - | 93.9 | 9.6 | - | $985.95 |
| 3 | Pioneer | P28Z89E | - | 93.3 | 10.5 | - | $979.65 |
| 4 | LG Seeds | LGS2881E3 | - | 92.5 | 11.3 | - | $971.25 |
| 5 | Axis | Seed | 2924ES | 91.9 | 9.9 | - | $964.95 |
| 6 | Xitavo | XO | 2735E | 91.7 | 10.9 | - | $962.85 |
| 7 | Beck's | 2550E3 | - | 90.7 | 9.5 | - | $952.35 |
| 8 | Axis | Seed | 2924ES | 90.0 | 9.9 | - | $945.00 |
| 9 | Sun | Prairie | Seeds SP 28E34 | 89.7 | 9.4 | - | $941.85 |
| 10 | Golden Harvest | GH2814E3S | Enlist E3 ® STS ® | 89.5 | 10.0 | - | $939.75 |
| 11 | LG Seeds | LGS2505E3 | - | 89.4 | 10.4 | - | $938.70 |
| 12 | NK | NK26-M6E3 | Enlist E3 ® | 89.2 | 9.9 | - | $936.60 |
| 13 | Sun | Prairie | Seeds SP 29E35 | 88.8 | 9.1 | - | $932.40 |
| 13 | LG Seeds | LGS3000E3 | - | 88.8 | 9.1 | - | $932.40 |
| 15 | Pioneer | P31Z03E | - | 88.4 | 9.3 | - | $928.20 |
| 16 | Pioneer | P28Z30E | - | 87.4 | 10.0 | - | $917.70 |
| 17 | Axis | Seed | 2704E | 87.3 | 10.3 | - | $916.65 |
| 18 | Beck's | 3300E3 | - | 86.9 | 9.6 | - | $912.45 |
| 19 | Axis | Seed | 3314E | 86.7 | 9.4 | - | $910.35 |
| 20 | Golden Harvest | GH2775E3 | Enlist E3 ® | 86.5 | 10.8 | - | $908.25 |
| 21 | Xitavo | XO | 2865E | 86.1 | 10.9 | - | $904.05 |
| 22 | Axis | Seed | 2924ES | 85.9 | 8.6 | - | $901.95 |
| 23 | APEX | AE3131S | - | 85.8 | 10.0 | - | $900.90 |
| 23 | LG Seeds | LGS3216E3 | - | 85.8 | 8.9 | - | $900.90 |
| 25 | Beck's | 3140E3 | - | 85.4 | 8.1 | - | $896.70 |
| 26 | Axis | Seed | 2824E | 85.0 | 9.2 | - | $892.50 |
| 27 | APEX | AE2940S | - | 84.9 | 8.8 | - | $891.45 |
| 28 | Sun | Prairie | Seeds SP 30E35 | 84.8 | 8.9 | - | $890.40 |
| 29 | APEX | AE3330S | - | 84.2 | 9.2 | - | $884.10 |
| 30 | LG Seeds | LGS3445E3 | - | 84.0 | 8.9 | - | $882.00 |
| 31 | Axis | Seed | 2924ES | 83.2 | 13.6 | - | $873.60 |
| 32 | Axis | Seed | 2924ES | 82.9 | 9.8 | - | $870.45 |
| 33 | Sun | Prairie | Seeds SP 31E33 Enlist | 82.3 | 8.3 | - | $864.15 |
| 34 | Golden Harvest | GH2922E3 | Enlist E3 ® | 82.0 | 11.1 | - | $861.00 |
| 35 | Axis | Seed | 2924ES | 81.2 | 9.2 | - | $852.60 |
| 36 | NK | NK30-A9E3 | Enlist E3 ® | 80.5 | 8.6 | - | $845.25 |
| 37 | Xitavo | XO | 2625E | 78.2 | 10.7 | - | $821.10 |
| 37 | Golden Harvest | GH3035E3 | Enlist E3 ® | 78.2 | 8.4 | - | $821.10 |
Top 5 by Yield: B263EE (Brevant) 93.9, P26Z78E (Pioneer) 93.9, P28Z89E (Pioneer) 93.3, LGS2881E3 (LG Seeds) 92.5, Seed (Axis) 91.9.