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 — Illinois, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Illinois (IL)
- Year: 2024
- Plot ID: 2419118
- Cooperator: Eugene Chiavario
- Planted: 2024-05-23
- Harvested: 2024-10-09
- Population: 140,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/il/2024/2419118
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Brevant | B243EE | - | 85.1 | 8.0 | - | $893.55 |
| 2 | Brevant | B294EE | - | 83.1 | 8.8 | - | $872.55 |
| 3 | Brevant | B202EE | - | 80.7 | 8.7 | - | $847.35 |
| 4 | Alloy | A27E35 | - | 79.4 | 8.2 | - | $833.70 |
| 5 | NK | NK29-Q3XF | XtendFlex ® | 78.1 | 8.4 | - | $820.05 |
| 6 | Brevant | B214EE | - | 76.9 | 8.2 | - | $807.45 |
| 7 | Xitavo | XO | 2832E | 76.8 | 8.0 | - | $806.40 |
| 8 | Asgrow | AG26XF4 | - | 76.5 | 8.1 | - | $803.25 |
| 9 | Asgrow | AG22XF5 | - | 75.5 | 8.2 | - | $792.75 |
| 10 | Asgrow | AG27XF3 | - | 74.7 | 8.3 | - | $784.35 |
| 11 | Alloy | A24E34 | - | 74.6 | 8.1 | - | $783.30 |
| 12 | NK | NK25-C9XF | XtendFlex ® | 74.5 | 7.8 | - | $782.25 |
| 13 | Asgrow | AG33XF3 | - | 74.4 | 9.1 | - | $781.20 |
| 14 | Asgrow | AG30XF4 | - | 73.9 | 8.3 | - | $775.95 |
| 14 | Xitavo | XO | 2444E | 73.9 | 7.9 | - | $775.95 |
| 16 | Asgrow | AG29XF5 | - | 73.0 | 8.0 | - | $766.50 |
| 16 | Alloy | A26E33 | - | 73.0 | 8.2 | - | $766.50 |
| 18 | NK | NK26-M6E3 | Enlist E3 ® | 72.8 | 7.8 | - | $764.40 |
| 19 | Brevant | B252EE | - | 72.6 | 8.1 | - | $762.30 |
| 20 | Asgrow | AG25XF5 | - | 72.4 | 8.4 | - | $760.20 |
| 21 | Asgrow | AG21XF2 | - | 72.3 | 8.3 | - | $759.15 |
| 22 | NK | NK27-W8XF | XtendFlex ® | 72.1 | 7.7 | - | $757.05 |
| 23 | Alloy | A29E35 | - | 71.8 | 7.9 | - | $753.90 |
| 24 | Asgrow | AG24XF4 | - | 71.6 | 8.1 | - | $751.80 |
| 25 | Xitavo | XO | 3224E | 71.0 | 8.7 | - | $745.50 |
| 26 | Xitavo | XO | 3375E | 70.7 | 9.0 | - | $742.35 |
| 27 | Alloy | A30E35 | - | 70.2 | 8.4 | - | $737.10 |
| 28 | Alloy | A23E33 | - | 69.6 | 8.2 | - | $730.80 |
| 29 | NK | NK21-C2E3 | Enlist E3 ® | 68.8 | 8.1 | - | $722.40 |
| 30 | Xitavo | XO | 2865E | 67.6 | 8.0 | - | $709.80 |
| 31 | Xitavo | XO | 3105E | 67.5 | 8.3 | - | $708.75 |
| 32 | Alloy | A21E34 | - | 65.7 | 8.4 | - | $689.85 |
| 33 | NK | NK27-J5E3 | Enlist E3 ® | 64.9 | 8.1 | - | $681.45 |
| 34 | Alloy | A28E34 | - | 64.5 | 8.6 | - | $677.25 |
Top 5 by Yield: B243EE (Brevant) 85.1, B294EE (Brevant) 83.1, B202EE (Brevant) 80.7, A27E35 (Alloy) 79.4, NK29-Q3XF (NK) 78.1.