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>
2.4 KiB
2.4 KiB
Soybean yield trial — Indiana, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Indiana (IN)
- Year: 2024
- Plot ID: 2420200
- Cooperator: Garth Jenkins
- Planted: 2024-05-13
- Harvested: 2024-10-10
- Population: 132,500 seeds/acre
- Row width: 15"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/in/2024/2420200
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Asgrow | AG24XF4 | - | 47.4 | 11.4 | - | $497.70 |
| 1 | Asgrow | AG26XF4 | - | 47.4 | 11.7 | - | $497.70 |
| 3 | Brevant | B324EE | - | 44.1 | 11.6 | - | $463.05 |
| 4 | Asgrow | AG30XF4 | - | 43.4 | 10.5 | - | $455.70 |
| 5 | NK | NK30-A9E3 | Enlist E3 ® | 42.9 | 11.2 | - | $450.45 |
| 6 | NK | NK21-C2E3 | Enlist E3 ® | 42.5 | 11.9 | - | $446.25 |
| 7 | Asgrow | AG29XF4 | - | 42.4 | 11.6 | - | $445.20 |
| 8 | NK | NK33-Y7E3S | Enlist E3 ® STS ® | 41.9 | 11.4 | - | $439.95 |
| 9 | Asgrow | AG27XF3 | - | 41.6 | 11.2 | - | $436.80 |
| 10 | Brevant | B224EE | - | 41.4 | 12.0 | - | $434.70 |
| 11 | Brevant | B272EE | - | 41.2 | 11.6 | - | $432.60 |
| 12 | Xitavo | XO | 3224E | 41.1 | 11.3 | - | $431.55 |
| 12 | Brevant | B342EE | - | 41.1 | 11.0 | - | $431.55 |
| 14 | Xitavo | XO | 2865E | 40.5 | 11.5 | - | $425.25 |
| 15 | Brevant | B294EE | - | 40.4 | 11.2 | - | $424.20 |
| 16 | Asgrow | AG28XF3 | - | 40.3 | 10.5 | - | $423.15 |
| 16 | Brevant | B344EE | - | 40.3 | 10.6 | - | $423.15 |
| 18 | NK | NK26-M6E3 | Enlist E3 ® | 39.8 | 11.6 | - | $417.90 |
| 19 | Brevant | B284EE | - | 38.0 | 11.7 | - | $399.00 |
| 20 | Asgrow | AG33XF3 | - | 37.3 | 10.6 | - | $391.65 |
| 21 | Xitavo | XO | 2625E | 37.0 | 11.8 | - | $388.50 |
| 22 | Xitavo | XO | 2985E | 36.9 | 10.8 | - | $387.45 |
| 23 | Brevant | B243EE | - | 36.7 | 11.5 | - | $385.35 |
| 24 | NK | NK23-P1E3 | Enlist E3 ® | 36.4 | 12.7 | - | $382.20 |
| 25 | NK | NK27-J5E3 | Enlist E3 ® | 36.2 | 11.8 | - | $380.10 |
| 26 | Xitavo | XO | 3014E | 34.5 | 12.0 | - | $362.25 |
| 27 | NK | NK34-Z8E3S | Enlist E3 ® STS ® | 34.4 | 11.2 | - | $361.20 |
| 28 | Asgrow | AG36XF4 | - | 33.4 | 10.7 | - | $350.70 |
| 29 | Xitavo | XO | 3015E | 32.2 | 11.5 | - | $338.10 |
Top 5 by Yield: AG24XF4 (Asgrow) 47.4, AG26XF4 (Asgrow) 47.4, B324EE (Brevant) 44.1, AG30XF4 (Asgrow) 43.4, NK30-A9E3 (NK) 42.9.