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 — Wisconsin, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Wisconsin (WI)
- Year: 2024
- Plot ID: 2440899
- Cooperator: University of Wisconsin - Spooner (Dryland)
- Planted: 2024-05-29
- Harvested: 2024-10-08
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/wi/2024/2440899
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Genesis | G1260E | - | 48.0 | - | - | $504.00 |
| 1 | Golden Harvest | GH0815E3 | Enlist E3 ® | 48.0 | - | - | $504.00 |
| 1 | Stine | 11EC02 | - | 48.0 | - | - | $504.00 |
| 4 | Legacy | Seeds | LS094-24 XF | 47.0 | - | - | $493.50 |
| 4 | NK | NK08-Z4E3 | Enlist E3 ® | 47.0 | - | - | $493.50 |
| 6 | Loyal | Brand | L0870E | 46.0 | - | - | $483.00 |
| 6 | Loyal | Brand | L1070E | 46.0 | - | - | $483.00 |
| 6 | Stine | 13EG23 | - | 46.0 | - | - | $483.00 |
| 9 | Genesis | G0750E | - | 45.0 | - | - | $472.50 |
| 10 | NK | NK11-A4E3 | Enlist E3 ® | 44.0 | - | - | $462.00 |
| 10 | Stine | 08EG62 | - | 44.0 | - | - | $462.00 |
| 12 | Asgrow | AG10XF4 | - | 43.0 | - | - | $451.50 |
| 12 | Asgrow | AG12XF4 | - | 43.0 | - | - | $451.50 |
| 12 | Genesis | G1290E | - | 43.0 | - | - | $451.50 |
| 12 | Golden Harvest | GH0734E3 | Enlist E3 ® | 43.0 | - | - | $451.50 |
| 12 | Legacy | Seeds | LS112-24 E | 43.0 | - | - | $451.50 |
| 12 | Loyal | Brand | L1270E | 43.0 | - | - | $451.50 |
| 12 | Xitavo | XO | 0602E | 43.0 | - | - | $451.50 |
| 19 | APEX | AE0720 | - | 42.0 | - | - | $441.00 |
| 19 | Golden Harvest | GH1194E3 | Enlist E3 ® | 42.0 | - | - | $441.00 |
| 19 | Xitavo | XO | 1095E | 42.0 | - | - | $441.00 |
| 22 | Asgrow | AG14XF4 | - | 41.0 | - | - | $430.50 |
| 22 | Legacy | Seeds | LS124-23XF | 41.0 | - | - | $430.50 |
| 22 | Loyal | Brand | L1160E | 41.0 | - | - | $430.50 |
| 25 | APEX | AE0930 | - | 40.0 | - | - | $420.00 |
| 25 | NK | NK07-G5E3 | Enlist E3 ® | 40.0 | - | - | $420.00 |
| 25 | Xitavo | XO | 0554E | 40.0 | - | - | $420.00 |
| 25 | Xitavo | XO | 0993E | 40.0 | - | - | $420.00 |
| 25 | Xitavo | XO | 1225E | 40.0 | - | - | $420.00 |
| 30 | NK | NK06-A1E3 | Enlist E3 ® | 39.0 | - | - | $409.50 |
| 31 | APEX | AE1140 | - | 38.0 | - | - | $399.00 |
| 31 | Genesis | G0880E | - | 38.0 | - | - | $399.00 |
| 31 | Stine | 10EG20 | - | 38.0 | - | - | $399.00 |
| 34 | BioGene | Seeds | BG9124E3 | 37.0 | - | - | $388.50 |
Top 5 by Yield: G1260E (Genesis) 48.0, GH0815E3 (Golden Harvest) 48.0, 11EC02 (Stine) 48.0, Seeds (Legacy) 47.0, NK08-Z4E3 (NK) 47.0.