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 — Kentucky, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Kentucky (KY)
- Year: 2024
- Plot ID: 2446663
- Cooperator: University of Kentucky - Caldwell Cnty Medium
- Planted: 2024-04-27
- Harvested: 2024-09-18
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ky/2024/2446663
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Connect | CT4025E | - | 62.4 | - | - | $655.20 |
| 2 | Innvictis | Seed | Solutions B4553E | 59.8 | - | - | $627.90 |
| 2 | NuTech | Seed | 45N10E | 59.8 | - | - | $627.90 |
| 4 | Fortus | 4125ES | - | 58.4 | - | - | $613.20 |
| 5 | NuTech | Seed | 42N05E | 57.7 | - | - | $605.85 |
| 6 | Armor | Seed | Armor 45-F65 | 57.2 | - | - | $600.60 |
| 7 | NuTech | Seed | 43N06E | 56.5 | - | - | $593.25 |
| 8 | Innvictis | Seed | Solutions A4503XF | 55.4 | - | - | $581.70 |
| 9 | Pioneer | P42A84E | - | 54.8 | - | - | $575.40 |
| 10 | UniSouth | Genetics | USG 7435XFS | 54.6 | - | - | $573.30 |
| 11 | Asgrow | AG40XF5 | - | 54.5 | - | - | $572.25 |
| 12 | Stine | 42EG23 | - | 54.3 | - | - | $570.15 |
| 13 | Armor | Seed | Armor 41-F65S | 53.6 | - | - | $562.80 |
| 14 | Pioneer | P45A81E | - | 53.2 | - | - | $558.60 |
| 15 | Golden Harvest | GH4093E3 | Enlist E3 ® | 52.8 | - | - | $554.40 |
| 16 | Partners | Brand | Seed 4424 E3 S | 52.3 | - | - | $549.15 |
| 17 | Stine | 41EG20 | - | 52.2 | - | - | $548.10 |
| 18 | Pioneer | P45Z75E | - | 51.9 | - | - | $544.95 |
| 19 | Revere | Seed | Revere 44-F44 XFS | 51.6 | - | - | $541.80 |
| 20 | NuTech | Seed | 43N11BE | 50.7 | - | - | $532.35 |
| 21 | Channel | 4125XF/SR | - | 49.9 | - | - | $523.95 |
| 21 | Stine | 45EH29 | - | 49.9 | - | - | $523.95 |
| 23 | Golden Harvest | GH4345XFS | XtendFlex ® STS ® | 49.7 | - | - | $521.85 |
| 24 | Innvictis | Seed | Solutions A4102XF | 49.5 | - | - | $519.75 |
| 25 | Xitavo | XO | 4364E | 49.3 | - | - | $517.65 |
| 25 | Xitavo | XO | 4255E | 49.3 | - | - | $517.65 |
| 27 | APEX | AE4342S | - | 48.8 | - | - | $512.40 |
| 28 | Channel | 4525RXF/SR | - | 48.4 | - | - | $508.20 |
| 28 | Asgrow | AG44XF4 | - | 48.4 | - | - | $508.20 |
| 30 | Stine | 43EG29 | - | 48.2 | - | - | $506.10 |
| 31 | Asgrow | AG42XF4 | - | 48.1 | - | - | $505.05 |
| 31 | Xitavo | XO | 4405E | 48.1 | - | - | $505.05 |
| 33 | Connect | CT4525E | - | 47.5 | - | - | $498.75 |
| 34 | Fortus | 4335E | - | 47.3 | - | - | $496.65 |
| 35 | Golden Harvest | GH4433E3S | Enlist E3 ® STS ® | 45.2 | - | - | $474.60 |
| 36 | Asgrow | AG43XF5 | - | 44.9 | - | - | $471.45 |
| 37 | Stine | 44EH23 | - | 44.7 | - | - | $469.35 |
| 38 | Golden Harvest | GH4214E3S | Enlist E3 ® STS ® | 42.9 | - | - | $450.45 |
| 39 | Catalyst | CT4413E3S | Enlist E3 ® STS ® | 40.5 | - | - | $425.25 |
| 39 | Asgrow | AG45XF3 | - | 40.5 | - | - | $425.25 |
Top 5 by Yield: CT4025E (Connect) 62.4, Seed (Innvictis) 59.8, Seed (NuTech) 59.8, 4125ES (Fortus) 58.4, Seed (NuTech) 57.7.