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: 2446660
- Cooperator: University of Kentucky - Daviess Cnty Medium
- Planted: 2024-04-24
- Harvested: 2024-09-17
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ky/2024/2446660
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Pioneer | P45A81E | - | 94.4 | - | - | $991.20 |
| 2 | Golden Harvest | GH4093E3 | Enlist E3 ® | 92.8 | - | - | $974.40 |
| 3 | Armor | Seed | Armor 45-F65 | 92.5 | - | - | $971.25 |
| 4 | Asgrow | AG40XF5 | - | 91.2 | - | - | $957.60 |
| 5 | Asgrow | AG43XF5 | - | 90.2 | - | - | $947.10 |
| 6 | NuTech | Seed | 43N11BE | 87.6 | - | - | $919.80 |
| 7 | APEX | AE4342S | - | 87.3 | - | - | $916.65 |
| 8 | Xitavo | XO | 4364E | 86.9 | - | - | $912.45 |
| 9 | UniSouth | Genetics | USG 7435XFS | 86.0 | - | - | $903.00 |
| 10 | Asgrow | AG42XF4 | - | 84.9 | - | - | $891.45 |
| 11 | Stine | 43EG29 | - | 84.6 | - | - | $888.30 |
| 12 | Armor | Seed | Armor 41-F65S | 84.5 | - | - | $887.25 |
| 12 | Channel | 4525RXF/SR | - | 84.5 | - | - | $887.25 |
| 14 | Pioneer | P42A84E | - | 84.3 | - | - | $885.15 |
| 15 | Fortus | 4125ES | - | 84.1 | - | - | $883.05 |
| 15 | Pioneer | P45Z75E | - | 84.1 | - | - | $883.05 |
| 17 | Connect | CT4025E | - | 83.8 | - | - | $879.90 |
| 18 | Golden Harvest | GH4345XFS | XtendFlex ® STS ® | 83.6 | - | - | $877.80 |
| 19 | Innvictis | Seed | Solutions A4102XF | 83.4 | - | - | $875.70 |
| 20 | Asgrow | AG44XF4 | - | 83.0 | - | - | $871.50 |
| 21 | Innvictis | Seed | Solutions B4553E | 82.9 | - | - | $870.45 |
| 21 | Golden Harvest | GH4433E3S | Enlist E3 ® STS ® | 82.9 | - | - | $870.45 |
| 23 | Asgrow | AG45XF3 | - | 82.4 | - | - | $865.20 |
| 24 | NuTech | Seed | 43N06E | 81.4 | - | - | $854.70 |
| 25 | Partners | Brand | Seed 4424 E3 S | 81.3 | - | - | $853.65 |
| 26 | Channel | 4125XF/SR | - | 80.9 | - | - | $849.45 |
| 27 | NuTech | Seed | 45N10E | 79.9 | - | - | $838.95 |
| 28 | NuTech | Seed | 42N05E | 78.6 | - | - | $825.30 |
| 29 | Catalyst | CT4413E3S | Enlist E3 ® STS ® | 78.5 | - | - | $824.25 |
| 30 | Stine | 41EG20 | - | 76.3 | - | - | $801.15 |
| 30 | Stine | 45EH29 | - | 76.3 | - | - | $801.15 |
| 32 | Innvictis | Seed | Solutions A4503XF | 75.8 | - | - | $795.90 |
| 33 | Stine | 42EG23 | - | 75.4 | - | - | $791.70 |
| 34 | Fortus | 4335E | - | 70.7 | - | - | $742.35 |
| 34 | Revere | Seed | Revere 44-F44 XFS | 70.7 | - | - | $742.35 |
| 36 | Connect | CT4525E | - | 70.4 | - | - | $739.20 |
| 37 | Xitavo | XO | 4405E | 70.1 | - | - | $736.05 |
| 38 | Stine | 44EH23 | - | 66.0 | - | - | $693.00 |
| 39 | Golden Harvest | GH4214E3S | Enlist E3 ® STS ® | 64.0 | - | - | $672.00 |
| 40 | Xitavo | XO | 4255E | 57.9 | - | - | $607.95 |
Top 5 by Yield: P45A81E (Pioneer) 94.4, GH4093E3 (Golden Harvest) 92.8, Seed (Armor) 92.5, AG40XF5 (Asgrow) 91.2, AG43XF5 (Asgrow) 90.2.