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>
2.1 KiB
2.1 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: 2446655
- Cooperator: University of Kentucky - Simpson Cnty Early
- Planted: 2024-04-25
- Harvested: 2024-09-16
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ky/2024/2446655
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | NuTech | Seed | 35N05E | 74.2 | - | - | $779.10 |
| 2 | Golden Harvest | GH3774E3 | Enlist E3 ® | 72.6 | - | - | $762.30 |
| 3 | NuTech | Seed | 37N03E | 70.9 | - | - | $744.45 |
| 4 | Asgrow | AG36XF4 | - | 69.7 | - | - | $731.85 |
| 5 | Stine | 39EH23 | - | 69.4 | - | - | $728.70 |
| 6 | Pioneer | P38A28E | - | 69.0 | - | - | $724.50 |
| 7 | Partners | Brand | Seed 3323 E3 S | 68.0 | - | - | $714.00 |
| 8 | NuTech | Seed | 38N05E | 67.8 | - | - | $711.90 |
| 9 | Asgrow | AG38XF3 | - | 67.5 | - | - | $708.75 |
| 10 | NuTech | Seed | 36N06E | 67.4 | - | - | $707.70 |
| 11 | Revere | Seed | Revere 3908XFS | 67.3 | - | - | $706.65 |
| 12 | Revere | Seed | Revere 36-E54 | 66.2 | - | - | $695.10 |
| 13 | Xitavo | XO | 3855E | 66.0 | - | - | $693.00 |
| 14 | Catalyst | CT3933E3 | - | 65.9 | - | - | $691.95 |
| 15 | Asgrow | AG33XF3 | - | 65.8 | - | - | $690.90 |
| 15 | Armor | Seed | Armor 39-E35S | 65.8 | - | - | $690.90 |
| 17 | Partners | Brand | Seed 3925 E3 S | 65.7 | - | - | $689.85 |
| 17 | Stine | 39EF32 | - | 65.7 | - | - | $689.85 |
| 19 | NuTech | Seed | 39N08E | 65.3 | - | - | $685.65 |
| 20 | Innvictis | Seed | Solutions A3974XF | 65.1 | - | - | $683.55 |
| 21 | Innvictis | Seed | Solutions B3934E | 64.9 | - | - | $681.45 |
| 22 | Channel | 3725RXF | - | 64.7 | - | - | $679.35 |
| 23 | Revere | Seed | Revere 39-E71 | 63.3 | - | - | $664.65 |
| 24 | Xitavo | XO | 3795E | 58.8 | - | - | $617.40 |
Top 5 by Yield: Seed (NuTech) 74.2, GH3774E3 (Golden Harvest) 72.6, Seed (NuTech) 70.9, AG36XF4 (Asgrow) 69.7, 39EH23 (Stine) 69.4.