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 — Ohio, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Ohio (OH)
- Year: 2024
- Plot ID: 2420170
- Cooperator: Ohio State University - Clinton County (Late)
- Planted: 2024-05-20
- Harvested: 2024-10-08
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/oh/2024/2420170
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Seed | Consultants | SC7385E | 87.5 | - | - | $918.75 |
| 2 | NK | NK40-P5E3 | Enlist E3 ® | 86.5 | - | - | $908.25 |
| 3 | NK | NK39-J2E3 | Enlist E3 ® | 85.3 | - | - | $895.65 |
| 4 | Axis | Seed | 3835E | 85.1 | - | - | $893.55 |
| 5 | Ebberts | G3760ES | - | 84.9 | - | - | $891.45 |
| 6 | Seed | Genetics | Direct ET-4738E3 | 84.4 | - | - | $886.20 |
| 7 | Seed | Consultants | SC7375E | 84.1 | - | - | $883.05 |
| 8 | Benson | Hill | BH39A232 | 82.2 | - | - | $863.10 |
| 9 | Benson | Hill | BX37C755 | 81.7 | - | - | $857.85 |
| 10 | Asgrow | AG39XF3 | - | 80.7 | - | - | $847.35 |
| 11 | NK | NK37-C1E3 | Enlist E3 ® | 79.5 | - | - | $834.75 |
| 12 | Seed | Genetics | Direct ET-4739E3 | 78.7 | - | - | $826.35 |
| 13 | Xitavo | XO | 3795E | 78.4 | - | - | $823.20 |
| 13 | Xitavo | XO | 3855E | 78.4 | - | - | $823.20 |
| 15 | Seed | Genetics | Direct ET-3739E3S | 76.6 | - | - | $804.30 |
| 16 | Benson | Hill | BX37Q467 | 76.5 | - | - | $803.25 |
| 17 | Asgrow | AG43XF2 | - | 75.7 | - | - | $794.85 |
| 18 | DonMario | Seeds | DM38E54 | 75.4 | - | - | $791.70 |
| 19 | Xitavo | XO | 4255E | 71.7 | - | - | $752.85 |
| 20 | Benson | Hill | BH37Q218 | 71.4 | - | - | $749.70 |
| 21 | Seed | Genetics | Direct ET-4743E3S | 69.7 | - | - | $731.85 |
| 22 | Benson | Hill | BH37U205 | 69.6 | - | - | $730.80 |
| 23 | Benson | Hill | C38H052S | 68.4 | - | - | $718.20 |
| 24 | Seed | Genetics | Direct ET-4744E3S | 67.5 | - | - | $708.75 |
Top 5 by Yield: Consultants (Seed) 87.5, NK40-P5E3 (NK) 86.5, NK39-J2E3 (NK) 85.3, Seed (Axis) 85.1, G3760ES (Ebberts) 84.9.