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>
3.3 KiB
3.3 KiB
Soybean yield trial — Oklahoma, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Oklahoma (OK)
- Year: 2025
- Plot ID: 2470359
- Cooperator: Wright Seed Llc
- Planted: 2025-06-15
- Harvested: 2025-11-05
- Population: 140,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ok/2025/2470359
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Beck's | 4661XF | - | 51.1 | 5.9 | 53.4 | $535.94 |
| 2 | AgriGold | G5364XF | - | 48.4 | 6.3 | 55.5 | $508.20 |
| 3 | Pioneer | P48A14E | - | 46.0 | 5.9 | 54.6 | $483.00 |
| 4 | Asgrow | AG48XF5 | - | 45.4 | 6.0 | 53.2 | $475.97 |
| 4 | NSGA | Sitzer | 4.9 | 45.4 | 5.5 | 56.8 | $476.70 |
| 6 | Asgrow | AG46XF2 | - | 45.2 | 5.6 | 54.5 | $474.60 |
| 7 | NSGA | Drew | III | 44.4 | 5.9 | 56.5 | $466.20 |
| 8 | Asgrow | AG48XF6 | - | 43.6 | 5.6 | 54.5 | $457.80 |
| 9 | Golden Harvest | GH4775E3S | Enlist E3 ® STS ® | 42.8 | 5.5 | 54.3 | $449.40 |
| 10 | AgriGold | G4650XF | - | 40.2 | 5.6 | 53.6 | $421.78 |
| 11 | Golden Harvest | GH4696E3 | Enlist E3 ® | 39.7 | 5.2 | 53.7 | $416.61 |
| 12 | Pioneer | P49Z02E | - | 39.1 | 5.3 | 53.3 | $410.00 |
| 13 | Pioneer | P44Z67BE | - | 39.0 | 5.4 | 52.3 | $408.17 |
| 14 | Beck's | 4760E3 | - | 38.9 | 5.4 | 53.4 | $407.98 |
| 15 | AgriGold | G5104XF | - | 38.5 | 6.0 | 52.8 | $403.33 |
| 16 | Beck's | 4860E3 | - | 37.9 | 5.3 | 55.0 | $397.95 |
| 17 | Golden Harvest | GH4766XFS | XtendFlex ® STS ® | 37.3 | 5.2 | 54.5 | $391.65 |
| 18 | Beck's | 4551XF | - | 37.1 | 5.9 | 52.9 | $388.73 |
| 19 | Golden Harvest | GH4995E3S | Enlist E3 ® STS ® | 37.0 | 5.2 | 53.8 | $388.35 |
| 20 | AgriGold | G4755XF | - | 36.6 | 5.5 | 53.8 | $384.15 |
| 21 | Beck's | 4777XF | - | 36.3 | 5.6 | 52.9 | $380.35 |
| 22 | Golden Harvest | GH4882XFS | XtendFlex ® STS ® | 36.1 | 5.6 | 53.9 | $378.98 |
| 23 | Asgrow | AG49XF3 | - | 36.0 | 5.7 | 54.4 | $378.00 |
| 24 | Golden Harvest | GH4944XFS | XtendFlex ® STS ® | 35.8 | 5.2 | 53.6 | $375.61 |
| 24 | Pioneer | P47Z15BE | - | 35.8 | 5.3 | 55.1 | $375.90 |
| 26 | Golden Harvest | GH5056E3S | Enlist E3 ® STS ® | 35.1 | 5.7 | 52.1 | $367.22 |
| 27 | Alloy | A47E35 | - | 34.1 | 5.7 | 54.6 | $358.05 |
| 28 | Asgrow | AG49XF6 | - | 33.0 | 5.3 | 54.2 | $346.50 |
| 28 | Pioneer | P50Z95E | - | 33.0 | 5.2 | 53.7 | $346.30 |
| 30 | Asgrow | AG52XF5 | - | 32.9 | 5.2 | 49.8 | $342.69 |
| 31 | Beck's | 4999XF | - | 32.7 | 5.2 | 54.1 | $343.35 |
| 32 | Golden Harvest | GH5226XFS | XtendFlex ® STS ® | 31.3 | 5.6 | 54.1 | $328.65 |
| 33 | Asgrow | AG52XF0 | - | 30.8 | 5.8 | 53.8 | $323.28 |
| 34 | NSGA | 52Cl22 | - | 30.3 | 6.2 | 54.5 | $318.15 |
| 35 | Asgrow | AG47XF2 | - | 30.2 | 5.4 | 54.1 | $317.10 |
| 36 | Pioneer | P45Z75E | - | 29.8 | 5.1 | 54.3 | $312.90 |
| 37 | Golden Harvest | GH4546XFS | XtendFlex ® STS ® | 29.5 | 5.4 | 51.5 | $308.28 |
| 38 | Alloy | A49E34 | - | 28.5 | 5.9 | 49.2 | $296.51 |
| 39 | Beck's | 4991X2 | - | 24.4 | 5.2 | 53.8 | $256.10 |
| 40 | Beck's | 4337XF | - | 24.0 | 5.5 | 49.8 | $249.98 |
| 41 | Beck's | 4320E3 | - | 21.7 | 7.9 | 51.2 | $226.63 |
Top 5 by Yield: 4661XF (Beck's) 51.1, G5364XF (AgriGold) 48.4, P48A14E (Pioneer) 46.0, AG48XF5 (Asgrow) 45.4, Sitzer (NSGA) 45.4.