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 — Mississippi, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Mississippi (MS)
- Year: 2024
- Plot ID: 2419597
- Cooperator: Dean Partnership
- Planted: 2024-05-08
- Harvested: 2024-10-04
- Population: 125,000 seeds/acre
- Row width: 38"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ms/2024/2419597
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Armor | Seed | Armor 46-F96 | 96.9 | 11.4 | 61.0 | $1017.45 |
| 2 | Armor | Seed | Armor 45-F65 | 93.7 | 12.0 | 51.0 | $978.23 |
| 3 | NK | NK44-J4XFS | XtendFlex ® STS ® | 92.0 | 10.4 | 59.9 | $966.00 |
| 4 | Armor | Seed | Armor 45-F02 | 91.3 | 11.5 | 59.3 | $958.65 |
| 5 | Asgrow | AG44XF4 | - | 90.6 | 11.1 | 57.6 | $951.30 |
| 5 | Beck's | 4337XF | - | 90.6 | 10.5 | 54.3 | $951.30 |
| 7 | Armor | Seed | Armor 48-F55S | 90.0 | 12.2 | 58.7 | $945.00 |
| 8 | NK | NK42-T5XF | XtendFlex ® | 89.9 | 9.7 | 57.0 | $943.95 |
| 9 | Pioneer | P45A70LX | - | 89.6 | 10.9 | 60.4 | $940.80 |
| 10 | Pioneer | P41Z80BLX | - | 89.0 | 10.8 | 59.8 | $934.50 |
| 10 | Innvictis | Seed | Solutions A4924XF | 89.0 | 10.0 | 60.9 | $934.50 |
| 12 | Pioneer | P48Z70BLX | - | 88.5 | 11.6 | 56.7 | $929.25 |
| 13 | Asgrow | AG45XF3 | - | 88.4 | 10.9 | 58.7 | $928.20 |
| 14 | Armor | Seed | Armor 46-F15S | 87.8 | 11.3 | 57.1 | $921.90 |
| 15 | Pioneer | P48A04LX | - | 87.0 | 11.4 | 59.3 | $913.50 |
| 16 | Pioneer | P44A60LX | - | 85.7 | 11.8 | 51.7 | $895.91 |
| 17 | Pioneer | P46A90LX | - | 85.5 | 12.1 | 56.4 | $897.75 |
| 18 | NK | NK49-N7XF | XtendFlex ® | 84.3 | 10.2 | 58.5 | $885.15 |
| 19 | Innvictis | Seed | Solutions A4862XF | 84.1 | 11.4 | 55.0 | $883.05 |
| 20 | NK | NK48-A8XFS | XtendFlex ® STS ® | 83.9 | 10.0 | 59.6 | $880.95 |
| 21 | Armor | Seed | Armor 50-F96 | 83.8 | 12.2 | 58.7 | $879.90 |
| 21 | Asgrow | AG46XF3 | - | 83.8 | 11.1 | 57.8 | $879.90 |
| 23 | NK | NK43-W1XFS | XtendFlex ® STS ® | 83.2 | 10.9 | 55.2 | $873.60 |
| 24 | NK | NK49-C2XFS | XtendFlex ® STS ® | 81.4 | 11.2 | 54.3 | $854.70 |
| 24 | Beck's | 4999XF | - | 81.4 | 10.8 | 56.1 | $854.70 |
| 26 | Innvictis | Seed | Solutions A4814XF | 80.8 | 11.1 | 60.0 | $848.40 |
| 27 | Beck's | 4777XF | - | 79.5 | 10.5 | 55.2 | $834.75 |
| 28 | Innvictis | Seed | Solutions A4503XF | 79.3 | 11.1 | 56.1 | $832.65 |
| 29 | Beck's | 4991X2 | - | 79.1 | 9.8 | 59.4 | $830.55 |
| 30 | Asgrow | AG49XF4 | - | 77.8 | 10.7 | 59.0 | $816.90 |
| 31 | NK | S49-F5X | Roundup Ready 2 Xtend ® | 77.5 | 10.9 | 55.0 | $813.75 |
| 32 | Beck's | 4661XF | - | 76.9 | 9.6 | 59.3 | $807.45 |
| 33 | Beck's | 4887XF | - | 76.8 | 9.7 | 58.3 | $806.40 |
| 34 | Armor | Seed | Armor 46-F35S | 74.6 | 12.5 | 56.3 | $783.30 |
| 35 | NK | NK46-B4XFS | XtendFlex ® STS ® | 68.1 | 10.9 | 57.6 | $715.05 |
Top 5 by Yield: Seed (Armor) 96.9, Seed (Armor) 93.7, NK44-J4XFS (NK) 92.0, Seed (Armor) 91.3, AG44XF4 (Asgrow) 90.6.