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>
2.7 KiB
2.7 KiB
Soybean yield trial — Missouri, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Missouri (MO)
- Year: 2024
- Plot ID: 2420189
- Cooperator: University of Missouri - Truxton
- Planted: 2024-05-20
- Harvested: 2024-10-02
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mo/2024/2420189
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Asgrow | AG40XF1 | - | 62.5 | - | - | $656.25 |
| 2 | Lakeview | Farms | Experimental | 60.9 | - | - | $639.45 |
| 3 | Golden Harvest | GH4093E3 | Enlist E3 ® | 60.7 | - | - | $637.35 |
| 4 | NuTech | Seed | 43N06E | 60.5 | - | - | $635.25 |
| 5 | Pioneer | P44A91E | - | 59.6 | - | - | $625.80 |
| 6 | Pioneer | P40A23E | - | 59.1 | - | - | $620.55 |
| 7 | NuTech | Seed | 45N10E | 58.9 | - | - | $618.45 |
| 8 | AgVenture | AV47Y6E | - | 58.5 | - | - | $614.25 |
| 9 | NK | NK40-P5E3 | Enlist E3 ® | 58.3 | - | - | $612.15 |
| 10 | Asgrow | AG42XF4 | - | 57.3 | - | - | $601.65 |
| 11 | Pioneer | P47Z15BE | - | 57.0 | - | - | $598.50 |
| 12 | Channel | 4720RXF/SR | - | 56.9 | - | - | $597.45 |
| 13 | Asgrow | AG47XF2 | - | 56.6 | - | - | $594.30 |
| 14 | NuTech | Seed | 47N04E | 56.5 | - | - | $593.25 |
| 15 | Missouri | U | S20-2227 | 56.2 | - | - | $590.10 |
| 16 | Lakeview | Farms | LVF4331 | 56.0 | - | - | $588.00 |
| 17 | Asgrow | AG41XF2 | - | 55.9 | - | - | $586.95 |
| 18 | Golden Harvest | GH4214E3S | Enlist E3 ® STS ® | 55.6 | - | - | $583.80 |
| 19 | Pioneer | P45A70LX | - | 55.5 | - | - | $582.75 |
| 19 | Pioneer | P45Z75E | - | 55.5 | - | - | $582.75 |
| 21 | NuTech | Seed | 49N05E | 55.0 | - | - | $577.50 |
| 22 | NuTech | Seed | 42N05E | 54.7 | - | - | $574.35 |
| 22 | Pioneer | P42A84E | - | 54.7 | - | - | $574.35 |
| 22 | Pioneer | P43Z44SE | - | 54.7 | - | - | $574.35 |
| 25 | Golden Harvest | GH4433E3S | Enlist E3 ® STS ® | 54.2 | - | - | $569.10 |
| 26 | Pioneer | P49Z02E | - | 53.8 | - | - | $564.90 |
| 27 | NK | NK42-A6E3S | Enlist E3 ® STS ® | 53.6 | - | - | $562.80 |
| 28 | Pioneer | P46A09E | - | 53.0 | - | - | $556.50 |
| 29 | Channel | 4823RXF/SR | - | 52.7 | - | - | $553.35 |
| 30 | Pioneer | P46A90LX | - | 52.5 | - | - | $551.25 |
| 31 | Pioneer | P48Z70BLX | - | 52.1 | - | - | $547.05 |
| 32 | AgVenture | AV45B2E | - | 52.0 | - | - | $546.00 |
| 32 | Asgrow | AG44XF4 | - | 52.0 | - | - | $546.00 |
| 34 | AgVenture | AV44B2E | - | 50.3 | - | - | $528.15 |
| 35 | Brevant | B402EE | - | 46.4 | - | - | $487.20 |
Top 5 by Yield: AG40XF1 (Asgrow) 62.5, Farms (Lakeview) 60.9, GH4093E3 (Golden Harvest) 60.7, Seed (NuTech) 60.5, P44A91E (Pioneer) 59.6.