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>
2.5 KiB
2.5 KiB
Soybean yield trial — Michigan, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Michigan (MI)
- Year: 2024
- Plot ID: 2452445
- Cooperator: Michigan State University - Ingham Cnty Early
- Planted: 2024-05-20
- Harvested: 2024-10-24
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mi/2024/2452445
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Xitavo | XO | 2075E | 71.6 | - | - | $751.80 |
| 2 | Xitavo | XO | 2181E | 69.4 | - | - | $728.70 |
| 3 | D.F. | Seeds | DF 3211 N E3 | 69.3 | - | - | $727.65 |
| 4 | NK | NK23-P1E3 | Enlist E3 ® | 69.1 | - | - | $725.55 |
| 5 | Wyckoff | Hybrids | W2495E3 | 68.7 | - | - | $721.35 |
| 6 | D.F. | Seeds | DF 3245 N E3 | 68.2 | - | - | $716.10 |
| 7 | Wyckoff | Hybrids | W2695E3 | 68.1 | - | - | $715.05 |
| 8 | Wyckoff | Hybrids | W2570E3 | 67.8 | - | - | $711.90 |
| 9 | Golden Harvest | GH2745XF | XtendFlex ® | 67.2 | - | - | $705.60 |
| 10 | NK | NK23-D7E3 | Enlist E3 ® | 67.0 | - | - | $703.50 |
| 11 | Golden Harvest | GH2674E3 | Enlist E3 ® | 66.8 | - | - | $701.40 |
| 12 | Renk | Seed | G2390E | 66.2 | - | - | $695.10 |
| 13 | Xitavo | XO | 2305E | 65.6 | - | - | $688.80 |
| 14 | Loyal | Brand | L2560E | 65.3 | - | - | $685.65 |
| 15 | Xitavo | XO | 2625E | 64.9 | - | - | $681.45 |
| 16 | DonMario | Seeds | DM22E64 | 64.4 | - | - | $676.20 |
| 17 | Renk | Seed | RS255NXF | 64.2 | - | - | $674.10 |
| 18 | Wyckoff | Hybrids | W2390E3 | 64.1 | - | - | $673.05 |
| 19 | Xitavo | XO | 2735E | 64.0 | - | - | $672.00 |
| 20 | M | & | W Seeds 25E25 | 63.1 | - | - | $662.55 |
| 21 | Loyal | Brand | LSX232-24E | 62.7 | - | - | $658.35 |
| 22 | D.F. | Seeds | DF 3264 N E3 | 62.6 | - | - | $657.30 |
| 23 | M | & | W Seeds 27E42 | 61.7 | - | - | $647.85 |
| 24 | D.F. | Seeds | DF 3225 N E3 | 60.7 | - | - | $637.35 |
| 25 | M | & | W Seeds 18E89 | 60.6 | - | - | $636.30 |
| 26 | Xitavo | XO | 2444E | 59.9 | - | - | $628.95 |
| 27 | M | & | W Seeds 20E71 | 59.7 | - | - | $626.85 |
| 27 | Wyckoff | Hybrids | W2095E3 | 59.7 | - | - | $626.85 |
| 29 | DonMario | Seeds | DM24E84 | 58.0 | - | - | $609.00 |
| 30 | M | & | W Seeds 23E05 | 57.6 | - | - | $604.80 |
| 31 | Renk | Seed | G2790E | 57.2 | - | - | $600.60 |
| 32 | M | & | W Seeds 26E08 | 53.6 | - | - | $562.80 |
Top 5 by Yield: XO (Xitavo) 71.6, XO (Xitavo) 69.4, Seeds (D.F.) 69.3, NK23-P1E3 (NK) 69.1, Hybrids (Wyckoff) 68.7.