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: 2452444
- Cooperator: Michigan State University - Hillsdale Early
- Planted: 2024-06-04
- Harvested: 2024-11-12
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mi/2024/2452444
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Renk | Seed | RS255NXF | 68.4 | - | - | $718.20 |
| 2 | Xitavo | XO | 2075E | 67.3 | - | - | $706.65 |
| 3 | Xitavo | XO | 2181E | 67.0 | - | - | $703.50 |
| 4 | NK | NK23-D7E3 | Enlist E3 ® | 66.9 | - | - | $702.45 |
| 5 | D.F. | Seeds | DF 3245 N E3 | 66.7 | - | - | $700.35 |
| 6 | Xitavo | XO | 2625E | 66.6 | - | - | $699.30 |
| 7 | M | & | W Seeds 26E08 | 66.4 | - | - | $697.20 |
| 8 | Loyal | Brand | L2560E | 66.2 | - | - | $695.10 |
| 9 | Golden Harvest | GH2674E3 | Enlist E3 ® | 65.9 | - | - | $691.95 |
| 10 | D.F. | Seeds | DF 3225 N E3 | 65.7 | - | - | $689.85 |
| 11 | Xitavo | XO | 2735E | 64.9 | - | - | $681.45 |
| 12 | Xitavo | XO | 2444E | 64.6 | - | - | $678.30 |
| 13 | NK | NK23-P1E3 | Enlist E3 ® | 64.4 | - | - | $676.20 |
| 14 | Wyckoff | Hybrids | W2495E3 | 63.9 | - | - | $670.95 |
| 15 | M | & | W Seeds 25E25 | 63.7 | - | - | $668.85 |
| 16 | DonMario | Seeds | DM22E64 | 63.0 | - | - | $661.50 |
| 16 | Wyckoff | Hybrids | W2570E3 | 63.0 | - | - | $661.50 |
| 18 | Loyal | Brand | LSX232-24E | 62.7 | - | - | $658.35 |
| 19 | D.F. | Seeds | DF 3211 N E3 | 62.5 | - | - | $656.25 |
| 20 | DonMario | Seeds | DM24E84 | 62.4 | - | - | $655.20 |
| 21 | D.F. | Seeds | DF 3264 N E3 | 61.9 | - | - | $649.95 |
| 22 | Golden Harvest | GH2745XF | XtendFlex ® | 61.6 | - | - | $646.80 |
| 23 | Wyckoff | Hybrids | W2695E3 | 61.5 | - | - | $645.75 |
| 24 | M | & | W Seeds 18E89 | 60.4 | - | - | $634.20 |
| 25 | Xitavo | XO | 2305E | 60.1 | - | - | $631.05 |
| 26 | Renk | Seed | G2790E | 59.4 | - | - | $623.70 |
| 27 | M | & | W Seeds 20E71 | 59.3 | - | - | $622.65 |
| 28 | Wyckoff | Hybrids | W2095E3 | 56.7 | - | - | $595.35 |
| 29 | M | & | W Seeds 27E42 | 54.7 | - | - | $574.35 |
| 30 | M | & | W Seeds 23E05 | 53.9 | - | - | $565.95 |
| 31 | Renk | Seed | G2390E | 53.8 | - | - | $564.90 |
| 32 | Wyckoff | Hybrids | W2390E3 | 53.7 | - | - | $563.85 |
Top 5 by Yield: Seed (Renk) 68.4, XO (Xitavo) 67.3, XO (Xitavo) 67.0, NK23-D7E3 (NK) 66.9, Seeds (D.F.) 66.7.