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 — North Dakota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: North Dakota (ND)
- Year: 2024
- Plot ID: 2438062
- Cooperator: NDSU - Langdon Research Extension Center (Walsh Cnty)
- Planted: 2024-05-10
- Harvested: 2024-10-02
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/nd/2024/2438062
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Legacy | Seeds | LS034-24 XF | 76.2 | - | - | $800.10 |
| 2 | Legacy | Seeds | LS044-23 XF | 72.8 | - | - | $764.40 |
| 3 | Channel | 0325RXF | - | 71.3 | - | - | $748.65 |
| 3 | NK | NK03-V5E3 | Enlist E3 ® | 71.3 | - | - | $748.65 |
| 5 | Proseed | EL | 50-13N | 70.2 | - | - | $737.10 |
| 6 | Xitavo | XO | 0234E | 69.9 | - | - | $733.95 |
| 7 | Fortus | 0165E | - | 69.1 | - | - | $725.55 |
| 8 | Legacy | Seeds | LS014-23 XF | 69.0 | - | - | $724.50 |
| 9 | Proseed | XF | 50-52N | 68.6 | - | - | $720.30 |
| 10 | Legacy | Seeds | LS032-23 E | 68.4 | - | - | $718.20 |
| 11 | Proseed | XF | 40-12 | 68.1 | - | - | $715.05 |
| 12 | Fortus | 0084E | - | 67.5 | - | - | $708.75 |
| 12 | Integra | Fortified | Seed XF0115 | 67.5 | - | - | $708.75 |
| 14 | NK | NK02-W8E3 | Enlist E3 ® | 67.4 | - | - | $707.70 |
| 15 | Integra | Fortified | Seed XF0493 | 66.6 | - | - | $699.30 |
| 16 | Xitavo | XO | 0094E | 65.7 | - | - | $689.85 |
| 17 | NK | NK009-G7E3 | Enlist E3 ® | 65.6 | - | - | $688.80 |
| 18 | Integra | Fortified | Seed XF0212 | 65.4 | - | - | $686.70 |
| 19 | Legacy | Seeds | LS022-24 E | 65.2 | - | - | $684.60 |
| 20 | Fortus | 0544E | - | 64.6 | - | - | $678.30 |
| 21 | Proseed | EL | 50-33N | 63.4 | - | - | $665.70 |
| 22 | Proseed | XF | 30-42 | 62.6 | - | - | $657.30 |
| 23 | NDSU | ND17009GT | - | 62.4 | - | - | $655.20 |
| 24 | Channel | 00924RXF | - | 61.3 | - | - | $643.65 |
| 24 | Fortus | 0324E | - | 61.3 | - | - | $643.65 |
| 26 | Channel | 0225RXF | - | 60.0 | - | - | $630.00 |
| 27 | Golden Harvest | GH0225XF | XtendFlex ® | 59.8 | - | - | $627.90 |
| 28 | Legacy | Seeds | LS024-23 XF | 58.9 | - | - | $618.45 |
| 29 | NDSU | ND21008GT20 | - | 58.7 | - | - | $616.35 |
| 30 | Golden Harvest | GH0384XF | XtendFlex ® | 56.1 | - | - | $589.05 |
| 31 | NK | NK006-Z5XF | XtendFlex ® | 51.4 | - | - | $539.70 |
| 32 | NK | NK006-U6E3 | Enlist E3 ® | 50.8 | - | - | $533.40 |
Top 5 by Yield: Seeds (Legacy) 76.2, Seeds (Legacy) 72.8, 0325RXF (Channel) 71.3, NK03-V5E3 (NK) 71.3, EL (Proseed) 70.2.