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>
2.4 KiB
2.4 KiB
Soybean yield trial — QC, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: QC (QC)
- Year: 2025
- Plot ID: 2467041
- Cooperator: Entreprise Sterograin Inc.
- Planted: 2025-06-11
- Harvested: 2025-10-10
- Population: 140,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/qc/2025/2467041
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Prograin | DYNO | R2X | 55.1 | 11.0 | 59.7 | $578.55 |
| 2 | Pride | Seeds | PS 0944 XRN | 54.9 | 11.6 | 59.0 | $576.45 |
| 3 | NK | S12-M5X | Roundup Ready 2 Xtend ® | 54.6 | 11.3 | 59.7 | $573.30 |
| 4 | Prograin | MERCADO | XF | 54.4 | 12.6 | 59.5 | $571.20 |
| 5 | NK | S18-J4XF | XtendFlex ® | 54.2 | 21.2 | 54.4 | $569.10 |
| 6 | Pride | Seeds | PS 1777 EN | 53.8 | 16.7 | 55.9 | $564.90 |
| 7 | Prograin | Experimental | - | 53.2 | 13.4 | 58.5 | $558.60 |
| 8 | Pride | Seeds | Experimental | 52.9 | 11.4 | 58.5 | $555.45 |
| 8 | Pride | Seeds | PS 1344 XFN | 52.9 | 12.4 | 58.9 | $555.45 |
| 10 | Prograin | Wilma | - | 52.8 | 11.4 | 60.5 | $554.40 |
| 10 | Prograin | Experimental | - | 52.8 | 11.7 | 59.0 | $554.40 |
| 10 | NK | S11-A4E3 | Enlist E3 ® | 52.8 | 12.0 | 59.2 | $554.40 |
| 13 | Prograin | Experimental | - | 52.6 | 11.4 | 59.0 | $552.30 |
| 14 | NK | S11-U2XF | XtendFlex ® | 52.5 | 11.9 | 59.3 | $551.25 |
| 15 | Prograin | Atena | - | 52.0 | 11.5 | 59.8 | $546.00 |
| 16 | NK | S11-A4E3 | Enlist E3 ® | 51.9 | 12.3 | 58.9 | $544.95 |
| 17 | NK | S10-H1XF | XtendFlex ® | 51.8 | 12.0 | 59.2 | $543.90 |
| 18 | NK | S15-G9E3S | Enlist E3 ® STS ® | 51.6 | 12.7 | 59.5 | $541.80 |
| 19 | Prograin | Akila | HO | 51.0 | 12.1 | 58.9 | $535.50 |
| 20 | Pride | Seeds | Experimental | 50.4 | 12.0 | 59.4 | $529.20 |
| 21 | NK | S08-Z4E3 | Enlist E3 ® | 49.5 | 11.3 | 59.0 | $519.75 |
| 22 | Prograin | Experimental | - | 49.2 | 11.2 | 58.0 | $516.60 |
| 23 | Pride | Seeds | Experimental | 48.7 | 17.6 | 55.3 | $511.35 |
| 24 | Prograin | Hola | - | 47.9 | 11.2 | 60.3 | $502.95 |
| 25 | Prograin | AYA | - | 47.4 | 11.2 | 59.8 | $497.70 |
| 26 | Pride | Seeds | Experimental | 46.9 | 11.3 | 60.0 | $492.45 |
Top 5 by Yield: DYNO (Prograin) 55.1, Seeds (Pride) 54.9, S12-M5X (NK) 54.6, MERCADO (Prograin) 54.4, S18-J4XF (NK) 54.2.