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>
1.9 KiB
1.9 KiB
Soybean yield trial — Arkansas, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Arkansas (AR)
- Year: 2024
- Plot ID: 2414779
- Cooperator: Barton Edwin Eldridge
- Planted: 2024-04-18
- Harvested: 2024-09-20
- Population: 125,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ar/2024/2414779
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Pioneer | P46A90LX | - | 67.4 | 13.0 | 59.3 | $707.70 |
| 2 | NK | NK49-C2XFS | XtendFlex ® STS ® | 66.4 | 13.5 | 54.5 | $697.20 |
| 3 | Pioneer | P48Z70BLX | - | 65.5 | 13.2 | 57.7 | $687.75 |
| 4 | NK | NK47-G5E3S | Enlist E3 ® STS ® | 65.1 | 13.9 | 56.2 | $683.55 |
| 5 | Pioneer | P49Z02E | - | 63.4 | 13.1 | 58.6 | $665.70 |
| 6 | Pioneer | P48A14E | - | 63.0 | 12.7 | 61.1 | $661.50 |
| 7 | Pioneer | P45A70LX | - | 61.9 | 12.9 | 55.9 | $649.95 |
| 8 | NK | NK42-T5XF | XtendFlex ® | 61.1 | 13.9 | 55.1 | $641.55 |
| 9 | Pioneer | P47Z15BE | - | 60.8 | 12.9 | 57.5 | $638.40 |
| 10 | NK | NK42-A6E3S | Enlist E3 ® STS ® | 59.5 | 13.7 | 54.4 | $624.75 |
| 10 | Pioneer | P45Z75E | - | 59.5 | 13.3 | 55.1 | $624.75 |
| 12 | Pioneer | P42A84E | - | 59.0 | 12.6 | 58.2 | $619.50 |
| 13 | NK | NK43-W1XFS | XtendFlex ® STS ® | 58.5 | 13.0 | 54.6 | $614.25 |
| 14 | NK | NK44-Q5E3S | Enlist E3 ® STS ® | 58.0 | 13.0 | 53.8 | $608.77 |
| 15 | NK | NK49-N7XF | XtendFlex ® | 57.9 | 13.7 | 55.1 | $607.95 |
| 16 | NK | NK44-J4XFS | XtendFlex ® STS ® | 57.1 | 13.3 | 54.9 | $599.55 |
| 17 | NK | NK48-A8XFS | XtendFlex ® STS ® | 56.9 | 14.0 | 54.2 | $597.45 |
| 18 | NK | NK49-U9E3S | Enlist E3 ® STS ® | 52.0 | 14.4 | 52.8 | $544.75 |
Top 5 by Yield: P46A90LX (Pioneer) 67.4, NK49-C2XFS (NK) 66.4, P48Z70BLX (Pioneer) 65.5, NK47-G5E3S (NK) 65.1, P49Z02E (Pioneer) 63.4.