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>
2.3 KiB
2.3 KiB
Soybean yield trial — Alabama, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Alabama (AL)
- Year: 2024
- Plot ID: 2465781
- Cooperator: Greenpoint Ag Holdings Llc
- Planted: 2024-06-21
- Harvested: 2024-10-24
- Population: 138,000 seeds/acre
- Row width: 15"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/al/2024/2465781
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | NK | NK54-J9XFS | XtendFlex ® STS ® | 59.8 | 13.1 | 53.8 | $627.66 |
| 2 | Armor | Seed | Armor 48-F55S | 58.5 | 9.6 | 54.9 | $614.25 |
| 3 | Armor | Seed | Armor 51-F29S | 55.8 | 9.5 | 55.5 | $585.90 |
| 4 | NK | NK46-B4XFS | XtendFlex ® STS ® | 55.5 | 9.6 | 54.8 | $582.75 |
| 5 | Asgrow | AG50XF5 | - | 55.0 | 9.4 | 54.8 | $577.50 |
| 6 | UniSouth | Genetics | USG 7543XF | 54.5 | 11.3 | 54.9 | $572.25 |
| 7 | Asgrow | AG49XF4 | - | 54.1 | 9.5 | 53.7 | $567.73 |
| 8 | UniSouth | Genetics | USG 7463XFS | 54.0 | 9.7 | 54.5 | $567.00 |
| 9 | Armor | Seed | Armor 49-F37 | 53.7 | 9.6 | 54.2 | $563.85 |
| 9 | Armor | Seed | Armor 50-F96 | 53.7 | 9.4 | 55.8 | $563.85 |
| 11 | NK | NK49-N7XF | XtendFlex ® | 53.4 | 9.6 | 54.5 | $560.70 |
| 11 | Pioneer | P48Z70BLX | - | 53.4 | 9.3 | 55.1 | $560.70 |
| 13 | Pioneer | P46A90LX | - | 53.0 | 9.5 | 55.4 | $556.50 |
| 14 | Armor | Seed | Armor 46-F15S | 52.7 | 9.6 | 53.4 | $552.72 |
| 15 | NK | NK49-C2XFS | XtendFlex ® STS ® | 52.6 | 9.6 | 55.1 | $552.30 |
| 16 | Armor | Seed | Armor 45-F65 | 52.3 | 9.6 | 54.3 | $549.15 |
| 17 | Asgrow | AG48XF5 | - | 51.9 | 9.7 | 53.9 | $544.85 |
| 18 | Asgrow | AG47XF5 | - | 51.4 | 9.7 | 53.9 | $539.60 |
| 19 | UniSouth | Genetics | USG 7495XFS | 50.4 | 8.8 | 54.2 | $529.20 |
| 20 | Armor | Seed | Armor 46-F96 | 50.1 | 9.6 | 54.3 | $526.05 |
| 21 | Armor | Seed | Armor 54-F34 | 48.7 | 9.7 | 55.9 | $511.35 |
| 21 | NK | NK52-V1XF | XtendFlex ® | 48.7 | 9.5 | 54.6 | $511.35 |
| 23 | Asgrow | AG44XF4 | - | 47.3 | 9.6 | 54.7 | $496.65 |
| 24 | Pioneer | P50A08LX | - | 45.8 | 8.8 | 56.1 | $480.90 |
Top 5 by Yield: NK54-J9XFS (NK) 59.8, Seed (Armor) 58.5, Seed (Armor) 55.8, NK46-B4XFS (NK) 55.5, AG50XF5 (Asgrow) 55.0.