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>
1.7 KiB
1.7 KiB
Soybean yield trial — Virginia, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Virginia (VA)
- Year: 2024
- Plot ID: 2452468
- Cooperator: Virginia Tech - Warsaw, VA Early Group 4
- Planted: 2024-05-02
- Harvested: 2024-10-07
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/va/2024/2452468
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Fortus | 4335E | - | 80.8 | - | - | $848.40 |
| 2 | UniSouth | Genetics | USG 7435XFS | 80.2 | - | - | $842.10 |
| 3 | UniSouth | Genetics | USG 7415ET | 79.2 | - | - | $831.60 |
| 4 | NK | NK43-W1XFS | XtendFlex ® STS ® | 78.9 | - | - | $828.45 |
| 5 | Channel | 4424RXF/SR | - | 78.6 | - | - | $825.30 |
| 6 | NK | NK42-A6E3S | Enlist E3 ® STS ® | 77.7 | - | - | $815.85 |
| 7 | Revere | Seed | Revere 44-F44 XFS | 77.6 | - | - | $814.80 |
| 8 | Virginia | Tech | V18-3866 | 77.5 | - | - | $813.75 |
| 9 | Asgrow | AG43XF5 | - | 76.4 | - | - | $802.20 |
| 10 | Southern | Harvest | SH4024 E3 | 76.3 | - | - | $801.15 |
| 11 | UniSouth | Genetics | USG 7434XF | 74.9 | - | - | $786.45 |
| 12 | Golden Harvest | GH4214E3S | Enlist E3 ® STS ® | 74.8 | - | - | $785.40 |
| 13 | Virginia | Tech | V20-1478R2DI | 74.1 | - | - | $778.05 |
| 14 | Virginia | Tech | V18-2720R2 | 71.8 | - | - | $753.90 |
| 15 | Public | P41MO21 | - | 71.4 | - | - | $749.70 |
| 16 | Arkansas | U | R19C-1012 | 69.5 | - | - | $729.75 |
| 17 | Virginia | Tech | V19-0064DT | 67.6 | - | - | $709.80 |
Top 5 by Yield: 4335E (Fortus) 80.8, Genetics (UniSouth) 80.2, Genetics (UniSouth) 79.2, NK43-W1XFS (NK) 78.9, 4424RXF/SR (Channel) 78.6.