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>
3.2 KiB
3.2 KiB
Soybean yield trial — Kentucky, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Kentucky (KY)
- Year: 2024
- Plot ID: 2446671
- Cooperator: University of Kentucky - Fayette Cnty Late
- Planted: 2024-05-01
- Harvested: 2024-09-20
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ky/2024/2446671
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | NuTech | Seed | 47N11BE | 56.5 | - | - | $593.25 |
| 2 | Innvictis | Seed | Solutions A4664XF | 55.3 | - | - | $580.65 |
| 2 | NuTech | Seed | 49N05E | 55.3 | - | - | $580.65 |
| 4 | Pioneer | P49Z02E | - | 55.2 | - | - | $579.60 |
| 5 | Innvictis | Seed | Solutions A4862XF | 55.1 | - | - | $578.55 |
| 6 | Pioneer | P48A14E | - | 54.9 | - | - | $576.45 |
| 7 | Asgrow | AG49XF4 | - | 54.0 | - | - | $567.00 |
| 8 | Partners | Brand | Seed 4726 E3 S | 53.7 | - | - | $563.85 |
| 9 | Armor | Seed | Armor 48-E95 | 53.1 | - | - | $557.55 |
| 10 | Golden Harvest | GH5253E3 | Enlist E3 ® | 52.8 | - | - | $554.40 |
| 11 | GDM | Seeds | 46F54S | 52.7 | - | - | $553.35 |
| 11 | NuTech | Seed | 47N04E | 52.7 | - | - | $553.35 |
| 11 | UniSouth | Genetics | USG 7495XFS | 52.7 | - | - | $553.35 |
| 14 | Fortus | 4665ES | - | 52.5 | - | - | $551.25 |
| 15 | Integra | Fortified | Seed XF4875S | 52.4 | - | - | $550.20 |
| 16 | Innvictis | Seed | Solutions A4924XF | 52.2 | - | - | $548.10 |
| 17 | Xitavo | XO | 4894E | 52.0 | - | - | $546.00 |
| 18 | Revere | Seed | Revere 47-F77 XFS | 51.0 | - | - | $535.50 |
| 19 | Integra | Fortified | Seed XF4634S | 50.7 | - | - | $532.35 |
| 20 | Armor | Seed | Armor 46-E75S | 50.6 | - | - | $531.30 |
| 21 | UniSouth | Genetics | USG 7474XFS | 50.3 | - | - | $528.15 |
| 21 | Xitavo | XO | 4772E | 50.3 | - | - | $528.15 |
| 23 | Golden Harvest | GH4995E3S | Enlist E3 ® STS ® | 50.2 | - | - | $527.10 |
| 24 | Stine | 46EG92 | - | 50.1 | - | - | $526.05 |
| 25 | Partners | Brand | Seed 4624 E3 S | 50.0 | - | - | $525.00 |
| 26 | GDM | Seeds | 48F53 | 49.9 | - | - | $523.95 |
| 27 | Golden Harvest | GH4864XFS | XtendFlex ® STS ® | 49.8 | - | - | $522.90 |
| 27 | Golden Harvest | GH4944XFS | XtendFlex ® STS ® | 49.8 | - | - | $522.90 |
| 29 | APEX | AE4640S | - | 49.0 | - | - | $514.50 |
| 30 | Asgrow | AG48XF3 | - | 48.8 | - | - | $512.40 |
| 30 | Revere | Seed | Revere 49-F36 XF | 48.8 | - | - | $512.40 |
| 32 | Armor | Seed | Armor 46-F15S | 48.7 | - | - | $511.35 |
| 32 | Golden Harvest | GH4775E3S | Enlist E3 ® STS ® | 48.7 | - | - | $511.35 |
| 34 | Innvictis | Seed | Solutions B4904E | 48.2 | - | - | $506.10 |
| 35 | Stine | 46EE20 | - | 47.6 | - | - | $499.80 |
| 36 | Stine | 48EE20 | - | 47.4 | - | - | $497.70 |
| 37 | Asgrow | AG46XF3 | - | 46.7 | - | - | $490.35 |
| 38 | Revere | Seed | Revere 4826XFS | 45.6 | - | - | $478.80 |
| 39 | Innvictis | Seed | Solutions A4814XF | 44.7 | - | - | $469.35 |
| 39 | UniSouth | Genetics | USG 7463XF | 44.7 | - | - | $469.35 |
| 41 | Asgrow | AG47XF5 | - | 43.7 | - | - | $458.85 |
Top 5 by Yield: Seed (NuTech) 56.5, Seed (Innvictis) 55.3, Seed (NuTech) 55.3, P49Z02E (Pioneer) 55.2, Seed (Innvictis) 55.1.