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: 2446670
- Cooperator: University of Kentucky - Woodford Cnty Late
- Planted: 2024-04-29
- Harvested: 2024-09-22
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ky/2024/2446670
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Pioneer | P49Z02E | - | 64.9 | - | - | $681.45 |
| 2 | Innvictis | Seed | Solutions A4862XF | 64.3 | - | - | $675.15 |
| 3 | GDM | Seeds | 48F53 | 63.9 | - | - | $670.95 |
| 4 | Integra | Fortified | Seed XF4875S | 63.3 | - | - | $664.65 |
| 5 | Asgrow | AG47XF5 | - | 62.3 | - | - | $654.15 |
| 6 | NuTech | Seed | 49N05E | 62.2 | - | - | $653.10 |
| 6 | Revere | Seed | Revere 47-F77 XFS | 62.2 | - | - | $653.10 |
| 8 | Partners | Brand | Seed 4726 E3 S | 61.7 | - | - | $647.85 |
| 9 | Pioneer | P48A14E | - | 60.8 | - | - | $638.40 |
| 10 | Stine | 48EE20 | - | 60.7 | - | - | $637.35 |
| 11 | Revere | Seed | Revere 4826XFS | 60.6 | - | - | $636.30 |
| 12 | Revere | Seed | Revere 49-F36 XF | 60.2 | - | - | $632.10 |
| 13 | Asgrow | AG48XF3 | - | 60.0 | - | - | $630.00 |
| 13 | Asgrow | AG49XF4 | - | 60.0 | - | - | $630.00 |
| 15 | Armor | Seed | Armor 46-F15S | 59.3 | - | - | $622.65 |
| 15 | NuTech | Seed | 47N11BE | 59.3 | - | - | $622.65 |
| 17 | NuTech | Seed | 47N04E | 59.1 | - | - | $620.55 |
| 18 | Innvictis | Seed | Solutions A4924XF | 59.0 | - | - | $619.50 |
| 19 | Armor | Seed | Armor 48-E95 | 58.9 | - | - | $618.45 |
| 19 | Golden Harvest | GH5253E3 | Enlist E3 ® | 58.9 | - | - | $618.45 |
| 21 | Golden Harvest | GH4944XFS | XtendFlex ® STS ® | 58.8 | - | - | $617.40 |
| 22 | Xitavo | XO | 4894E | 58.4 | - | - | $613.20 |
| 23 | Stine | 46EG92 | - | 58.1 | - | - | $610.05 |
| 24 | Integra | Fortified | Seed XF4634S | 57.7 | - | - | $605.85 |
| 25 | Asgrow | AG46XF3 | - | 57.5 | - | - | $603.75 |
| 26 | Innvictis | Seed | Solutions A4664XF | 57.3 | - | - | $601.65 |
| 27 | Golden Harvest | GH4775E3S | Enlist E3 ® STS ® | 56.7 | - | - | $595.35 |
| 27 | UniSouth | Genetics | USG 7463XF | 56.7 | - | - | $595.35 |
| 29 | Fortus | 4665ES | - | 56.5 | - | - | $593.25 |
| 29 | Innvictis | Seed | Solutions B4904E | 56.5 | - | - | $593.25 |
| 31 | UniSouth | Genetics | USG 7495XFS | 55.5 | - | - | $582.75 |
| 32 | Xitavo | XO | 4772E | 55.2 | - | - | $579.60 |
| 33 | UniSouth | Genetics | USG 7474XFS | 54.5 | - | - | $572.25 |
| 34 | Golden Harvest | GH4995E3S | Enlist E3 ® STS ® | 53.6 | - | - | $562.80 |
| 35 | Innvictis | Seed | Solutions A4814XF | 53.5 | - | - | $561.75 |
| 36 | Partners | Brand | Seed 4624 E3 S | 53.3 | - | - | $559.65 |
| 37 | Stine | 46EE20 | - | 52.9 | - | - | $555.45 |
| 38 | Golden Harvest | GH4864XFS | XtendFlex ® STS ® | 52.8 | - | - | $554.40 |
| 39 | GDM | Seeds | 46F54S | 52.5 | - | - | $551.25 |
| 40 | APEX | AE4640S | - | 52.0 | - | - | $546.00 |
| 41 | Armor | Seed | Armor 46-E75S | 51.0 | - | - | $535.50 |
Top 5 by Yield: P49Z02E (Pioneer) 64.9, Seed (Innvictis) 64.3, Seeds (GDM) 63.9, Fortified (Integra) 63.3, AG47XF5 (Asgrow) 62.3.