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>
2.9 KiB
2.9 KiB
Soybean yield trial — Michigan, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Michigan (MI)
- Year: 2024
- Plot ID: 2452440
- Cooperator: Michigan State University - Allegan Cnty Early
- Planted: 2024-05-18
- Harvested: 2024-10-06
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/mi/2024/2452440
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Renk | Seed | G1980E | 65.8 | - | - | $690.90 |
| 2 | D.F. | Seeds | DF 3225 N E3 | 64.5 | - | - | $677.25 |
| 2 | Xitavo | XO | 2075E | 64.5 | - | - | $677.25 |
| 4 | NK | NK14-U5E3 | Enlist E3 ® | 63.2 | - | - | $663.60 |
| 5 | Golden Harvest | GH2292E3 | Enlist E3 ® | 62.4 | - | - | $655.20 |
| 6 | NK | NK21-C2E3 | Enlist E3 ® | 61.7 | - | - | $647.85 |
| 7 | DonMario | Seeds | DM22E64 | 61.4 | - | - | $644.70 |
| 8 | NK | NK18-R4E3 | Enlist E3 ® | 60.6 | - | - | $636.30 |
| 9 | NK | NK19-T8E3S | Enlist E3 ® STS ® | 60.2 | - | - | $632.10 |
| 10 | D.F. | Seeds | DF 3211 N E3 | 60.1 | - | - | $631.05 |
| 11 | Renk | Seed | G2180E | 59.1 | - | - | $620.55 |
| 12 | NK | NK16-Z6E3 | Enlist E3 ® | 58.8 | - | - | $617.40 |
| 12 | Renk | Seed | G2150E | 58.8 | - | - | $617.40 |
| 14 | Loyal | Brand | L2130E | 58.4 | - | - | $613.20 |
| 15 | Golden Harvest | GH1973E3S | Enlist E3 ® STS ® | 58.3 | - | - | $612.15 |
| 16 | D.F. | Seeds | DF 3144 N E3 | 58.2 | - | - | $611.10 |
| 16 | Michigan | State | E21409-2GT | 58.2 | - | - | $611.10 |
| 18 | Renk | Seed | RS194NXF | 58.0 | - | - | $609.00 |
| 19 | D.F. | Seeds | DF 3115 N E3 | 57.5 | - | - | $603.75 |
| 20 | Renk | Seed | G1950E | 56.2 | - | - | $590.10 |
| 21 | D.F. | Seeds | DF 3125 N E3 | 56.0 | - | - | $588.00 |
| 21 | D.F. | Seeds | DF 3165 N E3 | 56.0 | - | - | $588.00 |
| 23 | D.F. | Seeds | DF 3114 N E3 | 55.3 | - | - | $580.65 |
| 23 | M | & | W Seeds 18E89 | 55.3 | - | - | $580.65 |
| 23 | M | & | W Seeds 20E71 | 55.3 | - | - | $580.65 |
| 26 | Loyal | Brand | L1860E | 55.2 | - | - | $579.60 |
| 27 | Xitavo | XO | 1545E | 54.9 | - | - | $576.45 |
| 28 | Xitavo | XO | 1404E | 54.7 | - | - | $574.35 |
| 29 | Xitavo | XO | 2181E | 54.5 | - | - | $572.25 |
| 30 | D.F. | Seeds | DF 3135 N E3 | 53.8 | - | - | $564.90 |
| 31 | Michigan | State | E21366GTHO | 52.9 | - | - | $555.45 |
| 32 | Loyal | Brand | L2160E | 51.9 | - | - | $544.95 |
| 33 | D.F. | Seeds | DF 3194 N E3 | 51.2 | - | - | $537.60 |
| 33 | Golden Harvest | GH1614E3 | Enlist E3 ® | 51.2 | - | - | $537.60 |
| 35 | D.F. | Seeds | DF 3105 N E3 | 49.6 | - | - | $520.80 |
| 36 | Xitavo | XO | 1971E | 49.2 | - | - | $516.60 |
| 37 | Golden Harvest | GH1922E3 | Enlist E3 ® | 47.7 | - | - | $500.85 |
Top 5 by Yield: Seed (Renk) 65.8, Seeds (D.F.) 64.5, XO (Xitavo) 64.5, NK14-U5E3 (NK) 63.2, GH2292E3 (Golden Harvest) 62.4.