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 — South Dakota, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: South Dakota (SD)
- Year: 2024
- Plot ID: 2419040
- Cooperator: Lake Area Ag
- Planted: 2024-05-20
- Harvested: 2024-09-29
- Population: 130,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/sd/2024/2419040
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | LG Seeds | LGS1385XF | - | 61.9 | 9.9 | 59.0 | $649.95 |
| 2 | Jacobsen | J1720E3 | - | 60.0 | 12.1 | 57.0 | $630.00 |
| 3 | Stine | 13EH62 | - | 59.5 | 9.4 | 58.7 | $624.75 |
| 4 | Golden Harvest | GH0815E3 | Enlist E3 ® | 59.3 | 8.5 | 58.4 | $622.65 |
| 5 | Golden Harvest | GH1555XF | XtendFlex ® | 59.0 | 12.7 | 56.9 | $619.50 |
| 6 | LG Seeds | LGS1585XF | - | 58.7 | 12.9 | 56.9 | $616.35 |
| 7 | Golden Harvest | GH1534E3S | Enlist E3 ® STS ® | 58.1 | 10.3 | 58.4 | $610.05 |
| 8 | Golden Harvest | GH1762XF | XtendFlex ® | 57.9 | 13.0 | 55.7 | $607.95 |
| 9 | Jacobsen | J1520E3 | - | 57.4 | 11.4 | 56.8 | $602.70 |
| 10 | Golden Harvest | GH1495E3 | Enlist E3 ® | 55.5 | 9.5 | 58.6 | $582.75 |
| 11 | LG Seeds | LGS1660E3 | - | 54.9 | 11.7 | 56.5 | $576.45 |
| 12 | Golden Harvest | GH1194E3 | Enlist E3 ® | 54.4 | 8.8 | 57.2 | $571.20 |
| 13 | Jacobsen | J1643E3 | - | 53.3 | 11.8 | 55.8 | $559.65 |
| 14 | Stine | 14EE21 | - | 53.2 | 10.8 | 57.9 | $558.60 |
| 15 | LG Seeds | LGS0830E3 | - | 51.9 | 9.0 | 57.5 | $544.95 |
| 15 | Jacobsen | J1250E3 | - | 51.9 | 9.0 | 58.9 | $544.95 |
| 17 | Stine | 12EB32 | - | 51.8 | 9.1 | 58.1 | $543.90 |
| 18 | LG Seeds | LGS1043E3 | - | 51.4 | 8.5 | 59.1 | $539.70 |
| 19 | Golden Harvest | GH1124XF | XtendFlex ® | 51.2 | 8.8 | 57.2 | $537.60 |
| 19 | LG Seeds | LGS1206E3 | - | 51.2 | 8.9 | 58.0 | $537.60 |
| 21 | Stine | 15EH62 | - | 50.1 | 10.8 | 57.2 | $526.05 |
| 22 | LG Seeds | LGS0701XF | - | 49.7 | 10.1 | 57.7 | $521.85 |
| 23 | LG Seeds | LGS1551E3 | - | 48.8 | 10.3 | 56.9 | $512.40 |
| 24 | LG Seeds | LGS0988XF | - | 48.7 | 8.5 | 57.5 | $511.35 |
Top 5 by Yield: LGS1385XF (LG Seeds) 61.9, J1720E3 (Jacobsen) 60.0, 13EH62 (Stine) 59.5, GH0815E3 (Golden Harvest) 59.3, GH1555XF (Golden Harvest) 59.0.