gh_plot_reports corpus (4,299 plots) + concurrency + 4-GPU pool
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>
This commit is contained in:
@@ -0,0 +1,45 @@
|
||||
# Soybean yield trial — Wisconsin, 2025
|
||||
|
||||
- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
|
||||
- **Crop:** Soybean
|
||||
- **State:** Wisconsin (WI)
|
||||
- **Year:** 2025
|
||||
- **Plot ID:** 2469466
|
||||
- **Cooperator:** Lime Lake Farms
|
||||
- **Planted:** 2025-05-10
|
||||
- **Harvested:** 2025-10-16
|
||||
- **Population:** 120,000 seeds/acre
|
||||
- **Row width:** 30"
|
||||
- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/wi/2025/2469466
|
||||
|
||||
---
|
||||
## Results (top-down by rank)
|
||||
|
||||
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| 1 | Pioneer | P22Z02E | - | 76.5 | 10.7 | - | $803.25 |
|
||||
| 2 | Pioneer | P16Z25E | - | 73.2 | 10.4 | 59.6 | $768.60 |
|
||||
| 3 | Pioneer | P19Z52E | - | 68.6 | 10.6 | - | $720.30 |
|
||||
| 4 | Pioneer | P16Z42E | - | 66.8 | 10.5 | 60.3 | $701.40 |
|
||||
| 5 | Ed | Seed | E1232 | 65.7 | 10.2 | - | $689.85 |
|
||||
| 6 | NK | NK17-H1E3 | Enlist E3 ® | 64.8 | 11.2 | 58.1 | $680.40 |
|
||||
| 7 | Pioneer | P21Z71E | - | 64.4 | 10.0 | - | $676.20 |
|
||||
| 8 | Ed | Seed | E1232 | 64.2 | 10.6 | 59.6 | $674.10 |
|
||||
| 9 | Pioneer | P17Z39E | - | 64.0 | 10.6 | 59.1 | $672.00 |
|
||||
| 10 | Golden Harvest | GH1194E3 | Enlist E3 ® | 63.6 | 11.5 | 59.3 | $667.80 |
|
||||
| 11 | Golden Harvest | GH2315E3 | Enlist E3 ® | 62.9 | 11.4 | 58.6 | $660.45 |
|
||||
| 12 | Ed | Seed | Experimental | 62.7 | 10.9 | - | $658.35 |
|
||||
| 13 | Ed | Seed | Experimental | 62.3 | 11.0 | - | $654.15 |
|
||||
| 14 | Golden Harvest | GH1614E3 | Enlist E3 ® | 61.6 | 11.2 | 58.7 | $646.80 |
|
||||
| 15 | Golden Harvest | GH1776E3 | Enlist E3 ® | 61.3 | 11.5 | 58.2 | $643.65 |
|
||||
| 16 | Ed | Seed | E1532 | 61.2 | 11.2 | 60.4 | $642.60 |
|
||||
| 17 | Ed | Seed | Experimental | 60.8 | 10.8 | - | $638.40 |
|
||||
| 18 | Ed | Seed | E1831 | 60.2 | 11.0 | 60.3 | $632.10 |
|
||||
| 19 | NK | NK21-C2E3 | Enlist E3 ® | 60.1 | 10.8 | 60.0 | $631.05 |
|
||||
| 20 | Ed | Seed | E2432S | 59.9 | 11.1 | 60.5 | $628.95 |
|
||||
| 21 | Golden Harvest | GH2292E3 | Enlist E3 ® | 59.3 | 13.1 | 58.4 | $622.65 |
|
||||
| 22 | Golden Harvest | GH1495E3 | Enlist E3 ® | 59.0 | 11.1 | 60.6 | $619.50 |
|
||||
| 23 | Golden Harvest | GH1973E3S | Enlist E3 ® STS ® | 58.4 | 11.3 | 61.0 | $613.20 |
|
||||
| 24 | Ed | Seed | E1232 | 54.6 | 11.4 | 59.5 | $573.30 |
|
||||
|
||||
Top 5 by Yield: P22Z02E (Pioneer) 76.5, P16Z25E (Pioneer) 73.2, P19Z52E (Pioneer) 68.6, P16Z42E (Pioneer) 66.8, Seed (Ed) 65.7.
|
||||
Reference in New Issue
Block a user