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>
2026-05-25 16:46:35 -04:00
parent cfa27d0bca
commit 0e625553e5
8602 changed files with 1013877 additions and 32 deletions
@@ -0,0 +1,49 @@
+# Soybean yield trial — Wisconsin, 2024
+
+- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
+- **Crop:** Soybean
+- **State:** Wisconsin (WI)
+- **Year:** 2024
+- **Plot ID:** 2465729
+- **Cooperator:** Matott, Justin
+- **Planted:** 2024-05-30
+- **Harvested:** 2024-10-06
+- **Population:** 150,000 seeds/acre
+- **Row width:** 30"
+- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/wi/2024/2465729
+
+---
+## Results (top-down by rank)
+
+| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
+|---|---|---|---|---|---|---|---|
+| 1 | Pioneer | P16Z42E | - | 57.9 | 10.0 | 56.4 | $607.95 |
+| 2 | Pioneer | P05Z60E | - | 55.0 | 8.6 | 57.6 | $577.50 |
+| 3 | Pioneer | P04A98E | - | 53.9 | 8.5 | 54.0 | $565.95 |
+| 4 | Pioneer | P13Z28E | - | 52.6 | 9.2 | 55.8 | $552.30 |
+| 5 | Pioneer | P15Z80E | - | 52.5 | 9.5 | 54.7 | $551.25 |
+| 6 | Connect | CT1223E | - | 52.0 | 9.3 | 55.9 | $546.00 |
+| 7 | Connect | CT1025E | - | 51.2 | 9.2 | 56.2 | $537.60 |
+| 8 | Pioneer | P09Z79E | - | 51.1 | 9.2 | 54.2 | $536.55 |
+| 9 | Pioneer | P06A38E | - | 50.9 | 8.5 | 58.0 | $534.45 |
+| 10 | Pioneer | P08A44E | - | 50.6 | 9.1 | 55.4 | $531.30 |
+| 11 | Connect | CT1624E | - | 49.8 | 9.5 | 55.8 | $522.90 |
+| 11 | Dairyland | Seed | DSR-1345E | 49.8 | 9.3 | 55.2 | $522.90 |
+| 13 | Connect | CT1325E | - | 49.7 | 9.2 | 55.0 | $521.85 |
+| 14 | Dairyland | Seed | DSR-1150E | 49.0 | 9.0 | 54.7 | $514.50 |
+| 15 | Pioneer | P11Z72E | - | 48.1 | 9.4 | 54.4 | $505.05 |
+| 16 | NK | NK11-A4E3 | Enlist E3 ® | 47.7 | 8.9 | 56.3 | $500.85 |
+| 17 | NK | NK08-Z4E3 | Enlist E3 ® | 47.3 | 9.1 | 54.9 | $496.65 |
+| 18 | Pioneer | P04Z49E | - | 46.8 | 8.4 | 53.6 | $491.03 |
+| 19 | Pioneer | P06Z90E | - | 46.7 | 8.9 | 55.7 | $490.35 |
+| 20 | Connect | CT1525E | - | 45.8 | 9.7 | 56.5 | $480.90 |
+| 21 | Xitavo | XO | 1095E | 45.1 | 9.3 | 55.0 | $473.55 |
+| 22 | Connect | CT0923E | - | 45.0 | 9.2 | 54.0 | $472.50 |
+| 23 | Connect | CT1425E | - | 44.7 | 9.5 | 55.1 | $469.35 |
+| 24 | Xitavo | XO | 1372E | 44.3 | 9.2 | 55.7 | $465.15 |
+| 25 | Xitavo | XO | 1225E | 43.2 | 9.2 | 56.1 | $453.60 |
+| 26 | Pioneer | P14Z16E | - | 40.9 | 9.7 | 54.8 | $429.45 |
+| 27 | Xitavo | XO | 0993E | 39.3 | 9.1 | 53.2 | $412.02 |
+| 28 | NK | NK09-H7E3 | Enlist E3 ® | 33.9 | 8.9 | 57.5 | $355.95 |
+
+Top 5 by Yield: P16Z42E (Pioneer) 57.9, P05Z60E (Pioneer) 55.0, P04A98E (Pioneer) 53.9, P13Z28E (Pioneer) 52.6, P15Z80E (Pioneer) 52.5.