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 +1,37 @@
+# Silage yield trial — Minnesota, 2024
+
+- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
+- **Crop:** Silage
+- **State:** Minnesota (MN)
+- **Year:** 2024
+- **Plot ID:** 2420269
+- **Cooperator:** Dobis Farms LLC
+- **Planted:** 2024-05-10
+- **Harvested:** 2024-09-13
+- **Population:** 32,000 seeds/acre
+- **Row width:** 30"
+- **URL:** https://www.goldenharvestseeds.com/silage/plot-report/mn/2024/2420269
+
+---
+## Results (top-down by rank)
+
+| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
+|---|---|---|---|---|---|---|---|---|
+| 1 | Enogen | E110F4-D | - | 28.8 | 3215.0 | 27778.0 | 222.0 | 1864.0 |
+| 2 | Enogen | E114C4-DV-LL | - | 28.2 | 2983.0 | 25236.0 | 211.0 | 1795.0 |
+| 3 | Enogen | E112S5-D | - | 27.9 | 3201.0 | 26792.0 | 221.0 | 1803.0 |
+| 4 | Enogen | E107C1-D | - | 27.5 | 2980.0 | 24585.0 | 214.0 | 1759.0 |
+| 4 | Enogen | E105Z5-D | - | 27.5 | 3139.0 | 25897.0 | 222.0 | 1781.0 |
+| 6 | Enogen | E111V7-D | - | 25.6 | 3174.0 | 24376.0 | 244.0 | 1716.0 |
+| 7 | Golden Harvest | G02K39-D | - | 25.1 | 3643.0 | 27432.0 | 274.0 | 1765.0 |
+| 8 | Golden Harvest | G05U86-DV | - | 24.4 | 3575.0 | 26169.0 | 269.0 | 1703.0 |
+| 9 | Enogen | E092W5-D | - | 24.2 | 3361.0 | 24401.0 | 240.0 | 1613.0 |
+| 10 | Enogen | E105T1-3000GT | - | 23.9 | 3251.0 | 23310.0 | 230.0 | 1569.0 |
+| 11 | Enogen | E095D3-D | - | 23.5 | 3094.0 | 21813.0 | 220.0 | 1518.0 |
+| 12 | Enogen | E094Z4-D | - | 22.7 | 3386.0 | 23059.0 | 274.0 | 1596.0 |
+| 13 | Golden Harvest | G98U62-DV | - | 21.3 | 3327.0 | 21260.0 | 241.0 | 1421.0 |
+| 14 | Golden Harvest | G03U08-D | - | 20.7 | 3566.0 | 22145.0 | 279.0 | 1468.0 |
+| 15 | Enogen | E100A3-D | - | 20.3 | 3400.0 | 20706.0 | 250.0 | 1374.0 |
+| 16 | Enogen | E085Z5-D | - | 18.6 | 3189.0 | 17795.0 | 228.0 | 1216.0 |
+
+Top 5 by Ton/Acre: E110F4-D (Enogen) 28.8, E114C4-DV-LL (Enogen) 28.2, E112S5-D (Enogen) 27.9, E107C1-D (Enogen) 27.5, E105Z5-D (Enogen) 27.5.