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>
1.8 KiB
1.8 KiB
Silage yield trial — Indiana, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Indiana (IN)
- Year: 2025
- Plot ID: 2467235
- Cooperator: Rediger Farm Inc
- Planted: 2025-06-04
- Harvested: 2025-10-04
- Population: 34,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/in/2025/2467235
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 | E107C1-D | - | 26.8 | 3198.0 | 25733.0 | 228.0 | 1754.0 |
| 2 | Golden Harvest | G13M31-AA | - | 26.4 | 2953.0 | 23361.0 | 198.0 | 1643.0 |
| 3 | Enogen | E114C4-DV-LL | - | 25.6 | 3192.0 | 24518.0 | 244.0 | 1718.0 |
| 4 | Golden Harvest | G12U11-AA | - | 25.0 | 2825.0 | 21176.0 | 175.0 | 1500.0 |
| 5 | Golden Harvest | G10M87-AA | - | 24.0 | 3134.0 | 22558.0 | 211.0 | 1527.0 |
| 6 | Golden Harvest | G14B32-DV | - | 23.7 | 3198.0 | 22758.0 | 236.0 | 1570.0 |
| 7 | Enogen | E117Z7-D | - | 23.4 | 3171.0 | 22242.0 | 227.0 | 1526.0 |
| 8 | Enogen | E102K7-D | - | 23.2 | 3357.0 | 23318.0 | 242.0 | 1549.0 |
| 9 | Golden Harvest | G16Q82-AA | - | 22.9 | 3258.0 | 22412.0 | 245.0 | 1541.0 |
| 10 | Enogen | E112S5-D | - | 22.8 | 3107.0 | 21233.0 | 226.0 | 1486.0 |
| 11 | Golden Harvest | G10U97-V | - | 21.7 | 3246.0 | 21101.0 | 251.0 | 1469.0 |
| 12 | Enogen | E108K4-DV | - | 20.8 | 3279.0 | 20498.0 | 255.0 | 1423.0 |
| 13 | Enogen | E105Z5-D | - | 20.7 | 3309.0 | 20589.0 | 262.0 | 1431.0 |
| 14 | Enogen | E111V7-D | - | 19.5 | 3270.0 | 19145.0 | 257.0 | 1337.0 |
Top 5 by Ton/Acre: E107C1-D (Enogen) 26.8, G13M31-AA (Golden Harvest) 26.4, E114C4-DV-LL (Enogen) 25.6, G12U11-AA (Golden Harvest) 25.0, G10M87-AA (Golden Harvest) 24.0.