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 — Colorado, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Colorado (CO)
- Year: 2024
- Plot ID: 2414852
- Cooperator: Chs Inc
- Planted: 2024-05-10
- Harvested: 2024-09-11
- Population: 25,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/silage/plot-report/co/2024/2414852
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 | E112S5-D | - | 38.9 | 3057.0 | 35721.0 | 218.0 | 2505.0 |
| 2 | NK | NK1082-DV | - | 38.8 | 2967.0 | 34565.0 | 220.0 | 2506.0 |
| 3 | Enogen | E114C4-DV-LL | - | 36.9 | 3022.0 | 33452.0 | 212.0 | 2353.0 |
| 4 | Enogen | E110F4-D | - | 36.4 | 3469.0 | 37880.0 | 268.0 | 2535.0 |
| 5 | Enogen | E117Z7-D | - | 33.8 | 2661.0 | 27013.0 | 156.0 | 1966.0 |
| 6 | Enogen | E114Z4-D | - | 33.5 | 2862.0 | 28790.0 | 181.0 | 2033.0 |
| 7 | NK | NK0821-D | - | 32.6 | 3099.0 | 30337.0 | 201.0 | 2044.0 |
| 8 | Enogen | E100A3-D | - | 32.1 | 3371.0 | 32429.0 | 294.0 | 2328.0 |
| 9 | NK | NK0880-V | - | 31.9 | 2991.0 | 28636.0 | 207.0 | 2016.0 |
| 10 | NK | NK1386-VZ | - | 31.1 | 3320.0 | 31024.0 | 241.0 | 2081.0 |
| 11 | NK | NK1307-DV | - | 30.8 | 2741.0 | 25368.0 | 163.0 | 1829.0 |
| 12 | Enogen | E107C1-D | - | 29.7 | 3090.0 | 27563.0 | 216.0 | 1908.0 |
| 13 | Enogen | E105Z5-D | - | 28.6 | 3273.0 | 28092.0 | 256.0 | 1955.0 |
| 14 | Enogen | E094Z4-D | - | 28.2 | 3245.0 | 27442.0 | 260.0 | 1940.0 |
| 15 | NK | NK1056-V | - | 26.2 | 2938.0 | 23135.0 | 198.0 | 1636.0 |
Top 5 by Ton/Acre: E112S5-D (Enogen) 38.9, NK1082-DV (NK) 38.8, E114C4-DV-LL (Enogen) 36.9, E110F4-D (Enogen) 36.4, E117Z7-D (Enogen) 33.8.