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>
2.6 KiB
2.6 KiB
Silage yield trial — Pennsylvania, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Silage
- State: Pennsylvania (PA)
- Year: 2024
- Plot ID: 2465799
- Cooperator: PDMP - West Grove, PA (late season)
- Planted: 2024-05-08
- Harvested: 2024-09-04
- URL: https://www.goldenharvestseeds.com/silage/plot-report/pa/2024/2465799
Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Mid-Atlantic | Seeds | MA6120PCE | 34.3 | - | - | - | - |
| 2 | Red | Tail | RT 64T39 | 32.2 | - | - | - | - |
| 3 | Seed | Consultants | SC1185V | 31.9 | - | - | - | - |
| 4 | Mid-Atlantic | Seeds | MA5144D | 31.7 | - | - | - | - |
| 5 | DEKALB | DKC115-81 | - | 31.4 | - | - | - | - |
| 6 | Mid-Atlantic | Seeds | MA6131PCE | 31.3 | - | - | - | - |
| 7 | Mid-Atlantic | Seeds | MA5124DV | 31.2 | - | - | - | - |
| 7 | Mid-Atlantic | Seeds | MA6153PCE | 31.2 | - | - | - | - |
| 9 | Revere | Seed | Revere 1839 TC | 31.0 | - | - | - | - |
| 10 | Channel | 212-40VT4P | - | 30.9 | - | - | - | - |
| 10 | Chemgro | 7539D4Z | - | 30.9 | - | - | - | - |
| 10 | Seed | Consultants | SC1154AM | 30.9 | - | - | - | - |
| 13 | Revere | Seed | Revere 114-P35 VT2P | 30.8 | - | - | - | - |
| 14 | Revere | Seed | Experimental | 30.7 | - | - | - | - |
| 14 | Revere | Seed | Revere 1307 TC | 30.7 | - | - | - | - |
| 16 | Seed | Consultants | SC1135PCE | 29.9 | - | - | - | - |
| 17 | Chemgro | 7259DVZ | - | 29.8 | - | - | - | - |
| 18 | Seed | Consultants | SC1112AM | 29.6 | - | - | - | - |
| 19 | Channel | 211-42SSP | - | 29.5 | - | - | - | - |
| 20 | Channel | 213-99SSP | - | 29.4 | - | - | - | - |
| 21 | Revere | Seed | Revere 1627 TC | 29.1 | - | - | - | - |
| 22 | DEKALB | DKC67-66 | - | 28.7 | - | - | - | - |
| 23 | Mid-Atlantic | Seeds | MA5137DV | 28.5 | - | - | - | - |
| 23 | Channel | 215-15SSP | - | 28.5 | - | - | - | - |
| 25 | DEKALB | DKC64-44 | - | 28.0 | - | - | - | - |
| 25 | Chemgro | 7554PCE | - | 28.0 | - | - | - | - |
| 27 | NK | NK1480-DV | - | 27.8 | - | - | - | - |
| 28 | Enogen | E117Z7-D | - | 27.7 | - | - | - | - |
| 29 | Mid-Atlantic | Seeds | MA7152HD | 27.4 | - | - | - | - |
| 30 | DEKALB | DKC61-80 | - | 27.1 | - | - | - | - |
| 31 | DEKALB | DKC113-62 | - | 26.6 | - | - | - | - |
| 32 | NK | NK1307-DV | - | 25.8 | - | - | - | - |
| 33 | Red | Tail | RT 61T99 | 25.7 | - | - | - | - |
Top 5 by Ton/Acre: Seeds (Mid-Atlantic) 34.3, Tail (Red) 32.2, Consultants (Seed) 31.9, Seeds (Mid-Atlantic) 31.7, DKC115-81 (DEKALB) 31.4.