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>
1.3 KiB
1.3 KiB
Soybean yield trial — Mississippi, 2025
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Mississippi (MS)
- Year: 2025
- Plot ID: 2485257
- Cooperator: Mississippi State University
- Planted: 2025-06-06
- Harvested: 2025-10-13
- Population: 140,000 seeds/acre
- Row width: 38"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ms/2025/2485257
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Revere | Seed | Revere 49-F36 | 75.6 | 14.9 | - | $793.80 |
| 2 | Progeny | P | 4947XFS | 74.8 | 13.7 | - | $785.40 |
| 3 | NK | NK47-U1XFS | XtendFlex ® STS ® | 73.1 | 13.4 | - | $767.55 |
| 4 | Innvictis | Seed | Solutions A4755XFS | 69.8 | 13.2 | - | $732.90 |
| 5 | Asgrow | AG49XF4 | - | 69.5 | 11.0 | - | $729.75 |
| 6 | Asgrow | AG43XF5 | - | 69.3 | 12.9 | - | $727.65 |
| 7 | Progeny | P | 4842XFS | 69.1 | 11.3 | - | $725.55 |
| 8 | Revere | Seed | Revere 47-F77 | 67.2 | 11.6 | - | $705.60 |
| 9 | Asgrow | AG48XF5 | - | 67.0 | 11.3 | - | $703.50 |
| 10 | Asgrow | AG45XF3 | - | 61.5 | 12.2 | - | $645.75 |
Top 5 by Yield: Seed (Revere) 75.6, P (Progeny) 74.8, NK47-U1XFS (NK) 73.1, Seed (Innvictis) 69.8, AG49XF4 (Asgrow) 69.5.