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>
2.3 KiB
2.3 KiB
Soybean yield trial — Arkansas, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Arkansas (AR)
- Year: 2024
- Plot ID: 2414648
- Cooperator: C & C Farms of Marianna LLC
- Planted: 2024-04-01
- Harvested: 2024-09-06
- Population: 130,000 seeds/acre
- Row width: 30"
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ar/2024/2414648
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Pioneer | P42A84E | - | 99.6 | 13.7 | 54.8 | $1045.80 |
| 2 | NK | NK44-Q5E3S | Enlist E3 ® STS ® | 98.5 | 13.6 | 55.9 | $1034.25 |
| 3 | Pioneer | P47Z15BE | - | 98.0 | 13.0 | 60.9 | $1029.00 |
| 4 | Asgrow | AG49XF4 | - | 97.7 | 12.7 | 58.1 | $1025.85 |
| 4 | NK | NK49-N7XF | XtendFlex ® | 97.7 | 13.0 | 56.7 | $1025.85 |
| 6 | Pioneer | P45Z75E | - | 96.2 | 13.2 | 55.4 | $1010.10 |
| 7 | NK | NK42-T5XF | XtendFlex ® | 95.8 | 12.9 | 60.2 | $1005.90 |
| 7 | Pioneer | P48A14E | - | 95.8 | 15.3 | 55.9 | $1005.90 |
| 9 | Pioneer | P46A90LX | - | 95.7 | 14.3 | 57.3 | $1004.85 |
| 10 | NK | NK42-A6E3S | Enlist E3 ® STS ® | 95.3 | 13.1 | 56.2 | $1000.65 |
| 11 | Asgrow | AG43XF5 | - | 95.1 | 13.8 | 54.4 | $998.55 |
| 12 | Asgrow | AG45XF3 | - | 94.5 | 13.3 | 55.8 | $992.25 |
| 13 | Asgrow | AG46XF3 | - | 94.2 | 13.4 | 58.3 | $989.10 |
| 14 | Pioneer | P49Z02E | - | 93.6 | 15.9 | 53.9 | $982.61 |
| 15 | Asgrow | AG48XF5 | - | 92.7 | 13.7 | 57.3 | $973.35 |
| 16 | NK | NK43-W1XFS | XtendFlex ® STS ® | 92.3 | 13.6 | 53.6 | $968.41 |
| 17 | Asgrow | AG47XF5 | - | 91.4 | 13.6 | 56.6 | $959.70 |
| 18 | NK | NK48-A8XFS | XtendFlex ® STS ® | 91.2 | 13.9 | 56.8 | $957.60 |
| 19 | Asgrow | AG48XF2 | - | 89.2 | 13.2 | 57.4 | $936.60 |
| 19 | Pioneer | P48Z70BLX | - | 89.2 | 16.5 | 52.2 | $933.39 |
| 21 | Asgrow | AG47XF2 | - | 88.5 | 13.1 | 55.9 | $929.25 |
| 22 | NK | NK47-G5E3S | Enlist E3 ® STS ® | 86.6 | 13.7 | 54.2 | $909.30 |
| 23 | Asgrow | AG44XF4 | - | 86.2 | 13.3 | 55.1 | $905.10 |
| 24 | NK | NK49-C2XFS | XtendFlex ® STS ® | 85.5 | 17.0 | 54.1 | $897.75 |
| 25 | Pioneer | P45A70LX | - | 85.4 | 14.1 | 54.4 | $896.70 |
Top 5 by Yield: P42A84E (Pioneer) 99.6, NK44-Q5E3S (NK) 98.5, P47Z15BE (Pioneer) 98.0, AG49XF4 (Asgrow) 97.7, NK49-N7XF (NK) 97.7.