gh_plot_reports corpus (4,299 plots) + concurrency + 4-GPU pool
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>
This commit is contained in:
@@ -0,0 +1,32 @@
|
||||
# Soybean yield trial — North Carolina, 2025
|
||||
|
||||
- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
|
||||
- **Crop:** Soybean
|
||||
- **State:** North Carolina (NC)
|
||||
- **Year:** 2025
|
||||
- **Plot ID:** 2467234
|
||||
- **Cooperator:** Jeffrey & Brooks Barnes
|
||||
- **Planted:** 2025-06-06
|
||||
- **Harvested:** 2025-10-24
|
||||
- **Population:** 130,000 seeds/acre
|
||||
- **Row width:** 30"
|
||||
- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/nc/2025/2467234
|
||||
|
||||
---
|
||||
## Results (top-down by rank)
|
||||
|
||||
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| 1 | NK | NK52-D6E3 | Enlist E3 ® | 59.0 | 9.1 | 58.0 | $619.50 |
|
||||
| 2 | NK | NK47-G5E3S | Enlist E3 ® STS ® | 57.9 | 8.9 | 57.0 | $607.95 |
|
||||
| 3 | NK | NK49-U9E3S | Enlist E3 ® STS ® | 57.0 | 9.2 | 57.0 | $598.50 |
|
||||
| 4 | NK | NK50-W4E3S | Enlist E3 ® STS ® | 55.5 | 9.2 | 57.0 | $582.75 |
|
||||
| 5 | NK | NK49-C2XFS | XtendFlex ® STS ® | 54.6 | 9.2 | 58.5 | $573.30 |
|
||||
| 6 | NK | NK52-M2XFS | XtendFlex ® STS ® | 53.0 | 9.2 | 58.0 | $556.50 |
|
||||
| 7 | NK | NK47-U1XFS | XtendFlex ® STS ® | 52.6 | 9.2 | 57.5 | $552.30 |
|
||||
| 8 | NK | NK49-N7XF | XtendFlex ® | 50.5 | 9.1 | 57.0 | $530.25 |
|
||||
| 9 | NK | NK58-Y9XF | XtendFlex ® | 46.2 | 8.7 | 58.5 | $485.10 |
|
||||
| 10 | NK | NK54-J9XFS | XtendFlex ® STS ® | 45.3 | 9.0 | 58.0 | $475.65 |
|
||||
| 11 | NK | NK58-B8E3S | Enlist E3 ® STS ® | 40.0 | 9.1 | 58.5 | $420.00 |
|
||||
|
||||
Top 5 by Yield: NK52-D6E3 (NK) 59.0, NK47-G5E3S (NK) 57.9, NK49-U9E3S (NK) 57.0, NK50-W4E3S (NK) 55.5, NK49-C2XFS (NK) 54.6.
|
||||
Reference in New Issue
Block a user