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 +1,53 @@
|
||||
# Soybean yield trial — Iowa, 2024
|
||||
|
||||
- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
|
||||
- **Crop:** Soybean
|
||||
- **State:** Iowa (IA)
|
||||
- **Year:** 2024
|
||||
- **Plot ID:** 2419092
|
||||
- **Cooperator:** Farmers Cooperative Society
|
||||
- **Planted:** 2024-04-24
|
||||
- **Harvested:** 2024-10-04
|
||||
- **Population:** 140,000 seeds/acre
|
||||
- **Row width:** 30"
|
||||
- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/ia/2024/2419092
|
||||
|
||||
---
|
||||
## Results (top-down by rank)
|
||||
|
||||
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| 1 | Asgrow | AG26XF4 | - | 76.5 | - | - | $803.25 |
|
||||
| 2 | NK | NK29-Q3XF | XtendFlex ® | 75.9 | - | - | $796.95 |
|
||||
| 3 | NK | NK27-W8XF | XtendFlex ® | 75.6 | - | - | $793.80 |
|
||||
| 4 | Brevant | B263EE | - | 75.3 | - | - | $790.65 |
|
||||
| 5 | Brevant | B243EE | - | 74.4 | - | - | $781.20 |
|
||||
| 6 | NK | NK23-T9XF | XtendFlex ® | 74.2 | - | - | $779.10 |
|
||||
| 7 | NK | NK20-K2XF | XtendFlex ® | 71.2 | - | - | $747.60 |
|
||||
| 8 | Xitavo | XO | 2444E | 69.1 | - | - | $725.55 |
|
||||
| 9 | NK | NK25-C9XF | XtendFlex ® | 68.8 | - | - | $722.40 |
|
||||
| 10 | Brevant | B214EE | - | 67.7 | - | - | $710.85 |
|
||||
| 10 | Brevant | B224EE | - | 67.7 | - | - | $710.85 |
|
||||
| 12 | Alloy | A21E34 | - | 67.3 | - | - | $706.65 |
|
||||
| 12 | NK | NK21-C2E3 | Enlist E3 ® | 67.3 | - | - | $706.65 |
|
||||
| 14 | Brevant | B194EE | - | 66.7 | - | - | $700.35 |
|
||||
| 15 | Asgrow | AG23XF3 | - | 66.0 | - | - | $693.00 |
|
||||
| 16 | Xitavo | XO | 2735E | 65.1 | - | - | $683.55 |
|
||||
| 17 | NK | NK17-M2XF | XtendFlex ® | 64.5 | - | - | $677.25 |
|
||||
| 18 | Brevant | B202EE | - | 62.3 | - | - | $654.15 |
|
||||
| 19 | Alloy | A23E33 | - | 62.2 | - | - | $653.10 |
|
||||
| 20 | Xitavo | XO | 2181E | 62.0 | - | - | $651.00 |
|
||||
| 20 | Brevant | B144EE | - | 62.0 | - | - | $651.00 |
|
||||
| 22 | NK | NK19-T8E3S | Enlist E3 ® STS ® | 61.8 | - | - | $648.90 |
|
||||
| 22 | Xitavo | XO | 1632E | 61.8 | - | - | $648.90 |
|
||||
| 24 | Asgrow | AG22XF5 | - | 61.6 | - | - | $646.80 |
|
||||
| 25 | Xitavo | XO | 2625E | 61.3 | - | - | $643.65 |
|
||||
| 26 | NK | NK18-R4E3 | Enlist E3 ® | 60.6 | - | - | $636.30 |
|
||||
| 27 | Alloy | A19E33 | - | 58.7 | - | - | $616.35 |
|
||||
| 28 | NK | NK23-P1E3 | Enlist E3 ® | 57.8 | - | - | $606.90 |
|
||||
| 28 | Xitavo | XO | 1545E | 57.8 | - | - | $606.90 |
|
||||
| 30 | Xitavo | XO | 2305E | 57.3 | - | - | $601.65 |
|
||||
| 31 | Asgrow | AG24XF1 | - | 56.8 | - | - | $596.40 |
|
||||
| 32 | Asgrow | AG19XF3 | - | 53.9 | - | - | $565.95 |
|
||||
|
||||
Top 5 by Yield: AG26XF4 (Asgrow) 76.5, NK29-Q3XF (NK) 75.9, NK27-W8XF (NK) 75.6, B263EE (Brevant) 75.3, B243EE (Brevant) 74.4.
|
||||
Reference in New Issue
Block a user