Files

T

justin 0e625553e5 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>

2026-05-25 16:46:35 -04:00

3.5 KiB

Raw Blame History

Soybean yield trial — Missouri, 2024

Source: Golden Harvest plot report (cross-vendor head-to-head)
Crop: Soybean
State: Missouri (MO)
Year: 2024
Plot ID: 2420191
Cooperator: University of Missouri - Canton
Planted: 2024-05-10
Harvested: 2024-10-03
URL: https://www.goldenharvestseeds.com/soybean/plot-report/mo/2024/2420191

Results (top-down by rank)

Rank	Brand	Product	Traits	Yield	%MST	Test Weight	Gross Revenue
1	APEX	AE3550S	-	90.6	-	-	$951.30
2	NuTech	Seed	38N05E	89.8	-	-	$942.90
3	NuTech	Seed	37N03E	88.3	-	-	$927.15
4	NK	NK36-Q6E3S	Enlist E3 ® STS ®	87.9	-	-	$922.95
5	AgVenture	AV36B2E	-	86.8	-	-	$911.40
6	Pioneer	P37A18E	-	86.7	-	-	$910.35
7	Asgrow	AG38XF1	-	86.6	-	-	$909.30
8	Asgrow	AG39XF3	-	85.9	-	-	$901.95
9	NuTech	Seed	36N06E	85.3	-	-	$895.65
10	Blue	River	Organic Seed 39R4	84.9	-	-	$891.45
11	Benson	Hill	BH39A232	84.3	-	-	$885.15
12	AgVenture	AV39B2E	-	84.1	-	-	$883.05
13	Asgrow	AG37XF1	-	84.0	-	-	$882.00
14	DonMario	Seeds	DM38E54	83.9	-	-	$880.95
14	NK	NK39-J2E3	Enlist E3 ®	83.9	-	-	$880.95
16	DonMario	Seeds	DM32F74	82.6	-	-	$867.30
17	Xitavo	XO	3655E	82.4	-	-	$865.20
18	Benson	Hill	BH35A233	82.1	-	-	$862.05
19	DonMario	Seeds	DM36F84S	81.1	-	-	$851.55
20	APEX	AE3540S	-	80.6	-	-	$846.30
21	NuTech	Seed	35N05E	80.1	-	-	$841.05
22	Xitavo	XO	3855E	80.0	-	-	$840.00
23	Benson	Hill	BX38F550	79.7	-	-	$836.85
24	APEX	AE3850	-	79.2	-	-	$831.60
25	Channel	3823RXF	-	79.1	-	-	$830.55
26	Pioneer	P38A28E	-	78.6	-	-	$825.30
27	DonMario	Seeds	DM36E94	78.0	-	-	$819.00
28	Benson	Hill	BH35A231	77.9	-	-	$817.95
28	Xitavo	XO	3705E	77.9	-	-	$817.95
30	MCIA	39C09	-	77.5	-	-	$813.75
31	NK	NK37-C1E3	Enlist E3 ®	77.4	-	-	$812.70
31	Xitavo	XO	3483E	77.4	-	-	$812.70
33	NuTech	Seed	39N08E	76.6	-	-	$804.30
34	Pioneer	P34A98E	-	76.4	-	-	$802.20
35	Brevant	B394EE	-	76.1	-	-	$799.05
36	Benson	Hill	BH37U206	75.8	-	-	$795.90
37	Asgrow	AG36XF4	-	75.3	-	-	$790.65
38	Benson	Hill	BH37U222	75.2	-	-	$789.60
38	Blue	River	Organic Seed 42D40	75.2	-	-	$789.60
40	Xitavo	XO	3375E	74.8	-	-	$785.40
41	Benson	Hill	BH37U221	74.4	-	-	$781.20
42	Brevant	B364EE	-	73.8	-	-	$774.90
42	Blue	River	Organic Seed 3418N	73.8	-	-	$774.90
44	Benson	Hill	BH37U205	71.7	-	-	$752.85
45	Benson	Hill	BH37Q218	71.6	-	-	$751.80
46	NuTech	Seed	34N02E	71.2	-	-	$747.60
47	APEX	AE3340	-	71.0	-	-	$745.50
48	AgVenture	AV38A1E	-	70.5	-	-	$740.25
49	Benson	Hill	BX37C755	69.2	-	-	$726.60
50	NuTech	Seed	32N04E	65.4	-	-	$686.70

Top 5 by Yield: AE3550S (APEX) 90.6, Seed (NuTech) 89.8, Seed (NuTech) 88.3, NK36-Q6E3S (NK) 87.9, AV36B2E (AgVenture) 86.8.

3.5 KiB Raw Blame History

Soybean yield trial — Missouri, 2024

Results (top-down by rank)

3.5 KiB

Raw Blame History