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 Permalink 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: 2420193
Cooperator: University of Missouri - Rock Port
Planted: 2024-05-30
Harvested: 2024-10-10
URL: https://www.goldenharvestseeds.com/soybean/plot-report/mo/2024/2420193

Results (top-down by rank)

Rank	Brand	Product	Traits	Yield	%MST	Test Weight	Gross Revenue
1	Pioneer	P38A28E	-	101.5	-	-	$1065.75
2	NuTech	Seed	38N05E	101.4	-	-	$1064.70
3	NK	NK36-Q6E3S	Enlist E3 ® STS ®	99.9	-	-	$1048.95
3	AgVenture	AV36B2E	-	99.9	-	-	$1048.95
5	NK	NK37-C1E3	Enlist E3 ®	99.8	-	-	$1047.90
6	Benson	Hill	BH35A231	98.3	-	-	$1032.15
7	Xitavo	XO	3375E	98.2	-	-	$1031.10
7	NuTech	Seed	34N02E	98.2	-	-	$1031.10
9	Brevant	B364EE	-	97.9	-	-	$1027.95
10	DonMario	Seeds	DM38E54	97.4	-	-	$1022.70
11	Benson	Hill	BH39A232	97.0	-	-	$1018.50
12	Asgrow	AG36XF4	-	96.9	-	-	$1017.45
13	Xitavo	XO	3705E	96.1	-	-	$1009.05
14	DonMario	Seeds	DM32F74	95.9	-	-	$1006.95
15	Blue	River	Organic Seed 42D40	95.3	-	-	$1000.65
16	NuTech	Seed	36N06E	94.6	-	-	$993.30
17	Channel	3823RXF	-	94.0	-	-	$987.00
18	Asgrow	AG39XF3	-	93.9	-	-	$985.95
19	AgVenture	AV38A1E	-	93.3	-	-	$979.65
20	APEX	AE3550S	-	92.7	-	-	$973.35
20	NuTech	Seed	32N04E	92.7	-	-	$973.35
22	APEX	AE3340	-	92.2	-	-	$968.10
23	NuTech	Seed	37N03E	92.1	-	-	$967.05
24	DonMario	Seeds	DM36E94	91.7	-	-	$962.85
25	AgVenture	AV39B2E	-	91.1	-	-	$956.55
26	Benson	Hill	BH37U221	91.0	-	-	$955.50
27	APEX	AE3850	-	90.4	-	-	$949.20
28	Pioneer	P34A98E	-	89.8	-	-	$942.90
29	Pioneer	P37A18E	-	89.3	-	-	$937.65
30	Blue	River	Organic Seed 3418N	89.0	-	-	$934.50
31	NuTech	Seed	39N08E	87.3	-	-	$916.65
31	Benson	Hill	BX37C755	87.3	-	-	$916.65
33	Xitavo	XO	3855E	87.0	-	-	$913.50
34	APEX	AE3540S	-	86.9	-	-	$912.45
35	Benson	Hill	BH37Q218	86.7	-	-	$910.35
36	Asgrow	AG38XF1	-	86.1	-	-	$904.05
37	Asgrow	AG37XF1	-	86.0	-	-	$903.00
38	DonMario	Seeds	DM36F84S	85.3	-	-	$895.65
39	Xitavo	XO	3655E	84.6	-	-	$888.30
40	NK	NK39-J2E3	Enlist E3 ®	84.3	-	-	$885.15
41	Benson	Hill	BH35A233	84.2	-	-	$884.10
41	MCIA	39C09	-	84.2	-	-	$884.10
43	Blue	River	Organic Seed 39R4	84.0	-	-	$882.00
44	Xitavo	XO	3483E	83.8	-	-	$879.90
45	Benson	Hill	BH37U206	81.7	-	-	$857.85
46	NuTech	Seed	35N05E	78.8	-	-	$827.40
47	Brevant	B394EE	-	78.2	-	-	$821.10
48	Benson	Hill	BH37U205	77.7	-	-	$815.85
49	Benson	Hill	BH37U222	76.5	-	-	$803.25
50	Benson	Hill	BX38F550	75.4	-	-	$791.70

Top 5 by Yield: P38A28E (Pioneer) 101.5, Seed (NuTech) 101.4, NK36-Q6E3S (NK) 99.9, AV36B2E (AgVenture) 99.9, NK37-C1E3 (NK) 99.8.

3.5 KiB Raw Permalink Blame History

Soybean yield trial — Missouri, 2024

Results (top-down by rank)

3.5 KiB

Raw Permalink Blame History