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

3.6 KiB

Raw Blame History

Soybean yield trial — Wisconsin, 2024

Source: Golden Harvest plot report (cross-vendor head-to-head)
Crop: Soybean
State: Wisconsin (WI)
Year: 2024
Plot ID: 2440897
Cooperator: University of Wisconsin - Seymour
Planted: 2024-05-14
Harvested: 2024-10-03
URL: https://www.goldenharvestseeds.com/soybean/plot-report/wi/2024/2440897

Results (top-down by rank)

Rank	Brand	Product	Traits	Yield	%MST	Test Weight	Gross Revenue
1	Loyal	Brand	L1670E	76.0	-	-	$798.00
2	Genesis	G1760E	-	75.0	-	-	$787.50
2	Golden Harvest	GH1614E3	-	75.0	-	-	$787.50
4	Genesis	G1290E	-	74.0	-	-	$777.00
5	Legacy	Seeds	LS194-23XF	72.0	-	-	$756.00
5	Loyal	Brand	L1860E	72.0	-	-	$756.00
5	Loyal	Brand	L2070E	72.0	-	-	$756.00
5	NK	NK14-U5E3	-	72.0	-	-	$756.00
5	Stine	17EE32	-	72.0	-	-	$756.00
10	BioGene	Seeds	BG9150E3	71.0	-	-	$745.50
10	Genesis	G1260E	-	71.0	-	-	$745.50
10	NK	NK11-A4E3	-	71.0	-	-	$745.50
10	Tracy	Seeds	1655E	71.0	-	-	$745.50
14	APEX	AE1220	-	70.0	-	-	$735.00
14	Loyal	Brand	L1540E	70.0	-	-	$735.00
16	Legacy	Seeds	LS144-24XF	69.0	-	-	$724.50
16	Tracy	Seeds	1854E	69.0	-	-	$724.50
18	APEX	AE1410	-	68.0	-	-	$714.00
18	Genesis	G1560E	-	68.0	-	-	$714.00
18	Golden Harvest	GH1534E3S	-	68.0	-	-	$714.00
18	Tracy	Seeds	1654E	68.0	-	-	$714.00
22	Asgrow	AG12XF5	-	67.0	-	-	$703.50
22	Asgrow	AG17XF5	-	67.0	-	-	$703.50
22	Genesis	G1590E	-	67.0	-	-	$703.50
22	Stine	11EC02	-	67.0	-	-	$703.50
26	Golden Harvest	GH1555XF	-	66.0	-	-	$693.00
26	Xitavo	XO	1095E	66.0	-	-	$693.00
28	NK	NK15-G9E3S	-	65.0	-	-	$682.50
28	Stine	13EG23	-	65.0	-	-	$682.50
28	Stine	15EE32	-	65.0	-	-	$682.50
28	Xitavo	XO	1632E	65.0	-	-	$682.50
32	Legacy	Seeds	LS112-24 E	64.0	-	-	$672.00
32	Legacy	Seeds	LS154-24XF	64.0	-	-	$672.00
32	Xitavo	XO	1404E	64.0	-	-	$672.00
35	Tracy	Seeds	1055E	63.0	-	-	$661.50
35	Xitavo	XO	1545E	63.0	-	-	$661.50
37	APEX	AE1710	-	62.0	-	-	$651.00
37	Asgrow	AG19XF3	-	62.0	-	-	$651.00
37	Loyal	Brand	L1070E	62.0	-	-	$651.00
37	Loyal	Brand	L1270E	62.0	-	-	$651.00
37	Stine	10EG20	-	62.0	-	-	$651.00
42	Legacy	Seeds	LS132-24 E	61.0	-	-	$640.50
42	NK	NK08-Z4E3	-	61.0	-	-	$640.50
42	Renk	Seed	RS155NXF	61.0	-	-	$640.50
42	Xitavo	XO	1372E	61.0	-	-	$640.50
46	Asgrow	AG14XF4	-	60.0	-	-	$630.00
46	O'Brien	Hybrids	O'Soy 1524EL-3	60.0	-	-	$630.00
48	Tracy	Seeds	1255E	59.0	-	-	$619.50
49	Loyal	Brand	L1160E	58.0	-	-	$609.00
49	Xitavo	XO	1225E	58.0	-	-	$609.00
51	APEX	AE1250	-	55.0	-	-	$577.50
51	Asgrow	AG16XF5	-	55.0	-	-	$577.50
51	Xitavo	XO	0993E	55.0	-	-	$577.50

Top 5 by Yield: Brand (Loyal) 76.0, G1760E (Genesis) 75.0, GH1614E3 (Golden Harvest) 75.0, G1290E (Genesis) 74.0, Seeds (Legacy) 72.0.

3.6 KiB Raw Blame History

Soybean yield trial — Wisconsin, 2024

Results (top-down by rank)

3.6 KiB

Raw Blame History