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 Permalink 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: 2440892
Cooperator: University of Wisconsin - Fond du Lac
Planted: 2024-04-30
Harvested: 2024-10-03
URL: https://www.goldenharvestseeds.com/soybean/plot-report/wi/2024/2440892

Results (top-down by rank)

Rank	Brand	Product	Traits	Yield	%MST	Test Weight	Gross Revenue
1	Xitavo	XO	2444E	85.0	-	-	$892.50
2	Legacy	Seeds	LS194-23XF	84.0	-	-	$882.00
3	Renk	Seed	RS194NXF	83.0	-	-	$871.50
4	Golden Harvest	GH2004XF	-	81.0	-	-	$850.50
4	NK	NK19-T8E3S	-	81.0	-	-	$850.50
6	Xitavo	XO	1632E	80.0	-	-	$840.00
6	Xitavo	XO	2282E	80.0	-	-	$840.00
6	Xitavo	XO	2305E	80.0	-	-	$840.00
9	Genesis	G1980E	-	79.0	-	-	$829.50
9	Golden Harvest	GH2315E3	-	79.0	-	-	$829.50
9	Stine	19EC12	-	79.0	-	-	$829.50
12	Asgrow	AG21XF2	-	78.0	-	-	$819.00
12	Golden Harvest	GH2292E3	-	78.0	-	-	$819.00
12	O'Brien	Hybrids	O'Soy 2024EL-3	78.0	-	-	$819.00
12	O'Brien	Hybrids	O'Soy 2523EL-3	78.0	-	-	$819.00
16	APEX	AE1940	-	77.0	-	-	$808.50
16	Genesis	G1950E	-	77.0	-	-	$808.50
16	Golden Harvest	GH1973E3S	-	77.0	-	-	$808.50
16	Loyal	Brand	L1860E	77.0	-	-	$808.50
16	Loyal	Brand	L2070E	77.0	-	-	$808.50
16	NK	NK21-C2E3	-	77.0	-	-	$808.50
22	BioGene	Seeds	BG9185E3	76.0	-	-	$798.00
22	DonMario	Seeds	DM22E64	76.0	-	-	$798.00
22	DonMario	Seeds	DM24E84	76.0	-	-	$798.00
22	Genesis	G2180E	-	76.0	-	-	$798.00
22	Loyal	Brand	L1540E	76.0	-	-	$798.00
22	Loyal	Brand	L1670E	76.0	-	-	$798.00
22	Stine	19EG92	-	76.0	-	-	$798.00
22	Stine	20EG02	-	76.0	-	-	$798.00
22	Tracy	Seeds	2055E	76.0	-	-	$798.00
22	Xitavo	XO	1404E	76.0	-	-	$798.00
32	Asgrow	AG16XF5	-	75.0	-	-	$787.50
32	Asgrow	AG19XF3	-	75.0	-	-	$787.50
32	Legacy	Seeds	LS154-24XF	75.0	-	-	$787.50
32	O'Brien	Hybrids	O'Soy 1524EL-3	75.0	-	-	$787.50
32	Stine	24EG23	-	75.0	-	-	$787.50
32	Tracy	Seeds	1655E	75.0	-	-	$787.50
32	Xitavo	XO	1545E	75.0	-	-	$787.50
39	APEX	AE2220	-	74.0	-	-	$777.00
39	Tracy	Seeds	2355E	74.0	-	-	$777.00
39	Xitavo	XO	1822E	74.0	-	-	$777.00
42	NK	NK18-R4E3	-	72.0	-	-	$756.00
42	Xitavo	XO	1372E	72.0	-	-	$756.00
44	Xitavo	XO	2181E	70.0	-	-	$735.00
45	Loyal	Brand	L2160E	69.0	-	-	$724.50
46	Tracy	Seeds	1654E	68.0	-	-	$714.00
46	Tracy	Seeds	1854E	68.0	-	-	$714.00
48	Stine	17EE32	-	67.0	-	-	$703.50
49	NK	NK16-Z6E3	-	65.0	-	-	$682.50
49	Xitavo	XO	1225E	65.0	-	-	$682.50
51	Tracy	Seeds	2255E	63.0	-	-	$661.50
52	Asgrow	AG20XF4	-	62.0	-	-	$651.00
52	Xitavo	XO	1095E	62.0	-	-	$651.00

Top 5 by Yield: XO (Xitavo) 85.0, Seeds (Legacy) 84.0, Seed (Renk) 83.0, GH2004XF (Golden Harvest) 81.0, NK19-T8E3S (NK) 81.0.

3.6 KiB Raw Permalink Blame History

Soybean yield trial — Wisconsin, 2024

Results (top-down by rank)

3.6 KiB

Raw Permalink Blame History