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

3.9 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: 2440891
Cooperator: University of Wisconsin - Platteville
Planted: 2024-05-15
Harvested: 2024-10-10
URL: https://www.goldenharvestseeds.com/soybean/plot-report/wi/2024/2440891

Results (top-down by rank)

Rank	Brand	Product	Traits	Yield	%MST	Test Weight	Gross Revenue
1	Cornelius	Seed	CB24XF75	90.0	-	-	$945.00
2	Genesis	G2960E	-	89.0	-	-	$934.50
2	Renk	Seed	RS255NXF	89.0	-	-	$934.50
4	Golden Harvest	GH2674E3	-	88.0	-	-	$924.00
4	Xitavo	XO	2305E	88.0	-	-	$924.00
6	Asgrow	AG26XF4	-	87.0	-	-	$913.50
7	Burrus	2729E	-	86.0	-	-	$903.00
7	NK	NK26-M6E3	-	86.0	-	-	$903.00
7	P3	Genetics	2424E	86.0	-	-	$903.00
7	Xitavo	XO	2832E	86.0	-	-	$903.00
11	Asgrow	AG25XF5	-	85.0	-	-	$892.50
11	Golden Harvest	GH2775E3	-	85.0	-	-	$892.50
11	P3	Genetics	2429E	85.0	-	-	$892.50
14	Asgrow	AG22XF5	-	84.0	-	-	$882.00
14	Asgrow	AG24XF4	-	84.0	-	-	$882.00
14	Burrus	2681E	-	84.0	-	-	$882.00
14	Cornelius	Seed	CB25XF99	84.0	-	-	$882.00
14	DonMario	Seeds	DM22E64	84.0	-	-	$882.00
14	DonMario	Seeds	DM24E84	84.0	-	-	$882.00
14	O'Brien	Hybrids	O'Soy 2523EL-3	84.0	-	-	$882.00
14	P3	Genetics	2325E	84.0	-	-	$882.00
14	Tracy	Seeds	2754E	84.0	-	-	$882.00
14	Xitavo	XO	2444E	84.0	-	-	$882.00
14	Xitavo	XO	2865E	84.0	-	-	$882.00
25	Burrus	2335E	-	83.0	-	-	$871.50
25	DonMario	Seeds	DM24E84	83.0	-	-	$871.50
25	NK	NK27-J5E3	-	83.0	-	-	$871.50
25	Stine	24EG23	-	83.0	-	-	$871.50
25	Stine	28EG32	-	83.0	-	-	$871.50
25	Tracy	Seeds	2655E	83.0	-	-	$871.50
31	NK	NK21-C2E3	-	82.0	-	-	$861.00
31	NK	NK23-P1E3	-	82.0	-	-	$861.00
31	P3	Genetics	2527E	82.0	-	-	$861.00
31	Stine	19EG92	-	82.0	-	-	$861.00
31	Xitavo	XO	2282E	82.0	-	-	$861.00
31	Xitavo	XO	2985E	82.0	-	-	$861.00
37	Asgrow	AG21XF2	-	81.0	-	-	$850.50
37	Asgrow	AG24XF1	-	81.0	-	-	$850.50
37	Genesis	G2570ES	-	81.0	-	-	$850.50
37	Loyal	Brand	L2070E	81.0	-	-	$850.50
37	Loyal	Brand	L2560E	81.0	-	-	$850.50
37	Stine	25EG23	-	81.0	-	-	$850.50
43	Asgrow	AG20XF4	-	80.0	-	-	$840.00
43	Burrus	2084E	-	80.0	-	-	$840.00
43	Genesis	G2790E	-	80.0	-	-	$840.00
43	Stine	22EG02	-	80.0	-	-	$840.00
43	Xitavo	XO	1822E	80.0	-	-	$840.00
48	Tracy	Seeds	2255E	79.0	-	-	$829.50
48	Xitavo	XO	2625E	79.0	-	-	$829.50
50	Loyal	Brand	L2160E	78.0	-	-	$819.00
50	Xitavo	XO	2181E	78.0	-	-	$819.00
52	Tracy	Seeds	2055E	77.0	-	-	$808.50
53	Stine	19EC12	-	76.0	-	-	$798.00
54	Stine	21EG32	-	75.0	-	-	$787.50
54	Xitavo	XO	2735E	75.0	-	-	$787.50
56	Loyal	Brand	L2370E	74.0	-	-	$777.00
56	O'Brien	Hybrids	O'Soy 2024EL-3	74.0	-	-	$777.00
58	NK	NK19-T8E3S	-	73.0	-	-	$766.50
58	Tracy	Seeds	2355E	73.0	-	-	$766.50

Top 5 by Yield: Seed (Cornelius) 90.0, G2960E (Genesis) 89.0, Seed (Renk) 89.0, GH2674E3 (Golden Harvest) 88.0, XO (Xitavo) 88.0.

3.9 KiB Raw Blame History

Soybean yield trial — Wisconsin, 2024

Results (top-down by rank)

3.9 KiB

Raw Blame History