justin
0e625553e5
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>
598 lines
12 KiB
JSON
598 lines
12 KiB
JSON
{
|
|
"source": "gh_plot_reports",
|
|
"source_key": "ghpr-soybeans-mo-2024-2420197",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "soybeans",
|
|
"state": "Missouri",
|
|
"state_abbrev": "mo",
|
|
"year": 2024,
|
|
"plot_id": "2420197",
|
|
"cooperator": "University of Missouri - Campbell",
|
|
"planted_date": "2024-04-25",
|
|
"harvested_date": "2024-10-04",
|
|
"population_seeds_per_acre": null,
|
|
"row_width_in": null,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "Golden Harvest",
|
|
"product": "GH4452XFS",
|
|
"traits": "XtendFlex ® STS ®",
|
|
"metrics": {
|
|
"Yield": 66.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 694.05
|
|
},
|
|
"entry_num": 3
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "UniSouth",
|
|
"product": "Genetics",
|
|
"traits": "USG 7463XF",
|
|
"metrics": {
|
|
"Yield": 65.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 684.6
|
|
},
|
|
"entry_num": 4
|
|
},
|
|
{
|
|
"rank": 3,
|
|
"brand": "Channel",
|
|
"product": "4720RXF/SR",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 62.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 656.25
|
|
},
|
|
"entry_num": 6
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "Delta",
|
|
"product": "Grow",
|
|
"traits": "DG48XF70STS",
|
|
"metrics": {
|
|
"Yield": 61.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 649.95
|
|
},
|
|
"entry_num": 8
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "Pioneer",
|
|
"product": "P40A23E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 61.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 641.55
|
|
},
|
|
"entry_num": 9
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "Asgrow",
|
|
"product": "AG36XF4",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 59.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 628.95
|
|
},
|
|
"entry_num": 10
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"brand": "Axis",
|
|
"product": "Seed",
|
|
"traits": "4625XFS",
|
|
"metrics": {
|
|
"Yield": 59.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 620.55
|
|
},
|
|
"entry_num": 12
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "Channel",
|
|
"product": "3823RXF",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 58.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 614.25
|
|
},
|
|
"entry_num": 13
|
|
},
|
|
{
|
|
"rank": 9,
|
|
"brand": "UniSouth",
|
|
"product": "Genetics",
|
|
"traits": "USG 7461XFS",
|
|
"metrics": {
|
|
"Yield": 56.8,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 596.4
|
|
},
|
|
"entry_num": 16
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Axis",
|
|
"product": "Seed",
|
|
"traits": "4815XFS",
|
|
"metrics": {
|
|
"Yield": 56.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 592.2
|
|
},
|
|
"entry_num": 18
|
|
},
|
|
{
|
|
"rank": 11,
|
|
"brand": "Axis",
|
|
"product": "Seed",
|
|
"traits": "4613XF",
|
|
"metrics": {
|
|
"Yield": 55.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 581.7
|
|
},
|
|
"entry_num": 19
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"brand": "AgVenture",
|
|
"product": "AV47Y6E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 55.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 580.65
|
|
},
|
|
"entry_num": 20
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "Axis",
|
|
"product": "Seed",
|
|
"traits": "4105XF",
|
|
"metrics": {
|
|
"Yield": 55.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 579.6
|
|
},
|
|
"entry_num": 21
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"brand": "Pioneer",
|
|
"product": "P34A98E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 54.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 576.45
|
|
},
|
|
"entry_num": 22
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"brand": "Asgrow",
|
|
"product": "AG37XF1",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 54.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 574.35
|
|
},
|
|
"entry_num": 23
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "Golden Harvest",
|
|
"product": "GH4864XFS",
|
|
"traits": "XtendFlex ® STS ®",
|
|
"metrics": {
|
|
"Yield": 54.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 572.25
|
|
},
|
|
"entry_num": 24
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "UniSouth",
|
|
"product": "Genetics",
|
|
"traits": "USG 7435XFS",
|
|
"metrics": {
|
|
"Yield": 54.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 570.15
|
|
},
|
|
"entry_num": 25
|
|
},
|
|
{
|
|
"rank": 18,
|
|
"brand": "Brevant",
|
|
"product": "B364EE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 54.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 569.1
|
|
},
|
|
"entry_num": 26
|
|
},
|
|
{
|
|
"rank": 19,
|
|
"brand": "AgVenture",
|
|
"product": "AV45B2E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 53.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 563.85
|
|
},
|
|
"entry_num": 27
|
|
},
|
|
{
|
|
"rank": 19,
|
|
"brand": "Golden Harvest",
|
|
"product": "GH4944XFS",
|
|
"traits": "XtendFlex ® STS ®",
|
|
"metrics": {
|
|
"Yield": 53.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 563.85
|
|
},
|
|
"entry_num": 28
|
|
},
|
|
{
|
|
"rank": 21,
|
|
"brand": "Asgrow",
|
|
"product": "AG44XF4",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 53.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 558.6
|
|
},
|
|
"entry_num": 29
|
|
},
|
|
{
|
|
"rank": 22,
|
|
"brand": "Benson",
|
|
"product": "Hill",
|
|
"traits": "BH43Q207",
|
|
"metrics": {
|
|
"Yield": 52.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 553.35
|
|
},
|
|
"entry_num": 30
|
|
},
|
|
{
|
|
"rank": 23,
|
|
"brand": "UniSouth",
|
|
"product": "Genetics",
|
|
"traits": "USG 7495XFS",
|
|
"metrics": {
|
|
"Yield": 52.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 550.2
|
|
},
|
|
"entry_num": 32
|
|
},
|
|
{
|
|
"rank": 24,
|
|
"brand": "Asgrow",
|
|
"product": "AG39XF3",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 51.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 544.95
|
|
},
|
|
"entry_num": 33
|
|
},
|
|
{
|
|
"rank": 25,
|
|
"brand": "Asgrow",
|
|
"product": "AG47XF2",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 51.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 542.85
|
|
},
|
|
"entry_num": 34
|
|
},
|
|
{
|
|
"rank": 26,
|
|
"brand": "Pioneer",
|
|
"product": "P46A90LX",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 50.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 534.45
|
|
},
|
|
"entry_num": 36
|
|
},
|
|
{
|
|
"rank": 27,
|
|
"brand": "Pioneer",
|
|
"product": "P44A91E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 50.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 531.3
|
|
},
|
|
"entry_num": 37
|
|
},
|
|
{
|
|
"rank": 28,
|
|
"brand": "Axis",
|
|
"product": "Seed",
|
|
"traits": "4905XF",
|
|
"metrics": {
|
|
"Yield": 50.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 528.15
|
|
},
|
|
"entry_num": 39
|
|
},
|
|
{
|
|
"rank": 28,
|
|
"brand": "Pioneer",
|
|
"product": "P45A70LX",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 50.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 528.15
|
|
},
|
|
"entry_num": 40
|
|
},
|
|
{
|
|
"rank": 30,
|
|
"brand": "Asgrow",
|
|
"product": "AG38XF1",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 50.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 527.1
|
|
},
|
|
"entry_num": 41
|
|
},
|
|
{
|
|
"rank": 31,
|
|
"brand": "Delta",
|
|
"product": "Grow",
|
|
"traits": "DG43XF65STS",
|
|
"metrics": {
|
|
"Yield": 49.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 516.6
|
|
},
|
|
"entry_num": 42
|
|
},
|
|
{
|
|
"rank": 32,
|
|
"brand": "AgVenture",
|
|
"product": "AV48B2E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 48.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 510.3
|
|
},
|
|
"entry_num": 43
|
|
},
|
|
{
|
|
"rank": 33,
|
|
"brand": "AgVenture",
|
|
"product": "AV44B2E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 48.0,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 504.0
|
|
},
|
|
"entry_num": 44
|
|
},
|
|
{
|
|
"rank": 34,
|
|
"brand": "Asgrow",
|
|
"product": "AG40XF1",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 47.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 500.85
|
|
},
|
|
"entry_num": 45
|
|
},
|
|
{
|
|
"rank": 35,
|
|
"brand": "Channel",
|
|
"product": "4823RXF/SR",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 47.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 495.6
|
|
},
|
|
"entry_num": 46
|
|
},
|
|
{
|
|
"rank": 35,
|
|
"brand": "Pioneer",
|
|
"product": "P46A09E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 47.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 495.6
|
|
},
|
|
"entry_num": 47
|
|
},
|
|
{
|
|
"rank": 37,
|
|
"brand": "UniSouth",
|
|
"product": "Genetics",
|
|
"traits": "USG 7474XFS",
|
|
"metrics": {
|
|
"Yield": 46.8,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 491.4
|
|
},
|
|
"entry_num": 48
|
|
},
|
|
{
|
|
"rank": 38,
|
|
"brand": "Pioneer",
|
|
"product": "P37A18E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 46.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 490.35
|
|
},
|
|
"entry_num": 49
|
|
},
|
|
{
|
|
"rank": 39,
|
|
"brand": "Delta",
|
|
"product": "Grow",
|
|
"traits": "DG46XF54STS",
|
|
"metrics": {
|
|
"Yield": 46.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 489.3
|
|
},
|
|
"entry_num": 50
|
|
},
|
|
{
|
|
"rank": 40,
|
|
"brand": "Pioneer",
|
|
"product": "P38A28E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 45.8,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 480.9
|
|
},
|
|
"entry_num": 52
|
|
},
|
|
{
|
|
"rank": 41,
|
|
"brand": "Brevant",
|
|
"product": "B394EE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 45.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 473.55
|
|
},
|
|
"entry_num": 53
|
|
},
|
|
{
|
|
"rank": 42,
|
|
"brand": "Pioneer",
|
|
"product": "P48Z70BLX",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 45.0,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 472.5
|
|
},
|
|
"entry_num": 54
|
|
},
|
|
{
|
|
"rank": 43,
|
|
"brand": "Delta",
|
|
"product": "Grow",
|
|
"traits": "DG49XF85STS",
|
|
"metrics": {
|
|
"Yield": 41.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 431.55
|
|
},
|
|
"entry_num": 55
|
|
},
|
|
{
|
|
"rank": 44,
|
|
"brand": "Delta",
|
|
"product": "Grow",
|
|
"traits": "DG47XF90STS",
|
|
"metrics": {
|
|
"Yield": 39.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 411.6
|
|
},
|
|
"entry_num": 57
|
|
}
|
|
],
|
|
"n_results": 44,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/soybean/plot-report/mo/2024/2420197"
|
|
],
|
|
"fetched_at": "2026-05-25T19:35:19.158852+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|