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>
507 lines
10 KiB
JSON
507 lines
10 KiB
JSON
{
|
|
"source": "gh_plot_reports",
|
|
"source_key": "ghpr-soybeans-nd-2024-2438061",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "soybeans",
|
|
"state": "North Dakota",
|
|
"state_abbrev": "nd",
|
|
"year": 2024,
|
|
"plot_id": "2438061",
|
|
"cooperator": "NDSU - Langdon Research Extension Center (Langdon)",
|
|
"planted_date": "2024-05-27",
|
|
"harvested_date": "2024-10-07",
|
|
"population_seeds_per_acre": null,
|
|
"row_width_in": null,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "Thunder",
|
|
"product": "Seed",
|
|
"traits": "TE7502N",
|
|
"metrics": {
|
|
"Yield": 75.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 788.55
|
|
},
|
|
"entry_num": 33
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "Golden Harvest",
|
|
"product": "GH0295E3",
|
|
"traits": "Enlist E3 ®",
|
|
"metrics": {
|
|
"Yield": 71.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 752.85
|
|
},
|
|
"entry_num": 13
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "Legacy",
|
|
"product": "Seeds",
|
|
"traits": "LS034-24 XF",
|
|
"metrics": {
|
|
"Yield": 71.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 752.85
|
|
},
|
|
"entry_num": 23
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "Legacy",
|
|
"product": "Seeds",
|
|
"traits": "LS088-23 E",
|
|
"metrics": {
|
|
"Yield": 70.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 739.2
|
|
},
|
|
"entry_num": 17
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "Legacy",
|
|
"product": "Seeds",
|
|
"traits": "LS0098-23 XF",
|
|
"metrics": {
|
|
"Yield": 69.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 728.7
|
|
},
|
|
"entry_num": 18
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "Golden Harvest",
|
|
"product": "GH00973E3",
|
|
"traits": "Enlist E3 ®",
|
|
"metrics": {
|
|
"Yield": 69.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 726.6
|
|
},
|
|
"entry_num": 11
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"brand": "Fortus",
|
|
"product": "0084E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 68.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 720.3
|
|
},
|
|
"entry_num": 7
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "Legacy",
|
|
"product": "Seeds",
|
|
"traits": "LS012-23 E",
|
|
"metrics": {
|
|
"Yield": 68.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 718.2
|
|
},
|
|
"entry_num": 19
|
|
},
|
|
{
|
|
"rank": 9,
|
|
"brand": "Xitavo",
|
|
"product": "XO",
|
|
"traits": "0234E",
|
|
"metrics": {
|
|
"Yield": 67.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 712.95
|
|
},
|
|
"entry_num": 38
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Proseed",
|
|
"product": "EL",
|
|
"traits": "40-093N",
|
|
"metrics": {
|
|
"Yield": 66.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 699.3
|
|
},
|
|
"entry_num": 26
|
|
},
|
|
{
|
|
"rank": 11,
|
|
"brand": "Dak-Sota",
|
|
"product": "DE54007",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 66.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 698.25
|
|
},
|
|
"entry_num": 31
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"brand": "Proseed",
|
|
"product": "XF",
|
|
"traits": "30-092N",
|
|
"metrics": {
|
|
"Yield": 66.0,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 693.0
|
|
},
|
|
"entry_num": 29
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "Xitavo",
|
|
"product": "XO",
|
|
"traits": "0094E",
|
|
"metrics": {
|
|
"Yield": 65.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 689.85
|
|
},
|
|
"entry_num": 37
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"brand": "Attain",
|
|
"product": "Attain",
|
|
"traits": "01A5N",
|
|
"metrics": {
|
|
"Yield": 65.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 687.75
|
|
},
|
|
"entry_num": 3
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"brand": "Fortus",
|
|
"product": "0165E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 64.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 678.3
|
|
},
|
|
"entry_num": 9
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "Legacy",
|
|
"product": "Seeds",
|
|
"traits": "LS022-24 E",
|
|
"metrics": {
|
|
"Yield": 63.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 666.75
|
|
},
|
|
"entry_num": 21
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "Golden Harvest",
|
|
"product": "GH00864XF",
|
|
"traits": "XtendFlex ®",
|
|
"metrics": {
|
|
"Yield": 63.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 663.6
|
|
},
|
|
"entry_num": 10
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "Proseed",
|
|
"product": "EL",
|
|
"traits": "50-063N",
|
|
"metrics": {
|
|
"Yield": 63.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 663.6
|
|
},
|
|
"entry_num": 27
|
|
},
|
|
{
|
|
"rank": 19,
|
|
"brand": "Channel",
|
|
"product": "0225RXF",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 62.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 660.45
|
|
},
|
|
"entry_num": 5
|
|
},
|
|
{
|
|
"rank": 20,
|
|
"brand": "Thunder",
|
|
"product": "Seed",
|
|
"traits": "TX82008N",
|
|
"metrics": {
|
|
"Yield": 62.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 653.1
|
|
},
|
|
"entry_num": 34
|
|
},
|
|
{
|
|
"rank": 21,
|
|
"brand": "Thunder",
|
|
"product": "Seed",
|
|
"traits": "TX85008",
|
|
"metrics": {
|
|
"Yield": 62.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 652.05
|
|
},
|
|
"entry_num": 36
|
|
},
|
|
{
|
|
"rank": 22,
|
|
"brand": "Legacy",
|
|
"product": "Seeds",
|
|
"traits": "LS0068-23 XF",
|
|
"metrics": {
|
|
"Yield": 60.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 633.15
|
|
},
|
|
"entry_num": 16
|
|
},
|
|
{
|
|
"rank": 23,
|
|
"brand": "Golden Harvest",
|
|
"product": "GH0225XF",
|
|
"traits": "XtendFlex ®",
|
|
"metrics": {
|
|
"Yield": 60.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 631.05
|
|
},
|
|
"entry_num": 12
|
|
},
|
|
{
|
|
"rank": 24,
|
|
"brand": "Fortus",
|
|
"product": "0089E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 59.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 624.75
|
|
},
|
|
"entry_num": 8
|
|
},
|
|
{
|
|
"rank": 25,
|
|
"brand": "Allegiant",
|
|
"product": "Allegiant",
|
|
"traits": "009F23 XF",
|
|
"metrics": {
|
|
"Yield": 59.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 622.65
|
|
},
|
|
"entry_num": 1
|
|
},
|
|
{
|
|
"rank": 26,
|
|
"brand": "Thunder",
|
|
"product": "Seed",
|
|
"traits": "TE71008N",
|
|
"metrics": {
|
|
"Yield": 59.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 621.6
|
|
},
|
|
"entry_num": 32
|
|
},
|
|
{
|
|
"rank": 27,
|
|
"brand": "Legacy",
|
|
"product": "Seeds",
|
|
"traits": "LS014-23 XF",
|
|
"metrics": {
|
|
"Yield": 58.8,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 617.4
|
|
},
|
|
"entry_num": 20
|
|
},
|
|
{
|
|
"rank": 28,
|
|
"brand": "Legacy",
|
|
"product": "Seeds",
|
|
"traits": "LS024-23 XF",
|
|
"metrics": {
|
|
"Yield": 58.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 610.05
|
|
},
|
|
"entry_num": 22
|
|
},
|
|
{
|
|
"rank": 29,
|
|
"brand": "Proseed",
|
|
"product": "XF",
|
|
"traits": "40-12",
|
|
"metrics": {
|
|
"Yield": 56.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 595.35
|
|
},
|
|
"entry_num": 30
|
|
},
|
|
{
|
|
"rank": 30,
|
|
"brand": "Channel",
|
|
"product": "00924RXF",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 56.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 594.3
|
|
},
|
|
"entry_num": 4
|
|
},
|
|
{
|
|
"rank": 31,
|
|
"brand": "Proseed",
|
|
"product": "XF",
|
|
"traits": "30-062",
|
|
"metrics": {
|
|
"Yield": 56.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 593.25
|
|
},
|
|
"entry_num": 28
|
|
},
|
|
{
|
|
"rank": 32,
|
|
"brand": "Thunder",
|
|
"product": "Seed",
|
|
"traits": "TX8402N",
|
|
"metrics": {
|
|
"Yield": 55.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 584.85
|
|
},
|
|
"entry_num": 35
|
|
},
|
|
{
|
|
"rank": 33,
|
|
"brand": "Allegiant",
|
|
"product": "Allegiant",
|
|
"traits": "01F24N XF",
|
|
"metrics": {
|
|
"Yield": 55.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 578.55
|
|
},
|
|
"entry_num": 2
|
|
},
|
|
{
|
|
"rank": 34,
|
|
"brand": "NDSU",
|
|
"product": "ND21008GT20",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 54.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 572.25
|
|
},
|
|
"entry_num": 25
|
|
},
|
|
{
|
|
"rank": 35,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed XF0063",
|
|
"metrics": {
|
|
"Yield": 52.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 553.35
|
|
},
|
|
"entry_num": 14
|
|
},
|
|
{
|
|
"rank": 36,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed XF0082",
|
|
"metrics": {
|
|
"Yield": 49.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 519.75
|
|
},
|
|
"entry_num": 15
|
|
},
|
|
{
|
|
"rank": 37,
|
|
"brand": "NDSU",
|
|
"product": "ND17009GT",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 48.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 509.25
|
|
},
|
|
"entry_num": 24
|
|
}
|
|
],
|
|
"n_results": 37,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/soybean/plot-report/nd/2024/2438061"
|
|
],
|
|
"fetched_at": "2026-05-25T19:40:21.456775+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|