Files
seed-mcp/corpus/gh_plot_reports/ghpr-silage-wi-2024-2465531.json
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

530 lines
12 KiB
JSON

{
"source": "gh_plot_reports",
"source_key": "ghpr-silage-wi-2024-2465531",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "silage",
"state": "Wisconsin",
"state_abbrev": "wi",
"year": 2024,
"plot_id": "2465531",
"cooperator": "Tom Kopp Farms",
"planted_date": "2024-05-10",
"harvested_date": "2024-09-16",
"population_seeds_per_acre": 37000,
"row_width_in": 30,
"results": [
{
"rank": 1,
"brand": "Legacy",
"product": "Seeds",
"traits": "Experimental",
"metrics": {
"Ton/Acre": 33.0,
"Milk Per Acre": 3520.0,
"Milk Per Ton": 34858.0,
"Beef Per Acre": 252.0,
"Beef Per Ton": 2618.0
},
"entry_num": null
},
{
"rank": 2,
"brand": "Midwest",
"product": "Seed",
"traits": "Genetics MW 09-90 PCE",
"metrics": {
"Ton/Acre": 32.3,
"Milk Per Acre": 3396.0,
"Milk Per Ton": 32949.0,
"Beef Per Acre": 233.0,
"Beef Per Ton": 2481.0
},
"entry_num": null
},
{
"rank": 3,
"brand": "Pioneer",
"product": "P14830Q",
"traits": "",
"metrics": {
"Ton/Acre": 31.8,
"Milk Per Acre": 3604.0,
"Milk Per Ton": 34412.0,
"Beef Per Acre": 270.0,
"Beef Per Ton": 2579.0
},
"entry_num": null
},
{
"rank": 4,
"brand": "Brevant",
"product": "B09C43V",
"traits": "",
"metrics": {
"Ton/Acre": 30.9,
"Milk Per Acre": 3082.0,
"Milk Per Ton": 28561.0,
"Beef Per Acre": 204.0,
"Beef Per Ton": 2229.0
},
"entry_num": null
},
{
"rank": 5,
"brand": "Brevant",
"product": "B08V35Q",
"traits": "",
"metrics": {
"Ton/Acre": 30.6,
"Milk Per Acre": 3525.0,
"Milk Per Ton": 32351.0,
"Beef Per Acre": 257.0,
"Beef Per Ton": 2432.0
},
"entry_num": null
},
{
"rank": 6,
"brand": "Legacy",
"product": "Seeds",
"traits": "LC554-23 SS",
"metrics": {
"Ton/Acre": 30.5,
"Milk Per Acre": 3475.0,
"Milk Per Ton": 31774.0,
"Beef Per Acre": 259.0,
"Beef Per Ton": 2441.0
},
"entry_num": null
},
{
"rank": 7,
"brand": "Legacy",
"product": "Seeds",
"traits": "LC644-22 DV",
"metrics": {
"Ton/Acre": 30.4,
"Milk Per Acre": 3292.0,
"Milk Per Ton": 30058.0,
"Beef Per Acre": 220.0,
"Beef Per Ton": 2277.0
},
"entry_num": null
},
{
"rank": 8,
"brand": "Legacy",
"product": "Seeds",
"traits": "Experimental",
"metrics": {
"Ton/Acre": 30.0,
"Milk Per Acre": 3434.0,
"Milk Per Ton": 30924.0,
"Beef Per Acre": 245.0,
"Beef Per Ton": 2343.0
},
"entry_num": null
},
{
"rank": 9,
"brand": "Legacy",
"product": "Seeds",
"traits": "LC572-22 SS",
"metrics": {
"Ton/Acre": 29.9,
"Milk Per Acre": 3383.0,
"Milk Per Ton": 30316.0,
"Beef Per Acre": 234.0,
"Beef Per Ton": 2289.0
},
"entry_num": null
},
{
"rank": 9,
"brand": "Legacy",
"product": "Seeds",
"traits": "Experimental",
"metrics": {
"Ton/Acre": 29.9,
"Milk Per Acre": 3750.0,
"Milk Per Ton": 33623.0,
"Beef Per Acre": 284.0,
"Beef Per Ton": 2481.0
},
"entry_num": null
},
{
"rank": 11,
"brand": "Dairyland",
"product": "Seed",
"traits": "HiDF-5033V",
"metrics": {
"Ton/Acre": 29.6,
"Milk Per Acre": 3594.0,
"Milk Per Ton": 31902.0,
"Beef Per Acre": 267.0,
"Beef Per Ton": 2390.0
},
"entry_num": null
},
{
"rank": 12,
"brand": "Legacy",
"product": "Seeds",
"traits": "Experimental",
"metrics": {
"Ton/Acre": 29.4,
"Milk Per Acre": 3647.0,
"Milk Per Ton": 32135.0,
"Beef Per Acre": 262.0,
"Beef Per Ton": 2391.0
},
"entry_num": null
},
{
"rank": 13,
"brand": "Pioneer",
"product": "P13777V",
"traits": "",
"metrics": {
"Ton/Acre": 29.3,
"Milk Per Acre": 3390.0,
"Milk Per Ton": 29826.0,
"Beef Per Acre": 235.0,
"Beef Per Ton": 2255.0
},
"entry_num": null
},
{
"rank": 14,
"brand": "Renk",
"product": "Seed",
"traits": "RK773TRE",
"metrics": {
"Ton/Acre": 29.2,
"Milk Per Acre": 3487.0,
"Milk Per Ton": 30589.0,
"Beef Per Acre": 240.0,
"Beef Per Ton": 2289.0
},
"entry_num": null
},
{
"rank": 15,
"brand": "Pioneer",
"product": "P0924Q",
"traits": "",
"metrics": {
"Ton/Acre": 29.1,
"Milk Per Acre": 3612.0,
"Milk Per Ton": 31502.0,
"Beef Per Acre": 267.0,
"Beef Per Ton": 2356.0
},
"entry_num": null
},
{
"rank": 15,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 29.1,
"Milk Per Acre": 3608.0,
"Milk Per Ton": 31490.0,
"Beef Per Acre": 260.0,
"Beef Per Ton": 2350.0
},
"entry_num": null
},
{
"rank": 17,
"brand": "Legacy",
"product": "Seeds",
"traits": "LC623-21 DV",
"metrics": {
"Ton/Acre": 28.9,
"Milk Per Acre": 3552.0,
"Milk Per Ton": 30778.0,
"Beef Per Acre": 252.0,
"Beef Per Ton": 2302.0
},
"entry_num": null
},
{
"rank": 18,
"brand": "Legacy",
"product": "Seeds",
"traits": "Experimental",
"metrics": {
"Ton/Acre": 28.8,
"Milk Per Acre": 3725.0,
"Milk Per Ton": 32237.0,
"Beef Per Acre": 290.0,
"Beef Per Ton": 2451.0
},
"entry_num": null
},
{
"rank": 19,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 28.5,
"Milk Per Acre": 3633.0,
"Milk Per Ton": 31041.0,
"Beef Per Acre": 285.0,
"Beef Per Ton": 2374.0
},
"entry_num": null
},
{
"rank": 20,
"brand": "Brevant",
"product": "B06F91Q",
"traits": "",
"metrics": {
"Ton/Acre": 28.4,
"Milk Per Acre": 3395.0,
"Milk Per Ton": 28931.0,
"Beef Per Acre": 235.0,
"Beef Per Ton": 2203.0
},
"entry_num": null
},
{
"rank": 21,
"brand": "Pioneer",
"product": "P1089AMXT",
"traits": "",
"metrics": {
"Ton/Acre": 28.1,
"Milk Per Acre": 3437.0,
"Milk Per Ton": 29018.0,
"Beef Per Acre": 243.0,
"Beef Per Ton": 2187.0
},
"entry_num": null
},
{
"rank": 22,
"brand": "Brevant",
"product": "B12C01Q",
"traits": "",
"metrics": {
"Ton/Acre": 27.6,
"Milk Per Acre": 3449.0,
"Milk Per Ton": 28544.0,
"Beef Per Acre": 248.0,
"Beef Per Ton": 2155.0
},
"entry_num": null
},
{
"rank": 23,
"brand": "Dairyland",
"product": "Seed",
"traits": "HiDF-4808V",
"metrics": {
"Ton/Acre": 27.5,
"Milk Per Acre": 3677.0,
"Milk Per Ton": 30333.0,
"Beef Per Acre": 269.0,
"Beef Per Ton": 2255.0
},
"entry_num": null
},
{
"rank": 24,
"brand": "Pioneer",
"product": "P0720Q",
"traits": "",
"metrics": {
"Ton/Acre": 27.4,
"Milk Per Acre": 3753.0,
"Milk Per Ton": 30823.0,
"Beef Per Acre": 283.0,
"Beef Per Ton": 2291.0
},
"entry_num": null
},
{
"rank": 25,
"brand": "Brevant",
"product": "B09T70SX",
"traits": "",
"metrics": {
"Ton/Acre": 27.2,
"Milk Per Acre": 3241.0,
"Milk Per Ton": 26402.0,
"Beef Per Acre": 218.0,
"Beef Per Ton": 2015.0
},
"entry_num": null
},
{
"rank": 26,
"brand": "Legacy",
"product": "Seeds",
"traits": "LC605-23 PCE",
"metrics": {
"Ton/Acre": 27.1,
"Milk Per Acre": 3427.0,
"Milk Per Ton": 27870.0,
"Beef Per Acre": 234.0,
"Beef Per Ton": 2100.0
},
"entry_num": null
},
{
"rank": 27,
"brand": "Pioneer",
"product": "P08527V",
"traits": "",
"metrics": {
"Ton/Acre": 26.9,
"Milk Per Acre": 3796.0,
"Milk Per Ton": 30603.0,
"Beef Per Acre": 286.0,
"Beef Per Ton": 2256.0
},
"entry_num": null
},
{
"rank": 27,
"brand": "NK",
"product": "NK0440-AT",
"traits": "",
"metrics": {
"Ton/Acre": 26.9,
"Milk Per Acre": 3626.0,
"Milk Per Ton": 29274.0,
"Beef Per Acre": 262.0,
"Beef Per Ton": 2181.0
},
"entry_num": null
},
{
"rank": 29,
"brand": "Dairyland",
"product": "Seed",
"traits": "HiDF-5000Q",
"metrics": {
"Ton/Acre": 25.6,
"Milk Per Acre": 3410.0,
"Milk Per Ton": 26237.0,
"Beef Per Acre": 233.0,
"Beef Per Ton": 1981.0
},
"entry_num": null
},
{
"rank": 30,
"brand": "Brevant",
"product": "B05D47V",
"traits": "",
"metrics": {
"Ton/Acre": 25.5,
"Milk Per Acre": 3738.0,
"Milk Per Ton": 28650.0,
"Beef Per Acre": 281.0,
"Beef Per Ton": 2120.0
},
"entry_num": null
},
{
"rank": 31,
"brand": "Legacy",
"product": "Seeds",
"traits": "Experimental",
"metrics": {
"Ton/Acre": 25.2,
"Milk Per Acre": 3642.0,
"Milk Per Ton": 27540.0,
"Beef Per Acre": 259.0,
"Beef Per Ton": 2035.0
},
"entry_num": null
},
{
"rank": 32,
"brand": "Renk",
"product": "Seed",
"traits": "RK811PCE",
"metrics": {
"Ton/Acre": 25.1,
"Milk Per Acre": 3367.0,
"Milk Per Ton": 25356.0,
"Beef Per Acre": 240.0,
"Beef Per Ton": 1952.0
},
"entry_num": null
},
{
"rank": 33,
"brand": "Pioneer",
"product": "P09312V",
"traits": "",
"metrics": {
"Ton/Acre": 24.8,
"Milk Per Acre": 3299.0,
"Milk Per Ton": 24510.0,
"Beef Per Acre": 215.0,
"Beef Per Ton": 1858.0
},
"entry_num": null
},
{
"rank": 34,
"brand": "NK",
"product": "NK0440-AT",
"traits": "",
"metrics": {
"Ton/Acre": 24.3,
"Milk Per Acre": 3369.0,
"Milk Per Ton": 24541.0,
"Beef Per Acre": 234.0,
"Beef Per Ton": 1862.0
},
"entry_num": null
},
{
"rank": 35,
"brand": "Legacy",
"product": "Seeds",
"traits": "Experimental",
"metrics": {
"Ton/Acre": 22.2,
"Milk Per Acre": 3540.0,
"Milk Per Ton": 23592.0,
"Beef Per Acre": 257.0,
"Beef Per Ton": 1768.0
},
"entry_num": null
},
{
"rank": 36,
"brand": "Renk",
"product": "Seed",
"traits": "RK700SSTX",
"metrics": {
"Ton/Acre": 21.7,
"Milk Per Acre": 3438.0,
"Milk Per Ton": 22406.0,
"Beef Per Acre": 245.0,
"Beef Per Ton": 1696.0
},
"entry_num": null
}
],
"n_results": 36,
"source_urls": [
"https://www.goldenharvestseeds.com/silage/plot-report/wi/2024/2465531"
],
"fetched_at": "2026-05-25T19:42:13.864387+00:00",
"scraper_version": "0.1.0"
}