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>
362 lines
7.9 KiB
JSON
362 lines
7.9 KiB
JSON
{
|
|
"source": "gh_plot_reports",
|
|
"source_key": "ghpr-silage-wi-2025-2469663",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "silage",
|
|
"state": "Wisconsin",
|
|
"state_abbrev": "wi",
|
|
"year": 2025,
|
|
"plot_id": "2469663",
|
|
"cooperator": "Lee Vandergeest",
|
|
"planted_date": "2025-05-15",
|
|
"harvested_date": "2025-10-02",
|
|
"population_seeds_per_acre": 32000,
|
|
"row_width_in": 30,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "Enogen",
|
|
"product": "E085Z5-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 27.5,
|
|
"Milk Per Acre": 3695.0,
|
|
"Milk Per Ton": 30514.0,
|
|
"Beef Per Acre": 272.0,
|
|
"Beef Per Ton": 1930.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "Channel",
|
|
"product": "186-56STX",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 27.1,
|
|
"Milk Per Acre": 3368.0,
|
|
"Milk Per Ton": 27357.0,
|
|
"Beef Per Acre": 232.0,
|
|
"Beef Per Ton": 1782.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 3,
|
|
"brand": "DEKALB",
|
|
"product": "DKC39-55",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 26.9,
|
|
"Milk Per Acre": 3442.0,
|
|
"Milk Per Ton": 27825.0,
|
|
"Beef Per Acre": 252.0,
|
|
"Beef Per Ton": 1832.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "Pioneer",
|
|
"product": "P87040PCE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 26.5,
|
|
"Milk Per Acre": 3484.0,
|
|
"Milk Per Ton": 27659.0,
|
|
"Beef Per Acre": 244.0,
|
|
"Beef Per Ton": 1776.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "Brevant",
|
|
"product": "B87D33Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 26.3,
|
|
"Milk Per Acre": 3497.0,
|
|
"Milk Per Ton": 27610.0,
|
|
"Beef Per Acre": 258.0,
|
|
"Beef Per Ton": 1805.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "Pioneer",
|
|
"product": "P8602AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 25.9,
|
|
"Milk Per Acre": 3279.0,
|
|
"Milk Per Ton": 25495.0,
|
|
"Beef Per Acre": 224.0,
|
|
"Beef Per Ton": 1683.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"brand": "Pioneer",
|
|
"product": "P90630AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 25.4,
|
|
"Milk Per Acre": 3378.0,
|
|
"Milk Per Ton": 25791.0,
|
|
"Beef Per Acre": 242.0,
|
|
"Beef Per Ton": 1701.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "DEKALB",
|
|
"product": "DKC36-48",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 25.0,
|
|
"Milk Per Acre": 3398.0,
|
|
"Milk Per Ton": 25496.0,
|
|
"Beef Per Acre": 236.0,
|
|
"Beef Per Ton": 1656.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "Brevant",
|
|
"product": "B89A44PCE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 25.0,
|
|
"Milk Per Acre": 3703.0,
|
|
"Milk Per Ton": 27756.0,
|
|
"Beef Per Acre": 270.0,
|
|
"Beef Per Ton": 1746.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "NK",
|
|
"product": "NK9231-AA",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 23.0,
|
|
"Milk Per Acre": 3684.0,
|
|
"Milk Per Ton": 25448.0,
|
|
"Beef Per Acre": 271.0,
|
|
"Beef Per Ton": 1610.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 11,
|
|
"brand": "Brevant",
|
|
"product": "B91K05Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 22.9,
|
|
"Milk Per Acre": 3639.0,
|
|
"Milk Per Ton": 24986.0,
|
|
"Beef Per Acre": 260.0,
|
|
"Beef Per Ton": 1574.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"brand": "Brevant",
|
|
"product": "B86J43AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 22.3,
|
|
"Milk Per Acre": 3753.0,
|
|
"Milk Per Ton": 25119.0,
|
|
"Beef Per Acre": 279.0,
|
|
"Beef Per Ton": 1582.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "DEKALB",
|
|
"product": "DKC093-05",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 21.9,
|
|
"Milk Per Acre": 3548.0,
|
|
"Milk Per Ton": 23265.0,
|
|
"Beef Per Acre": 254.0,
|
|
"Beef Per Ton": 1489.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"brand": "NK",
|
|
"product": "NK9400-V",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 21.1,
|
|
"Milk Per Acre": 3508.0,
|
|
"Milk Per Ton": 22205.0,
|
|
"Beef Per Acre": 254.0,
|
|
"Beef Per Ton": 1437.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"brand": "DEKALB",
|
|
"product": "DKC45-74",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 20.9,
|
|
"Milk Per Acre": 3453.0,
|
|
"Milk Per Ton": 21604.0,
|
|
"Beef Per Acre": 277.0,
|
|
"Beef Per Ton": 1473.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "Brevant",
|
|
"product": "B92D25Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 20.4,
|
|
"Milk Per Acre": 3502.0,
|
|
"Milk Per Ton": 21430.0,
|
|
"Beef Per Acre": 274.0,
|
|
"Beef Per Ton": 1434.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "DEKALB",
|
|
"product": "DKC092-13",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 20.1,
|
|
"Milk Per Acre": 3260.0,
|
|
"Milk Per Ton": 19676.0,
|
|
"Beef Per Acre": 272.0,
|
|
"Beef Per Ton": 1410.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 18,
|
|
"brand": "Enogen",
|
|
"product": "E092W5-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 19.9,
|
|
"Milk Per Acre": 3591.0,
|
|
"Milk Per Ton": 21430.0,
|
|
"Beef Per Acre": 262.0,
|
|
"Beef Per Ton": 1372.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 18,
|
|
"brand": "Enogen",
|
|
"product": "E094Z4-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 19.9,
|
|
"Milk Per Acre": 3777.0,
|
|
"Milk Per Ton": 22566.0,
|
|
"Beef Per Acre": 274.0,
|
|
"Beef Per Ton": 1399.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 20,
|
|
"brand": "Channel",
|
|
"product": "192-10STX",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 19.4,
|
|
"Milk Per Acre": 3404.0,
|
|
"Milk Per Ton": 19854.0,
|
|
"Beef Per Acre": 239.0,
|
|
"Beef Per Ton": 1293.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 20,
|
|
"brand": "Enogen",
|
|
"product": "E095D3-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 19.4,
|
|
"Milk Per Acre": 3487.0,
|
|
"Milk Per Ton": 20330.0,
|
|
"Beef Per Acre": 250.0,
|
|
"Beef Per Ton": 1317.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 22,
|
|
"brand": "Brevant",
|
|
"product": "B96M56PCE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 18.0,
|
|
"Milk Per Acre": 3578.0,
|
|
"Milk Per Ton": 19283.0,
|
|
"Beef Per Acre": 256.0,
|
|
"Beef Per Ton": 1228.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 23,
|
|
"brand": "Brevant",
|
|
"product": "B95R21V",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 17.7,
|
|
"Milk Per Acre": 3553.0,
|
|
"Milk Per Ton": 18831.0,
|
|
"Beef Per Acre": 260.0,
|
|
"Beef Per Ton": 1215.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 24,
|
|
"brand": "Pioneer",
|
|
"product": "P9624AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 16.9,
|
|
"Milk Per Acre": 3576.0,
|
|
"Milk Per Ton": 18146.0,
|
|
"Beef Per Acre": 261.0,
|
|
"Beef Per Ton": 1166.0
|
|
},
|
|
"entry_num": null
|
|
}
|
|
],
|
|
"n_results": 24,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2469663"
|
|
],
|
|
"fetched_at": "2026-05-25T19:50:38.747860+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|