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
8.0 KiB
JSON
362 lines
8.0 KiB
JSON
{
|
|
"source": "gh_plot_reports",
|
|
"source_key": "ghpr-silage-tn-2024-2435174",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "silage",
|
|
"state": "Tennessee",
|
|
"state_abbrev": "tn",
|
|
"year": 2024,
|
|
"plot_id": "2435174",
|
|
"cooperator": "William Andrew Shipley",
|
|
"planted_date": "2024-06-12",
|
|
"harvested_date": "2024-10-14",
|
|
"population_seeds_per_acre": 33000,
|
|
"row_width_in": 30,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "DEKALB",
|
|
"product": "DKC114-99",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 19.4,
|
|
"Milk Per Acre": 3000.0,
|
|
"Milk Per Ton": 17460.0,
|
|
"Beef Per Acre": 217.0,
|
|
"Beef Per Ton": 1246.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "NK",
|
|
"product": "NK1755-DV",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 18.6,
|
|
"Milk Per Acre": 3071.0,
|
|
"Milk Per Ton": 17136.0,
|
|
"Beef Per Acre": 232.0,
|
|
"Beef Per Ton": 1225.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 3,
|
|
"brand": "Augusta",
|
|
"product": "Seed",
|
|
"traits": "A2464-DV",
|
|
"metrics": {
|
|
"Ton/Acre": 16.9,
|
|
"Milk Per Acre": 3038.0,
|
|
"Milk Per Ton": 15403.0,
|
|
"Beef Per Acre": 218.0,
|
|
"Beef Per Ton": 1088.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "Enogen",
|
|
"product": "E114Z4-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 16.6,
|
|
"Milk Per Acre": 3041.0,
|
|
"Milk Per Ton": 15144.0,
|
|
"Beef Per Acre": 205.0,
|
|
"Beef Per Ton": 1046.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "Pioneer",
|
|
"product": "P1380Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 16.5,
|
|
"Milk Per Acre": 2855.0,
|
|
"Milk Per Ton": 14132.0,
|
|
"Beef Per Acre": 190.0,
|
|
"Beef Per Ton": 1015.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "Pioneer",
|
|
"product": "P1587Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 16.3,
|
|
"Milk Per Acre": 3016.0,
|
|
"Milk Per Ton": 14748.0,
|
|
"Beef Per Acre": 214.0,
|
|
"Beef Per Ton": 1042.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "Enogen",
|
|
"product": "E117Z7-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 16.3,
|
|
"Milk Per Acre": 2985.0,
|
|
"Milk Per Ton": 14597.0,
|
|
"Beef Per Acre": 203.0,
|
|
"Beef Per Ton": 1023.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "Pioneer",
|
|
"product": "P17677Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 16.3,
|
|
"Milk Per Acre": 2937.0,
|
|
"Milk Per Ton": 14362.0,
|
|
"Beef Per Acre": 223.0,
|
|
"Beef Per Ton": 1057.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "DEKALB",
|
|
"product": "DKC113-62",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 16.3,
|
|
"Milk Per Acre": 3009.0,
|
|
"Milk Per Ton": 14714.0,
|
|
"Beef Per Acre": 216.0,
|
|
"Beef Per Ton": 1045.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Pioneer",
|
|
"product": "P1742Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 16.1,
|
|
"Milk Per Acre": 3082.0,
|
|
"Milk Per Ton": 14886.0,
|
|
"Beef Per Acre": 233.0,
|
|
"Beef Per Ton": 1062.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Augusta",
|
|
"product": "Seed",
|
|
"traits": "A1964-DV",
|
|
"metrics": {
|
|
"Ton/Acre": 16.1,
|
|
"Milk Per Acre": 2822.0,
|
|
"Milk Per Ton": 13630.0,
|
|
"Beef Per Acre": 188.0,
|
|
"Beef Per Ton": 987.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"brand": "DEKALB",
|
|
"product": "DKC115-81",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 16.0,
|
|
"Milk Per Acre": 3021.0,
|
|
"Milk Per Ton": 14501.0,
|
|
"Beef Per Acre": 196.0,
|
|
"Beef Per Ton": 994.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "DEKALB",
|
|
"product": "DKC67-66",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 15.7,
|
|
"Milk Per Acre": 2777.0,
|
|
"Milk Per Ton": 13080.0,
|
|
"Beef Per Acre": 173.0,
|
|
"Beef Per Ton": 939.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"brand": "Augusta",
|
|
"product": "Seed",
|
|
"traits": "A4465-DV",
|
|
"metrics": {
|
|
"Ton/Acre": 15.6,
|
|
"Milk Per Acre": 2828.0,
|
|
"Milk Per Ton": 13235.0,
|
|
"Beef Per Acre": 185.0,
|
|
"Beef Per Ton": 951.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"brand": "DEKALB",
|
|
"product": "DKC70-64",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 15.4,
|
|
"Milk Per Acre": 2886.0,
|
|
"Milk Per Ton": 13333.0,
|
|
"Beef Per Acre": 206.0,
|
|
"Beef Per Ton": 971.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "DEKALB",
|
|
"product": "DKC70-94",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 15.2,
|
|
"Milk Per Acre": 2711.0,
|
|
"Milk Per Ton": 12362.0,
|
|
"Beef Per Acre": 176.0,
|
|
"Beef Per Ton": 914.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "Pioneer",
|
|
"product": "P17677Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 14.7,
|
|
"Milk Per Acre": 3072.0,
|
|
"Milk Per Ton": 13548.0,
|
|
"Beef Per Acre": 238.0,
|
|
"Beef Per Ton": 976.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 18,
|
|
"brand": "Pioneer",
|
|
"product": "P14830Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 14.5,
|
|
"Milk Per Acre": 2948.0,
|
|
"Milk Per Ton": 12824.0,
|
|
"Beef Per Acre": 212.0,
|
|
"Beef Per Ton": 924.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 19,
|
|
"brand": "Augusta",
|
|
"product": "Seed",
|
|
"traits": "A2064-D",
|
|
"metrics": {
|
|
"Ton/Acre": 14.0,
|
|
"Milk Per Acre": 3004.0,
|
|
"Milk Per Ton": 12617.0,
|
|
"Beef Per Acre": 213.0,
|
|
"Beef Per Ton": 894.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 20,
|
|
"brand": "DEKALB",
|
|
"product": "Experimental",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 13.7,
|
|
"Milk Per Acre": 2932.0,
|
|
"Milk Per Ton": 12051.0,
|
|
"Beef Per Acre": 207.0,
|
|
"Beef Per Ton": 866.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 21,
|
|
"brand": "Pioneer",
|
|
"product": "P13777PCUE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 13.4,
|
|
"Milk Per Acre": 3119.0,
|
|
"Milk Per Ton": 12538.0,
|
|
"Beef Per Acre": 240.0,
|
|
"Beef Per Ton": 893.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 22,
|
|
"brand": "DEKALB",
|
|
"product": "DKC105-25",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 13.0,
|
|
"Milk Per Acre": 3155.0,
|
|
"Milk Per Ton": 12305.0,
|
|
"Beef Per Acre": 237.0,
|
|
"Beef Per Ton": 862.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 23,
|
|
"brand": "Enogen",
|
|
"product": "E114C4-DV-LL",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 11.9,
|
|
"Milk Per Acre": 2958.0,
|
|
"Milk Per Ton": 10560.0,
|
|
"Beef Per Acre": 204.0,
|
|
"Beef Per Ton": 748.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 24,
|
|
"brand": "DEKALB",
|
|
"product": "Experimental",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 10.7,
|
|
"Milk Per Acre": 2861.0,
|
|
"Milk Per Ton": 9184.0,
|
|
"Beef Per Acre": 196.0,
|
|
"Beef Per Ton": 664.0
|
|
},
|
|
"entry_num": null
|
|
}
|
|
],
|
|
"n_results": 24,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/silage/plot-report/tn/2024/2435174"
|
|
],
|
|
"fetched_at": "2026-05-25T19:39:53.577727+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|