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-ut-2024-2452510",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "silage",
|
|
"state": "Utah",
|
|
"state_abbrev": "ut",
|
|
"year": 2024,
|
|
"plot_id": "2452510",
|
|
"cooperator": "Holt Farms (Modena)",
|
|
"planted_date": "2024-05-10",
|
|
"harvested_date": "2024-09-10",
|
|
"population_seeds_per_acre": 40000,
|
|
"row_width_in": 22,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "Axis",
|
|
"product": "Seed",
|
|
"traits": "Experimental",
|
|
"metrics": {
|
|
"Ton/Acre": 32.0,
|
|
"Milk Per Acre": 3576.0,
|
|
"Milk Per Ton": 32078.0,
|
|
"Beef Per Acre": 227.0,
|
|
"Beef Per Ton": 2175.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "Pioneer",
|
|
"product": "P9489AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 31.8,
|
|
"Milk Per Acre": 3647.0,
|
|
"Milk Per Ton": 34361.0,
|
|
"Beef Per Acre": 233.0,
|
|
"Beef Per Ton": 2226.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 3,
|
|
"brand": "Pioneer",
|
|
"product": "P9193AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 30.8,
|
|
"Milk Per Acre": 3671.0,
|
|
"Milk Per Ton": 33257.0,
|
|
"Beef Per Acre": 237.0,
|
|
"Beef Per Ton": 2185.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "PGS",
|
|
"product": "Hybrids",
|
|
"traits": "4291",
|
|
"metrics": {
|
|
"Ton/Acre": 30.7,
|
|
"Milk Per Acre": 3733.0,
|
|
"Milk Per Ton": 35353.0,
|
|
"Beef Per Acre": 243.0,
|
|
"Beef Per Ton": 2243.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "Pioneer",
|
|
"product": "P90630AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 30.6,
|
|
"Milk Per Acre": 3678.0,
|
|
"Milk Per Ton": 33099.0,
|
|
"Beef Per Acre": 233.0,
|
|
"Beef Per Ton": 2144.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "Pioneer",
|
|
"product": "P9492AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 30.0,
|
|
"Milk Per Acre": 3477.0,
|
|
"Milk Per Ton": 29370.0,
|
|
"Beef Per Acre": 227.0,
|
|
"Beef Per Ton": 2038.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"brand": "PGS",
|
|
"product": "Hybrids",
|
|
"traits": "4292",
|
|
"metrics": {
|
|
"Ton/Acre": 29.6,
|
|
"Milk Per Acre": 3723.0,
|
|
"Milk Per Ton": 32469.0,
|
|
"Beef Per Acre": 240.0,
|
|
"Beef Per Ton": 2133.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "NK",
|
|
"product": "NK9044-AA",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 29.4,
|
|
"Milk Per Acre": 3535.0,
|
|
"Milk Per Ton": 31103.0,
|
|
"Beef Per Acre": 233.0,
|
|
"Beef Per Ton": 2060.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 9,
|
|
"brand": "Axis",
|
|
"product": "Seed",
|
|
"traits": "Experimental",
|
|
"metrics": {
|
|
"Ton/Acre": 28.7,
|
|
"Milk Per Acre": 3700.0,
|
|
"Milk Per Ton": 32738.0,
|
|
"Beef Per Acre": 243.0,
|
|
"Beef Per Ton": 2091.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Western",
|
|
"product": "Hybrids",
|
|
"traits": "2290",
|
|
"metrics": {
|
|
"Ton/Acre": 28.1,
|
|
"Milk Per Acre": 3287.0,
|
|
"Milk Per Ton": 26849.0,
|
|
"Beef Per Acre": 223.0,
|
|
"Beef Per Ton": 1882.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 11,
|
|
"brand": "DEKALB",
|
|
"product": "DKC39-54",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 27.9,
|
|
"Milk Per Acre": 3168.0,
|
|
"Milk Per Ton": 28945.0,
|
|
"Beef Per Acre": 230.0,
|
|
"Beef Per Ton": 1925.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"brand": "Axis",
|
|
"product": "Seed",
|
|
"traits": "Experimental",
|
|
"metrics": {
|
|
"Ton/Acre": 27.7,
|
|
"Milk Per Acre": 3675.0,
|
|
"Milk Per Ton": 32130.0,
|
|
"Beef Per Acre": 247.0,
|
|
"Beef Per Ton": 2050.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "Western",
|
|
"product": "Hybrids",
|
|
"traits": "3S284",
|
|
"metrics": {
|
|
"Ton/Acre": 27.6,
|
|
"Milk Per Acre": 3294.0,
|
|
"Milk Per Ton": 27662.0,
|
|
"Beef Per Acre": 223.0,
|
|
"Beef Per Ton": 1848.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"brand": "Axis",
|
|
"product": "Seed",
|
|
"traits": "36Q52",
|
|
"metrics": {
|
|
"Ton/Acre": 27.3,
|
|
"Milk Per Acre": 3566.0,
|
|
"Milk Per Ton": 28396.0,
|
|
"Beef Per Acre": 230.0,
|
|
"Beef Per Ton": 1881.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"brand": "Western",
|
|
"product": "Hybrids",
|
|
"traits": "5DR3387",
|
|
"metrics": {
|
|
"Ton/Acre": 26.9,
|
|
"Milk Per Acre": 3393.0,
|
|
"Milk Per Ton": 26977.0,
|
|
"Beef Per Acre": 227.0,
|
|
"Beef Per Ton": 1829.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "Legacy",
|
|
"product": "Seeds",
|
|
"traits": "LC414-21 VT2P",
|
|
"metrics": {
|
|
"Ton/Acre": 26.7,
|
|
"Milk Per Acre": 3361.0,
|
|
"Milk Per Ton": 25629.0,
|
|
"Beef Per Acre": 223.0,
|
|
"Beef Per Ton": 1792.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "NK",
|
|
"product": "NK8558-AA",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 26.6,
|
|
"Milk Per Acre": 3365.0,
|
|
"Milk Per Ton": 26885.0,
|
|
"Beef Per Acre": 223.0,
|
|
"Beef Per Ton": 1785.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 18,
|
|
"brand": "DEKALB",
|
|
"product": "DKC31-85",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 26.1,
|
|
"Milk Per Acre": 3286.0,
|
|
"Milk Per Ton": 25559.0,
|
|
"Beef Per Acre": 220.0,
|
|
"Beef Per Ton": 1722.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 19,
|
|
"brand": "Western",
|
|
"product": "Hybrids",
|
|
"traits": "5P1484",
|
|
"metrics": {
|
|
"Ton/Acre": 26.0,
|
|
"Milk Per Acre": 3306.0,
|
|
"Milk Per Ton": 25156.0,
|
|
"Beef Per Acre": 217.0,
|
|
"Beef Per Ton": 1692.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 20,
|
|
"brand": "NK",
|
|
"product": "NK8005-V",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 25.9,
|
|
"Milk Per Acre": 3301.0,
|
|
"Milk Per Ton": 26106.0,
|
|
"Beef Per Acre": 220.0,
|
|
"Beef Per Ton": 1707.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 20,
|
|
"brand": "Pioneer",
|
|
"product": "P8294AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 25.9,
|
|
"Milk Per Acre": 3191.0,
|
|
"Milk Per Ton": 24949.0,
|
|
"Beef Per Acre": 217.0,
|
|
"Beef Per Ton": 1681.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 22,
|
|
"brand": "DEKALB",
|
|
"product": "DKC32-35",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 24.1,
|
|
"Milk Per Acre": 3244.0,
|
|
"Milk Per Ton": 23751.0,
|
|
"Beef Per Acre": 220.0,
|
|
"Beef Per Ton": 1593.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 22,
|
|
"brand": "Pioneer",
|
|
"product": "P87040AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 24.1,
|
|
"Milk Per Acre": 3428.0,
|
|
"Milk Per Ton": 24278.0,
|
|
"Beef Per Acre": 223.0,
|
|
"Beef Per Ton": 1612.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 24,
|
|
"brand": "DEKALB",
|
|
"product": "DKC35-34",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 23.2,
|
|
"Milk Per Acre": 3465.0,
|
|
"Milk Per Ton": 24267.0,
|
|
"Beef Per Acre": 227.0,
|
|
"Beef Per Ton": 1578.0
|
|
},
|
|
"entry_num": null
|
|
}
|
|
],
|
|
"n_results": 24,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/silage/plot-report/ut/2024/2452510"
|
|
],
|
|
"fetched_at": "2026-05-25T19:41:42.922841+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|