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-2024-2419091",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "silage",
|
|
"state": "Wisconsin",
|
|
"state_abbrev": "wi",
|
|
"year": 2024,
|
|
"plot_id": "2419091",
|
|
"cooperator": "Prairie Ag Services Inc",
|
|
"planted_date": "2024-05-01",
|
|
"harvested_date": "2024-08-26",
|
|
"population_seeds_per_acre": 34000,
|
|
"row_width_in": 30,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "NK",
|
|
"product": "NK9771-DV",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 27.6,
|
|
"Milk Per Acre": 3327.0,
|
|
"Milk Per Ton": 27588.0,
|
|
"Beef Per Acre": 235.0,
|
|
"Beef Per Ton": 1827.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "NK",
|
|
"product": "NK9805-DV",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 27.4,
|
|
"Milk Per Acre": 3321.0,
|
|
"Milk Per Ton": 27299.0,
|
|
"Beef Per Acre": 221.0,
|
|
"Beef Per Ton": 1771.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 3,
|
|
"brand": "Enogen",
|
|
"product": "E105Z5-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 26.7,
|
|
"Milk Per Acre": 3356.0,
|
|
"Milk Per Ton": 26896.0,
|
|
"Beef Per Acre": 233.0,
|
|
"Beef Per Ton": 1760.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "NK",
|
|
"product": "NK0252-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 26.4,
|
|
"Milk Per Acre": 3428.0,
|
|
"Milk Per Ton": 27153.0,
|
|
"Beef Per Acre": 248.0,
|
|
"Beef Per Ton": 1783.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "Pioneer",
|
|
"product": "P0275Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 26.2,
|
|
"Milk Per Acre": 3256.0,
|
|
"Milk Per Ton": 25627.0,
|
|
"Beef Per Acre": 211.0,
|
|
"Beef Per Ton": 1669.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "Enogen",
|
|
"product": "E092W5-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 25.6,
|
|
"Milk Per Acre": 3757.0,
|
|
"Milk Per Ton": 28832.0,
|
|
"Beef Per Acre": 291.0,
|
|
"Beef Per Ton": 1846.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"brand": "NK",
|
|
"product": "NK9771-DV",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 24.8,
|
|
"Milk Per Acre": 3608.0,
|
|
"Milk Per Ton": 26843.0,
|
|
"Beef Per Acre": 256.0,
|
|
"Beef Per Ton": 1696.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "Pioneer",
|
|
"product": "P0275Q",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 24.7,
|
|
"Milk Per Acre": 3614.0,
|
|
"Milk Per Ton": 26811.0,
|
|
"Beef Per Acre": 265.0,
|
|
"Beef Per Ton": 1716.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 9,
|
|
"brand": "NK",
|
|
"product": "NK0501-DV",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 24.6,
|
|
"Milk Per Acre": 3037.0,
|
|
"Milk Per Ton": 22425.0,
|
|
"Beef Per Acre": 220.0,
|
|
"Beef Per Ton": 1588.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "NK",
|
|
"product": "NK0440-AT",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 24.2,
|
|
"Milk Per Acre": 3279.0,
|
|
"Milk Per Ton": 23789.0,
|
|
"Beef Per Acre": 222.0,
|
|
"Beef Per Ton": 1567.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Enogen",
|
|
"product": "E094Z4-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 24.2,
|
|
"Milk Per Acre": 3574.0,
|
|
"Milk Per Ton": 25944.0,
|
|
"Beef Per Acre": 266.0,
|
|
"Beef Per Ton": 1680.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Enogen",
|
|
"product": "E105Z5-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 24.2,
|
|
"Milk Per Acre": 3320.0,
|
|
"Milk Per Ton": 24081.0,
|
|
"Beef Per Acre": 226.0,
|
|
"Beef Per Ton": 1576.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "Enogen",
|
|
"product": "E107C1-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 23.3,
|
|
"Milk Per Acre": 3101.0,
|
|
"Milk Per Ton": 21714.0,
|
|
"Beef Per Acre": 222.0,
|
|
"Beef Per Ton": 1511.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"brand": "Enogen",
|
|
"product": "E094Z4-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 23.1,
|
|
"Milk Per Acre": 3723.0,
|
|
"Milk Per Ton": 25779.0,
|
|
"Beef Per Acre": 279.0,
|
|
"Beef Per Ton": 1636.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"brand": "NK",
|
|
"product": "NK0440-AT",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 22.8,
|
|
"Milk Per Acre": 3195.0,
|
|
"Milk Per Ton": 21839.0,
|
|
"Beef Per Acre": 226.0,
|
|
"Beef Per Ton": 1485.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "Enogen",
|
|
"product": "E107C1-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 22.5,
|
|
"Milk Per Acre": 3298.0,
|
|
"Milk Per Ton": 22227.0,
|
|
"Beef Per Acre": 244.0,
|
|
"Beef Per Ton": 1507.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "Enogen",
|
|
"product": "E092W5-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 22.3,
|
|
"Milk Per Acre": 3328.0,
|
|
"Milk Per Ton": 22297.0,
|
|
"Beef Per Acre": 237.0,
|
|
"Beef Per Ton": 1481.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 18,
|
|
"brand": "Enogen",
|
|
"product": "E095D3-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 21.6,
|
|
"Milk Per Acre": 3503.0,
|
|
"Milk Per Ton": 22722.0,
|
|
"Beef Per Acre": 244.0,
|
|
"Beef Per Ton": 1451.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 19,
|
|
"brand": "NK",
|
|
"product": "NK0501-DV",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 21.3,
|
|
"Milk Per Acre": 3488.0,
|
|
"Milk Per Ton": 22280.0,
|
|
"Beef Per Acre": 244.0,
|
|
"Beef Per Ton": 1428.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 20,
|
|
"brand": "NK",
|
|
"product": "NK9021-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 21.2,
|
|
"Milk Per Acre": 3470.0,
|
|
"Milk Per Ton": 22083.0,
|
|
"Beef Per Acre": 247.0,
|
|
"Beef Per Ton": 1429.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 21,
|
|
"brand": "NK",
|
|
"product": "NK9805-DV",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 20.6,
|
|
"Milk Per Acre": 3508.0,
|
|
"Milk Per Ton": 21651.0,
|
|
"Beef Per Acre": 258.0,
|
|
"Beef Per Ton": 1411.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 22,
|
|
"brand": "NK",
|
|
"product": "NK9021-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 20.4,
|
|
"Milk Per Acre": 3456.0,
|
|
"Milk Per Ton": 21105.0,
|
|
"Beef Per Acre": 242.0,
|
|
"Beef Per Ton": 1362.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 23,
|
|
"brand": "Enogen",
|
|
"product": "E095D3-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 19.6,
|
|
"Milk Per Acre": 3286.0,
|
|
"Milk Per Ton": 19366.0,
|
|
"Beef Per Acre": 229.0,
|
|
"Beef Per Ton": 1286.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 24,
|
|
"brand": "NK",
|
|
"product": "NK0252-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 18.9,
|
|
"Milk Per Acre": 3624.0,
|
|
"Milk Per Ton": 20534.0,
|
|
"Beef Per Acre": 260.0,
|
|
"Beef Per Ton": 1300.0
|
|
},
|
|
"entry_num": null
|
|
}
|
|
],
|
|
"n_results": 24,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/silage/plot-report/wi/2024/2419091"
|
|
],
|
|
"fetched_at": "2026-05-25T19:31:20.050470+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|