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>
390 lines
8.8 KiB
JSON
390 lines
8.8 KiB
JSON
{
|
|
"source": "gh_plot_reports",
|
|
"source_key": "ghpr-silage-ga-2024-2462608",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "silage",
|
|
"state": "Georgia",
|
|
"state_abbrev": "ga",
|
|
"year": 2024,
|
|
"plot_id": "2462608",
|
|
"cooperator": "University of Georgia - Plains, GA",
|
|
"planted_date": "2024-04-10",
|
|
"harvested_date": "2024-07-21",
|
|
"population_seeds_per_acre": 36000,
|
|
"row_width_in": null,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "DEKALB",
|
|
"product": "DKC68-35",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 38.8,
|
|
"Milk Per Acre": 3269.0,
|
|
"Milk Per Ton": 38018.0,
|
|
"Beef Per Acre": 234.0,
|
|
"Beef Per Ton": 2722.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "Innvictis",
|
|
"product": "Seed",
|
|
"traits": "Solutions A1993T",
|
|
"metrics": {
|
|
"Ton/Acre": 38.7,
|
|
"Milk Per Acre": 3393.0,
|
|
"Milk Per Ton": 39423.0,
|
|
"Beef Per Acre": 240.0,
|
|
"Beef Per Ton": 2793.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 3,
|
|
"brand": "BH",
|
|
"product": "Genetics",
|
|
"traits": "BH 8705VIP3110",
|
|
"metrics": {
|
|
"Ton/Acre": 38.6,
|
|
"Milk Per Acre": 3335.0,
|
|
"Milk Per Ton": 38659.0,
|
|
"Beef Per Acre": 237.0,
|
|
"Beef Per Ton": 2747.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "BH",
|
|
"product": "Genetics",
|
|
"traits": "BH 8690VIP3110",
|
|
"metrics": {
|
|
"Ton/Acre": 38.3,
|
|
"Milk Per Acre": 3295.0,
|
|
"Milk Per Ton": 37890.0,
|
|
"Beef Per Acre": 235.0,
|
|
"Beef Per Ton": 2706.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "BH",
|
|
"product": "Genetics",
|
|
"traits": "Experimental",
|
|
"metrics": {
|
|
"Ton/Acre": 37.6,
|
|
"Milk Per Acre": 3436.0,
|
|
"Milk Per Ton": 38712.0,
|
|
"Beef Per Acre": 242.0,
|
|
"Beef Per Ton": 2723.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "BH",
|
|
"product": "Genetics",
|
|
"traits": "BH 8721VT2P",
|
|
"metrics": {
|
|
"Ton/Acre": 37.2,
|
|
"Milk Per Acre": 3421.0,
|
|
"Milk Per Ton": 38175.0,
|
|
"Beef Per Acre": 241.0,
|
|
"Beef Per Ton": 2693.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed 6915 TRE",
|
|
"metrics": {
|
|
"Ton/Acre": 36.9,
|
|
"Milk Per Acre": 3345.0,
|
|
"Milk Per Ton": 37042.0,
|
|
"Beef Per Acre": 238.0,
|
|
"Beef Per Ton": 2632.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "Revere",
|
|
"product": "Seed",
|
|
"traits": "Revere 1839 TC",
|
|
"metrics": {
|
|
"Ton/Acre": 36.7,
|
|
"Milk Per Acre": 3422.0,
|
|
"Milk Per Ton": 37711.0,
|
|
"Beef Per Acre": 241.0,
|
|
"Beef Per Ton": 2656.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 9,
|
|
"brand": "DEKALB",
|
|
"product": "DKC66-06",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 36.5,
|
|
"Milk Per Acre": 3371.0,
|
|
"Milk Per Ton": 36949.0,
|
|
"Beef Per Acre": 239.0,
|
|
"Beef Per Ton": 2620.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "AgraTech",
|
|
"product": "AT",
|
|
"traits": "79VT2P",
|
|
"metrics": {
|
|
"Ton/Acre": 36.1,
|
|
"Milk Per Acre": 3417.0,
|
|
"Milk Per Ton": 37022.0,
|
|
"Beef Per Acre": 241.0,
|
|
"Beef Per Ton": 2611.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 11,
|
|
"brand": "Innvictis",
|
|
"product": "Seed",
|
|
"traits": "Solutions A1792T",
|
|
"metrics": {
|
|
"Ton/Acre": 36.0,
|
|
"Milk Per Acre": 3464.0,
|
|
"Milk Per Ton": 37437.0,
|
|
"Beef Per Acre": 243.0,
|
|
"Beef Per Ton": 2630.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 11,
|
|
"brand": "Pioneer",
|
|
"product": "P17677YHR",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 36.0,
|
|
"Milk Per Acre": 3333.0,
|
|
"Milk Per Ton": 36022.0,
|
|
"Beef Per Acre": 237.0,
|
|
"Beef Per Ton": 2565.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed 6891 AS3110",
|
|
"metrics": {
|
|
"Ton/Acre": 35.8,
|
|
"Milk Per Acre": 3133.0,
|
|
"Milk Per Ton": 33604.0,
|
|
"Beef Per Acre": 228.0,
|
|
"Beef Per Ton": 2449.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"brand": "DEKALB",
|
|
"product": "DKC70-45",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 35.7,
|
|
"Milk Per Acre": 3328.0,
|
|
"Milk Per Ton": 35650.0,
|
|
"Beef Per Acre": 237.0,
|
|
"Beef Per Ton": 2539.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"brand": "Enogen",
|
|
"product": "E114C4-DV-LL",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 35.3,
|
|
"Milk Per Acre": 3373.0,
|
|
"Milk Per Ton": 35759.0,
|
|
"Beef Per Acre": 239.0,
|
|
"Beef Per Ton": 2537.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed Experimental",
|
|
"metrics": {
|
|
"Ton/Acre": 35.2,
|
|
"Milk Per Acre": 3491.0,
|
|
"Milk Per Ton": 36816.0,
|
|
"Beef Per Acre": 244.0,
|
|
"Beef Per Ton": 2577.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "BH",
|
|
"product": "Genetics",
|
|
"traits": "BH 8420VIP3110",
|
|
"metrics": {
|
|
"Ton/Acre": 35.0,
|
|
"Milk Per Acre": 3337.0,
|
|
"Milk Per Ton": 35069.0,
|
|
"Beef Per Acre": 237.0,
|
|
"Beef Per Ton": 2491.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed 6493 VT2P",
|
|
"metrics": {
|
|
"Ton/Acre": 35.0,
|
|
"Milk Per Acre": 3406.0,
|
|
"Milk Per Ton": 35809.0,
|
|
"Beef Per Acre": 241.0,
|
|
"Beef Per Ton": 2530.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed 6641 SS",
|
|
"metrics": {
|
|
"Ton/Acre": 35.0,
|
|
"Milk Per Acre": 3266.0,
|
|
"Milk Per Ton": 34275.0,
|
|
"Beef Per Acre": 234.0,
|
|
"Beef Per Ton": 2453.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 20,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed 6709 VT2P",
|
|
"metrics": {
|
|
"Ton/Acre": 34.9,
|
|
"Milk Per Acre": 3224.0,
|
|
"Milk Per Ton": 33736.0,
|
|
"Beef Per Acre": 232.0,
|
|
"Beef Per Ton": 2435.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 21,
|
|
"brand": "NK",
|
|
"product": "NK1402-DV",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 34.1,
|
|
"Milk Per Acre": 3435.0,
|
|
"Milk Per Ton": 35167.0,
|
|
"Beef Per Acre": 243.0,
|
|
"Beef Per Ton": 2489.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 21,
|
|
"brand": "Revere",
|
|
"product": "Seed",
|
|
"traits": "Revere 1627 TC",
|
|
"metrics": {
|
|
"Ton/Acre": 34.1,
|
|
"Milk Per Acre": 3174.0,
|
|
"Milk Per Ton": 32510.0,
|
|
"Beef Per Acre": 231.0,
|
|
"Beef Per Ton": 2370.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 21,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed 6864 RR",
|
|
"metrics": {
|
|
"Ton/Acre": 34.1,
|
|
"Milk Per Acre": 3421.0,
|
|
"Milk Per Ton": 35027.0,
|
|
"Beef Per Acre": 242.0,
|
|
"Beef Per Ton": 2474.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 24,
|
|
"brand": "Enogen",
|
|
"product": "E117Z7-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 32.6,
|
|
"Milk Per Acre": 3241.0,
|
|
"Milk Per Ton": 31736.0,
|
|
"Beef Per Acre": 233.0,
|
|
"Beef Per Ton": 2285.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 25,
|
|
"brand": "BH",
|
|
"product": "Genetics",
|
|
"traits": "Experimental",
|
|
"metrics": {
|
|
"Ton/Acre": 31.3,
|
|
"Milk Per Acre": 3306.0,
|
|
"Milk Per Ton": 31089.0,
|
|
"Beef Per Acre": 236.0,
|
|
"Beef Per Ton": 2219.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 26,
|
|
"brand": "BH",
|
|
"product": "Genetics",
|
|
"traits": "Experimental",
|
|
"metrics": {
|
|
"Ton/Acre": 31.0,
|
|
"Milk Per Acre": 3436.0,
|
|
"Milk Per Ton": 31998.0,
|
|
"Beef Per Acre": 242.0,
|
|
"Beef Per Ton": 2257.0
|
|
},
|
|
"entry_num": null
|
|
}
|
|
],
|
|
"n_results": 26,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/silage/plot-report/ga/2024/2462608"
|
|
],
|
|
"fetched_at": "2026-05-25T19:41:56.379621+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|