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>
222 lines
4.9 KiB
JSON
222 lines
4.9 KiB
JSON
{
|
|
"source": "gh_plot_reports",
|
|
"source_key": "ghpr-silage-mo-2025-2465957",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "silage",
|
|
"state": "Missouri",
|
|
"state_abbrev": "mo",
|
|
"year": 2025,
|
|
"plot_id": "2465957",
|
|
"cooperator": "Heins Family Farm",
|
|
"planted_date": "2025-04-18",
|
|
"harvested_date": "2025-08-25",
|
|
"population_seeds_per_acre": 34000,
|
|
"row_width_in": 30,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "Pioneer",
|
|
"product": "P13777PCUE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 36.0,
|
|
"Milk Per Acre": 3240.0,
|
|
"Milk Per Ton": 34968.0,
|
|
"Beef Per Acre": 254.0,
|
|
"Beef Per Ton": 2453.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "Pioneer",
|
|
"product": "P14830AML",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 34.1,
|
|
"Milk Per Acre": 3174.0,
|
|
"Milk Per Ton": 32500.0,
|
|
"Beef Per Acre": 263.0,
|
|
"Beef Per Ton": 2359.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 3,
|
|
"brand": "DEKALB",
|
|
"product": "DKC68-35",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 33.0,
|
|
"Milk Per Acre": 3576.0,
|
|
"Milk Per Ton": 35407.0,
|
|
"Beef Per Acre": 281.0,
|
|
"Beef Per Ton": 2348.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "Pioneer",
|
|
"product": "P17677AM",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 32.4,
|
|
"Milk Per Acre": 3299.0,
|
|
"Milk Per Ton": 32083.0,
|
|
"Beef Per Acre": 240.0,
|
|
"Beef Per Ton": 2161.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "DEKALB",
|
|
"product": "DKC115-81",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 32.0,
|
|
"Milk Per Acre": 3291.0,
|
|
"Milk Per Ton": 31616.0,
|
|
"Beef Per Acre": 241.0,
|
|
"Beef Per Ton": 2138.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "DEKALB",
|
|
"product": "DKC113-62",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 31.9,
|
|
"Milk Per Acre": 3308.0,
|
|
"Milk Per Ton": 31701.0,
|
|
"Beef Per Acre": 263.0,
|
|
"Beef Per Ton": 2207.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"brand": "Pioneer",
|
|
"product": "P17623PCE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 31.8,
|
|
"Milk Per Acre": 3333.0,
|
|
"Milk Per Ton": 31774.0,
|
|
"Beef Per Acre": 261.0,
|
|
"Beef Per Ton": 2190.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "Enogen",
|
|
"product": "E111V7-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 31.6,
|
|
"Milk Per Acre": 3074.0,
|
|
"Milk Per Ton": 29138.0,
|
|
"Beef Per Acre": 248.0,
|
|
"Beef Per Ton": 2132.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 9,
|
|
"brand": "Enogen",
|
|
"product": "E114C4-DV-LL",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 31.4,
|
|
"Milk Per Acre": 3290.0,
|
|
"Milk Per Ton": 31024.0,
|
|
"Beef Per Acre": 254.0,
|
|
"Beef Per Ton": 2141.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Pioneer",
|
|
"product": "P14364PCUE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 30.8,
|
|
"Milk Per Acre": 3318.0,
|
|
"Milk Per Ton": 30706.0,
|
|
"Beef Per Acre": 251.0,
|
|
"Beef Per Ton": 2091.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 11,
|
|
"brand": "DEKALB",
|
|
"product": "DKC67-44",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 30.7,
|
|
"Milk Per Acre": 3277.0,
|
|
"Milk Per Ton": 30162.0,
|
|
"Beef Per Acre": 255.0,
|
|
"Beef Per Ton": 2093.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"brand": "DEKALB",
|
|
"product": "DKC67-66",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 30.5,
|
|
"Milk Per Acre": 3400.0,
|
|
"Milk Per Ton": 31121.0,
|
|
"Beef Per Acre": 253.0,
|
|
"Beef Per Ton": 2076.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "Enogen",
|
|
"product": "E117Z7-D",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 29.2,
|
|
"Milk Per Acre": 3221.0,
|
|
"Milk Per Ton": 28219.0,
|
|
"Beef Per Acre": 245.0,
|
|
"Beef Per Ton": 1961.0
|
|
},
|
|
"entry_num": null
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"brand": "DEKALB",
|
|
"product": "DKC111-02",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Ton/Acre": 26.5,
|
|
"Milk Per Acre": 3130.0,
|
|
"Milk Per Ton": 24856.0,
|
|
"Beef Per Acre": 262.0,
|
|
"Beef Per Ton": 1827.0
|
|
},
|
|
"entry_num": null
|
|
}
|
|
],
|
|
"n_results": 14,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/silage/plot-report/mo/2025/2465957"
|
|
],
|
|
"fetched_at": "2026-05-25T19:43:29.656033+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|