justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
bd71f30ca72067d8939bcab40ea565397cc8c216
seed-mcp/corpus/gh_plot_reports/ghpr-silage-wi-2025-2465995.json
T
justin 0e625553e5 gh_plot_reports corpus (4,299 plots) + concurrency + 4-GPU pool 
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>
2026-05-25 16:46:35 -04:00

418 lines
9.1 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-silage-wi-2025-2465995",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "silage",
"state": "Wisconsin",
"state_abbrev": "wi",
"year": 2025,
"plot_id": "2465995",
"cooperator": "Prairie Ag Services Inc",
"planted_date": "2025-05-07",
"harvested_date": "2025-09-17",
"population_seeds_per_acre": 33000,
"row_width_in": 30,
"results": [
{
"rank": 1,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 32.1,
"Milk Per Acre": 3288.0,
"Milk Per Ton": 31694.0,
"Beef Per Acre": 239.0,
"Beef Per Ton": 2137.0
},
"entry_num": null
},
{
"rank": 2,
"brand": "NK",
"product": "NK0025-DV",
"traits": "",
"metrics": {
"Ton/Acre": 29.4,
"Milk Per Acre": 3117.0,
"Milk Per Ton": 27478.0,
"Beef Per Acre": 211.0,
"Beef Per Ton": 1869.0
},
"entry_num": null
},
{
"rank": 3,
"brand": "NK",
"product": "NK0604-DV",
"traits": "",
"metrics": {
"Ton/Acre": 28.9,
"Milk Per Acre": 3297.0,
"Milk Per Ton": 28583.0,
"Beef Per Acre": 218.0,
"Beef Per Ton": 1860.0
},
"entry_num": null
},
{
"rank": 4,
"brand": "NK",
"product": "NK0604-DV",
"traits": "",
"metrics": {
"Ton/Acre": 28.6,
"Milk Per Acre": 3390.0,
"Milk Per Ton": 29080.0,
"Beef Per Acre": 244.0,
"Beef Per Ton": 1919.0
},
"entry_num": null
},
{
"rank": 5,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 27.9,
"Milk Per Acre": 3162.0,
"Milk Per Ton": 26466.0,
"Beef Per Acre": 221.0,
"Beef Per Ton": 1804.0
},
"entry_num": null
},
{
"rank": 6,
"brand": "DEKALB",
"product": "DKC105-33",
"traits": "",
"metrics": {
"Ton/Acre": 27.4,
"Milk Per Acre": 3055.0,
"Milk Per Ton": 25073.0,
"Beef Per Acre": 204.0,
"Beef Per Ton": 1720.0
},
"entry_num": null
},
{
"rank": 7,
"brand": "Enogen",
"product": "E092W5-D",
"traits": "",
"metrics": {
"Ton/Acre": 27.3,
"Milk Per Acre": 3364.0,
"Milk Per Ton": 27544.0,
"Beef Per Acre": 251.0,
"Beef Per Ton": 1850.0
},
"entry_num": null
},
{
"rank": 8,
"brand": "Enogen",
"product": "E095D3-D",
"traits": "",
"metrics": {
"Ton/Acre": 27.1,
"Milk Per Acre": 3053.0,
"Milk Per Ton": 24800.0,
"Beef Per Acre": 193.0,
"Beef Per Ton": 1672.0
},
"entry_num": null
},
{
"rank": 8,
"brand": "Enogen",
"product": "E108K4-DV",
"traits": "",
"metrics": {
"Ton/Acre": 27.1,
"Milk Per Acre": 3141.0,
"Milk Per Ton": 25529.0,
"Beef Per Acre": 217.0,
"Beef Per Ton": 1741.0
},
"entry_num": null
},
{
"rank": 10,
"brand": "Enogen",
"product": "E102K7-D",
"traits": "",
"metrics": {
"Ton/Acre": 26.9,
"Milk Per Acre": 3065.0,
"Milk Per Ton": 24755.0,
"Beef Per Acre": 205.0,
"Beef Per Ton": 1696.0
},
"entry_num": null
},
{
"rank": 11,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 26.3,
"Milk Per Acre": 3303.0,
"Milk Per Ton": 26045.0,
"Beef Per Acre": 226.0,
"Beef Per Ton": 1712.0
},
"entry_num": null
},
{
"rank": 12,
"brand": "DEKALB",
"product": "DKC105-33",
"traits": "",
"metrics": {
"Ton/Acre": 26.2,
"Milk Per Acre": 3480.0,
"Milk Per Ton": 27362.0,
"Beef Per Acre": 263.0,
"Beef Per Ton": 1812.0
},
"entry_num": null
},
{
"rank": 13,
"brand": "NK",
"product": "NK9771-DV",
"traits": "",
"metrics": {
"Ton/Acre": 26.1,
"Milk Per Acre": 3229.0,
"Milk Per Ton": 25284.0,
"Beef Per Acre": 229.0,
"Beef Per Ton": 1710.0
},
"entry_num": null
},
{
"rank": 14,
"brand": "Enogen",
"product": "E102K7-D",
"traits": "",
"metrics": {
"Ton/Acre": 25.9,
"Milk Per Acre": 3159.0,
"Milk Per Ton": 24522.0,
"Beef Per Acre": 217.0,
"Beef Per Ton": 1663.0
},
"entry_num": null
},
{
"rank": 14,
"brand": "NK",
"product": "NK0440-AT",
"traits": "",
"metrics": {
"Ton/Acre": 25.9,
"Milk Per Acre": 3285.0,
"Milk Per Ton": 25564.0,
"Beef Per Acre": 229.0,
"Beef Per Ton": 1699.0
},
"entry_num": null
},
{
"rank": 16,
"brand": "NK",
"product": "NK0440-AT",
"traits": "",
"metrics": {
"Ton/Acre": 25.7,
"Milk Per Acre": 3196.0,
"Milk Per Ton": 24649.0,
"Beef Per Acre": 209.0,
"Beef Per Ton": 1631.0
},
"entry_num": null
},
{
"rank": 17,
"brand": "Enogen",
"product": "E097K6-D",
"traits": "",
"metrics": {
"Ton/Acre": 25.6,
"Milk Per Acre": 3200.0,
"Milk Per Ton": 24578.0,
"Beef Per Acre": 240.0,
"Beef Per Ton": 1706.0
},
"entry_num": null
},
{
"rank": 18,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 24.8,
"Milk Per Acre": 3210.0,
"Milk Per Ton": 23919.0,
"Beef Per Acre": 209.0,
"Beef Per Ton": 1576.0
},
"entry_num": null
},
{
"rank": 19,
"brand": "NK",
"product": "NK9771-DV",
"traits": "",
"metrics": {
"Ton/Acre": 23.9,
"Milk Per Acre": 3135.0,
"Milk Per Ton": 22472.0,
"Beef Per Acre": 211.0,
"Beef Per Ton": 1521.0
},
"entry_num": null
},
{
"rank": 20,
"brand": "Enogen",
"product": "E094Z4-D",
"traits": "",
"metrics": {
"Ton/Acre": 23.3,
"Milk Per Acre": 2942.0,
"Milk Per Ton": 20604.0,
"Beef Per Acre": 181.0,
"Beef Per Ton": 1415.0
},
"entry_num": null
},
{
"rank": 20,
"brand": "NK",
"product": "NK0025-DV",
"traits": "",
"metrics": {
"Ton/Acre": 23.3,
"Milk Per Acre": 3232.0,
"Milk Per Ton": 22576.0,
"Beef Per Acre": 248.0,
"Beef Per Ton": 1571.0
},
"entry_num": null
},
{
"rank": 22,
"brand": "Pioneer",
"product": "P0275Q",
"traits": "",
"metrics": {
"Ton/Acre": 22.5,
"Milk Per Acre": 3325.0,
"Milk Per Ton": 22428.0,
"Beef Per Acre": 242.0,
"Beef Per Ton": 1503.0
},
"entry_num": null
},
{
"rank": 23,
"brand": "Enogen",
"product": "E097K6-D",
"traits": "",
"metrics": {
"Ton/Acre": 22.3,
"Milk Per Acre": 3126.0,
"Milk Per Ton": 20887.0,
"Beef Per Acre": 209.0,
"Beef Per Ton": 1413.0
},
"entry_num": null
},
{
"rank": 24,
"brand": "Pioneer",
"product": "P0275Q",
"traits": "",
"metrics": {
"Ton/Acre": 20.4,
"Milk Per Acre": 3293.0,
"Milk Per Ton": 20117.0,
"Beef Per Acre": 227.0,
"Beef Per Ton": 1329.0
},
"entry_num": null
},
{
"rank": 25,
"brand": "Enogen",
"product": "E108K4-DV",
"traits": "",
"metrics": {
"Ton/Acre": 20.0,
"Milk Per Acre": 3374.0,
"Milk Per Ton": 20195.0,
"Beef Per Acre": 235.0,
"Beef Per Ton": 1320.0
},
"entry_num": null
},
{
"rank": 26,
"brand": "Enogen",
"product": "E094Z4-D",
"traits": "",
"metrics": {
"Ton/Acre": 19.6,
"Milk Per Acre": 3147.0,
"Milk Per Ton": 18498.0,
"Beef Per Acre": 225.0,
"Beef Per Ton": 1274.0
},
"entry_num": null
},
{
"rank": 27,
"brand": "Enogen",
"product": "E095D3-D",
"traits": "",
"metrics": {
"Ton/Acre": 19.3,
"Milk Per Acre": 3159.0,
"Milk Per Ton": 18300.0,
"Beef Per Acre": 230.0,
"Beef Per Ton": 1266.0
},
"entry_num": null
},
{
"rank": 28,
"brand": "Enogen",
"product": "E092W5-D",
"traits": "",
"metrics": {
"Ton/Acre": 19.2,
"Milk Per Acre": 3165.0,
"Milk Per Ton": 18233.0,
"Beef Per Acre": 214.0,
"Beef Per Ton": 1227.0
},
"entry_num": null
}
],
"n_results": 28,
"source_urls": [
"https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2465995"
],
"fetched_at": "2026-05-25T19:43:34.680966+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink