justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
cd4a0f3148156d2d08bd47a8b1b3e6a20b8d3fbb
seed-mcp/corpus/gh_plot_reports/ghpr-silage-wi-2025-2466599.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

348 lines
7.7 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-silage-wi-2025-2466599",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "silage",
"state": "Wisconsin",
"state_abbrev": "wi",
"year": 2025,
"plot_id": "2466599",
"cooperator": "Wayside Dairy Farms",
"planted_date": "2025-05-09",
"harvested_date": "2025-09-22",
"population_seeds_per_acre": 32000,
"row_width_in": 30,
"results": [
{
"rank": 1,
"brand": "Brevant",
"product": "B96M56PCE",
"traits": "",
"metrics": {
"Ton/Acre": 29.6,
"Milk Per Acre": 3412.0,
"Milk Per Ton": 30319.0,
"Beef Per Acre": 249.0,
"Beef Per Ton": 2003.0
},
"entry_num": null
},
{
"rank": 2,
"brand": "Dairyland",
"product": "Seed",
"traits": "HIDF-4545Q",
"metrics": {
"Ton/Acre": 29.5,
"Milk Per Acre": 3363.0,
"Milk Per Ton": 29811.0,
"Beef Per Acre": 243.0,
"Beef Per Ton": 1980.0
},
"entry_num": null
},
{
"rank": 3,
"brand": "Brevant",
"product": "B05D47V",
"traits": "",
"metrics": {
"Ton/Acre": 29.0,
"Milk Per Acre": 3398.0,
"Milk Per Ton": 29546.0,
"Beef Per Acre": 245.0,
"Beef Per Ton": 1946.0
},
"entry_num": null
},
{
"rank": 4,
"brand": "Enogen",
"product": "E094Z4-D",
"traits": "",
"metrics": {
"Ton/Acre": 28.4,
"Milk Per Acre": 3590.0,
"Milk Per Ton": 30609.0,
"Beef Per Acre": 276.0,
"Beef Per Ton": 2006.0
},
"entry_num": null
},
{
"rank": 5,
"brand": "Dairyland",
"product": "Seed",
"traits": "HIDF-4321V",
"metrics": {
"Ton/Acre": 28.3,
"Milk Per Acre": 3269.0,
"Milk Per Ton": 27743.0,
"Beef Per Acre": 227.0,
"Beef Per Ton": 1848.0
},
"entry_num": null
},
{
"rank": 6,
"brand": "Beck's",
"product": "5212TCV2P",
"traits": "",
"metrics": {
"Ton/Acre": 28.0,
"Milk Per Acre": 3405.0,
"Milk Per Ton": 28586.0,
"Beef Per Acre": 246.0,
"Beef Per Ton": 1884.0
},
"entry_num": null
},
{
"rank": 7,
"brand": "Enogen",
"product": "E097K6-D",
"traits": "",
"metrics": {
"Ton/Acre": 27.5,
"Milk Per Acre": 3274.0,
"Milk Per Ton": 27002.0,
"Beef Per Acre": 227.0,
"Beef Per Ton": 1794.0
},
"entry_num": null
},
{
"rank": 8,
"brand": "Pioneer",
"product": "P9955V",
"traits": "",
"metrics": {
"Ton/Acre": 27.3,
"Milk Per Acre": 3505.0,
"Milk Per Ton": 28706.0,
"Beef Per Acre": 253.0,
"Beef Per Ton": 1858.0
},
"entry_num": null
},
{
"rank": 9,
"brand": "XL",
"product": "5324V",
"traits": "",
"metrics": {
"Ton/Acre": 27.0,
"Milk Per Acre": 3583.0,
"Milk Per Ton": 29000.0,
"Beef Per Acre": 267.0,
"Beef Per Ton": 1878.0
},
"entry_num": null
},
{
"rank": 10,
"brand": "Brevant",
"product": "B99A24V",
"traits": "",
"metrics": {
"Ton/Acre": 26.8,
"Milk Per Acre": 3376.0,
"Milk Per Ton": 27192.0,
"Beef Per Acre": 244.0,
"Beef Per Ton": 1802.0
},
"entry_num": null
},
{
"rank": 11,
"brand": "Pioneer",
"product": "P9884Q",
"traits": "",
"metrics": {
"Ton/Acre": 26.7,
"Milk Per Acre": 3422.0,
"Milk Per Ton": 27404.0,
"Beef Per Acre": 242.0,
"Beef Per Ton": 1785.0
},
"entry_num": null
},
{
"rank": 11,
"brand": "XL",
"product": "5332AM",
"traits": "",
"metrics": {
"Ton/Acre": 26.7,
"Milk Per Acre": 3326.0,
"Milk Per Ton": 26664.0,
"Beef Per Acre": 248.0,
"Beef Per Ton": 1803.0
},
"entry_num": null
},
{
"rank": 13,
"brand": "Pioneer",
"product": "P96760V",
"traits": "",
"metrics": {
"Ton/Acre": 26.6,
"Milk Per Acre": 3426.0,
"Milk Per Ton": 27289.0,
"Beef Per Acre": 263.0,
"Beef Per Ton": 1836.0
},
"entry_num": null
},
{
"rank": 13,
"brand": "Dairyland",
"product": "Seed",
"traits": "HIDF-4073Q",
"metrics": {
"Ton/Acre": 26.6,
"Milk Per Acre": 3458.0,
"Milk Per Ton": 27558.0,
"Beef Per Acre": 257.0,
"Beef Per Ton": 1820.0
},
"entry_num": null
},
{
"rank": 15,
"brand": "Preceon",
"product": "PR105-50",
"traits": "",
"metrics": {
"Ton/Acre": 26.5,
"Milk Per Acre": 3362.0,
"Milk Per Ton": 26708.0,
"Beef Per Acre": 237.0,
"Beef Per Ton": 1756.0
},
"entry_num": null
},
{
"rank": 16,
"brand": "Preceon",
"product": "PR102-50",
"traits": "",
"metrics": {
"Ton/Acre": 26.3,
"Milk Per Acre": 3343.0,
"Milk Per Ton": 26413.0,
"Beef Per Acre": 238.0,
"Beef Per Ton": 1750.0
},
"entry_num": null
},
{
"rank": 17,
"brand": "Dairyland",
"product": "Seed",
"traits": "HiDF-3522Q",
"metrics": {
"Ton/Acre": 26.1,
"Milk Per Acre": 3351.0,
"Milk Per Ton": 26226.0,
"Beef Per Acre": 249.0,
"Beef Per Ton": 1765.0
},
"entry_num": null
},
{
"rank": 17,
"brand": "Preceon",
"product": "PR104-60",
"traits": "",
"metrics": {
"Ton/Acre": 26.1,
"Milk Per Acre": 3535.0,
"Milk Per Ton": 27729.0,
"Beef Per Acre": 265.0,
"Beef Per Ton": 1814.0
},
"entry_num": null
},
{
"rank": 19,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 25.9,
"Milk Per Acre": 3083.0,
"Milk Per Ton": 23984.0,
"Beef Per Acre": 218.0,
"Beef Per Ton": 1668.0
},
"entry_num": null
},
{
"rank": 20,
"brand": "Dairyland",
"product": "Seed",
"traits": "DB-4022Q",
"metrics": {
"Ton/Acre": 25.8,
"Milk Per Acre": 3537.0,
"Milk Per Ton": 27346.0,
"Beef Per Acre": 269.0,
"Beef Per Ton": 1799.0
},
"entry_num": null
},
{
"rank": 21,
"brand": "Enogen",
"product": "E102K7-D",
"traits": "",
"metrics": {
"Ton/Acre": 25.5,
"Milk Per Acre": 3564.0,
"Milk Per Ton": 27301.0,
"Beef Per Acre": 257.0,
"Beef Per Ton": 1748.0
},
"entry_num": null
},
{
"rank": 22,
"brand": "Enogen",
"product": "E095D3-D",
"traits": "",
"metrics": {
"Ton/Acre": 25.1,
"Milk Per Acre": 3505.0,
"Milk Per Ton": 26418.0,
"Beef Per Acre": 257.0,
"Beef Per Ton": 1719.0
},
"entry_num": null
},
{
"rank": 23,
"brand": "Dairyland",
"product": "Seed",
"traits": "DB-3434Q",
"metrics": {
"Ton/Acre": 24.7,
"Milk Per Acre": 3569.0,
"Milk Per Ton": 26458.0,
"Beef Per Acre": 256.0,
"Beef Per Ton": 1690.0
},
"entry_num": null
}
],
"n_results": 23,
"source_urls": [
"https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2466599"
],
"fetched_at": "2026-05-25T19:46:12.180479+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink