justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
d60d747858ddaf4ff7835ade281150d0d5424bf3
seed-mcp/corpus/gh_plot_reports/ghpr-silage-wi-2025-2469877.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

404 lines
8.9 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-silage-wi-2025-2469877",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "silage",
"state": "Wisconsin",
"state_abbrev": "wi",
"year": 2025,
"plot_id": "2469877",
"cooperator": "Abel Dairy Farms LLC",
"planted_date": "2025-05-07",
"harvested_date": "2025-09-29",
"population_seeds_per_acre": 34000,
"row_width_in": 20,
"results": [
{
"rank": 1,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 37.5,
"Milk Per Acre": 3402.0,
"Milk Per Ton": 38222.0,
"Beef Per Acre": 268.0,
"Beef Per Ton": 2608.0
},
"entry_num": null
},
{
"rank": 2,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 36.8,
"Milk Per Acre": 3233.0,
"Milk Per Ton": 35738.0,
"Beef Per Acre": 247.0,
"Beef Per Ton": 2483.0
},
"entry_num": null
},
{
"rank": 3,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 36.6,
"Milk Per Acre": 3250.0,
"Milk Per Ton": 35732.0,
"Beef Per Acre": 251.0,
"Beef Per Ton": 2485.0
},
"entry_num": null
},
{
"rank": 3,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 36.6,
"Milk Per Acre": 3295.0,
"Milk Per Ton": 36163.0,
"Beef Per Acre": 245.0,
"Beef Per Ton": 2456.0
},
"entry_num": null
},
{
"rank": 5,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 36.5,
"Milk Per Acre": 3381.0,
"Milk Per Ton": 37024.0,
"Beef Per Acre": 264.0,
"Beef Per Ton": 2527.0
},
"entry_num": null
},
{
"rank": 6,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 36.4,
"Milk Per Acre": 3468.0,
"Milk Per Ton": 37864.0,
"Beef Per Acre": 276.0,
"Beef Per Ton": 2568.0
},
"entry_num": null
},
{
"rank": 7,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 36.2,
"Milk Per Acre": 3231.0,
"Milk Per Ton": 35119.0,
"Beef Per Acre": 250.0,
"Beef Per Ton": 2452.0
},
"entry_num": null
},
{
"rank": 8,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 36.1,
"Milk Per Acre": 3071.0,
"Milk Per Ton": 33240.0,
"Beef Per Acre": 213.0,
"Beef Per Ton": 2302.0
},
"entry_num": null
},
{
"rank": 9,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 35.9,
"Milk Per Acre": 3073.0,
"Milk Per Ton": 33138.0,
"Beef Per Acre": 218.0,
"Beef Per Ton": 2311.0
},
"entry_num": null
},
{
"rank": 10,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 35.7,
"Milk Per Acre": 3243.0,
"Milk Per Ton": 34738.0,
"Beef Per Acre": 257.0,
"Beef Per Ton": 2445.0
},
"entry_num": null
},
{
"rank": 11,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 35.6,
"Milk Per Acre": 3354.0,
"Milk Per Ton": 35870.0,
"Beef Per Acre": 234.0,
"Beef Per Ton": 2352.0
},
"entry_num": null
},
{
"rank": 11,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 35.6,
"Milk Per Acre": 3286.0,
"Milk Per Ton": 35090.0,
"Beef Per Acre": 242.0,
"Beef Per Ton": 2380.0
},
"entry_num": null
},
{
"rank": 13,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 35.5,
"Milk Per Acre": 3398.0,
"Milk Per Ton": 36203.0,
"Beef Per Acre": 258.0,
"Beef Per Ton": 2436.0
},
"entry_num": null
},
{
"rank": 14,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 35.2,
"Milk Per Acre": 3309.0,
"Milk Per Ton": 34947.0,
"Beef Per Acre": 253.0,
"Beef Per Ton": 2396.0
},
"entry_num": null
},
{
"rank": 15,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 35.1,
"Milk Per Acre": 3423.0,
"Milk Per Ton": 36031.0,
"Beef Per Acre": 254.0,
"Beef Per Ton": 2390.0
},
"entry_num": null
},
{
"rank": 16,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 34.9,
"Milk Per Acre": 3388.0,
"Milk Per Ton": 35484.0,
"Beef Per Acre": 265.0,
"Beef Per Ton": 2421.0
},
"entry_num": null
},
{
"rank": 17,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 34.8,
"Milk Per Acre": 3232.0,
"Milk Per Ton": 33727.0,
"Beef Per Acre": 232.0,
"Beef Per Ton": 2287.0
},
"entry_num": null
},
{
"rank": 18,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 34.7,
"Milk Per Acre": 3394.0,
"Milk Per Ton": 35334.0,
"Beef Per Acre": 266.0,
"Beef Per Ton": 2409.0
},
"entry_num": null
},
{
"rank": 18,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 34.7,
"Milk Per Acre": 3227.0,
"Milk Per Ton": 33582.0,
"Beef Per Acre": 242.0,
"Beef Per Ton": 2320.0
},
"entry_num": null
},
{
"rank": 20,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 34.5,
"Milk Per Acre": 3357.0,
"Milk Per Ton": 34793.0,
"Beef Per Acre": 259.0,
"Beef Per Ton": 2371.0
},
"entry_num": null
},
{
"rank": 21,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 33.8,
"Milk Per Acre": 3242.0,
"Milk Per Ton": 32877.0,
"Beef Per Acre": 241.0,
"Beef Per Ton": 2258.0
},
"entry_num": null
},
{
"rank": 22,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 33.6,
"Milk Per Acre": 3508.0,
"Milk Per Ton": 35354.0,
"Beef Per Acre": 260.0,
"Beef Per Ton": 2311.0
},
"entry_num": null
},
{
"rank": 23,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 33.4,
"Milk Per Acre": 3490.0,
"Milk Per Ton": 34990.0,
"Beef Per Acre": 265.0,
"Beef Per Ton": 2317.0
},
"entry_num": null
},
{
"rank": 24,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 33.2,
"Milk Per Acre": 3352.0,
"Milk Per Ton": 33397.0,
"Beef Per Acre": 246.0,
"Beef Per Ton": 2235.0
},
"entry_num": null
},
{
"rank": 24,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 33.2,
"Milk Per Acre": 3249.0,
"Milk Per Ton": 32343.0,
"Beef Per Acre": 239.0,
"Beef Per Ton": 2209.0
},
"entry_num": null
},
{
"rank": 26,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 32.2,
"Milk Per Acre": 3521.0,
"Milk Per Ton": 34059.0,
"Beef Per Acre": 263.0,
"Beef Per Ton": 2230.0
},
"entry_num": null
},
{
"rank": 27,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 32.0,
"Milk Per Acre": 3404.0,
"Milk Per Ton": 32716.0,
"Beef Per Acre": 245.0,
"Beef Per Ton": 2154.0
},
"entry_num": null
}
],
"n_results": 27,
"source_urls": [
"https://www.goldenharvestseeds.com/silage/plot-report/wi/2025/2469877"
],
"fetched_at": "2026-05-25T19:51:28.645880+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink