Files
seed-mcp/corpus/gh_plot_reports/ghpr-silage-mi-2024-2414728.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

166 lines
3.7 KiB
JSON

{
"source": "gh_plot_reports",
"source_key": "ghpr-silage-mi-2024-2414728",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "silage",
"state": "Michigan",
"state_abbrev": "mi",
"year": 2024,
"plot_id": "2414728",
"cooperator": "Grownorth Ag Llc",
"planted_date": "2024-05-10",
"harvested_date": "2024-09-12",
"population_seeds_per_acre": 35000,
"row_width_in": 30,
"results": [
{
"rank": 1,
"brand": "Enogen",
"product": "E112S5-D",
"traits": "",
"metrics": {
"Ton/Acre": 38.0,
"Milk Per Acre": 3114.0,
"Milk Per Ton": 35468.0,
"Beef Per Acre": 185.0,
"Beef Per Ton": 2316.0
},
"entry_num": null
},
{
"rank": 2,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 35.6,
"Milk Per Acre": 3322.0,
"Milk Per Ton": 35453.0,
"Beef Per Acre": 227.0,
"Beef Per Ton": 2323.0
},
"entry_num": null
},
{
"rank": 3,
"brand": "Enogen",
"product": "E105Z5-D",
"traits": "",
"metrics": {
"Ton/Acre": 34.7,
"Milk Per Acre": 3300.0,
"Milk Per Ton": 34367.0,
"Beef Per Acre": 241.0,
"Beef Per Ton": 2316.0
},
"entry_num": null
},
{
"rank": 4,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 34.3,
"Milk Per Acre": 3174.0,
"Milk Per Ton": 32642.0,
"Beef Per Acre": 216.0,
"Beef Per Ton": 2198.0
},
"entry_num": null
},
{
"rank": 5,
"brand": "Enogen",
"product": "E107C1-D",
"traits": "",
"metrics": {
"Ton/Acre": 34.1,
"Milk Per Acre": 3303.0,
"Milk Per Ton": 33774.0,
"Beef Per Acre": 219.0,
"Beef Per Ton": 2197.0
},
"entry_num": null
},
{
"rank": 6,
"brand": "Enogen",
"product": "E110F4-D",
"traits": "",
"metrics": {
"Ton/Acre": 33.2,
"Milk Per Acre": 3311.0,
"Milk Per Ton": 32933.0,
"Beef Per Acre": 221.0,
"Beef Per Ton": 2143.0
},
"entry_num": null
},
{
"rank": 7,
"brand": "Enogen",
"product": "E111V7-D",
"traits": "",
"metrics": {
"Ton/Acre": 31.3,
"Milk Per Acre": 3154.0,
"Milk Per Ton": 29575.0,
"Beef Per Acre": 206.0,
"Beef Per Ton": 1974.0
},
"entry_num": null
},
{
"rank": 8,
"brand": "Enogen",
"product": "E100A3-D",
"traits": "",
"metrics": {
"Ton/Acre": 30.3,
"Milk Per Acre": 3315.0,
"Milk Per Ton": 30120.0,
"Beef Per Acre": 247.0,
"Beef Per Ton": 2042.0
},
"entry_num": null
},
{
"rank": 9,
"brand": "Enogen",
"product": "E095D3-D",
"traits": "",
"metrics": {
"Ton/Acre": 30.2,
"Milk Per Acre": 3493.0,
"Milk Per Ton": 31600.0,
"Beef Per Acre": 259.0,
"Beef Per Ton": 2072.0
},
"entry_num": null
},
{
"rank": 10,
"brand": "Enogen",
"product": "E094Z4-D",
"traits": "",
"metrics": {
"Ton/Acre": 29.2,
"Milk Per Acre": 3430.0,
"Milk Per Ton": 30092.0,
"Beef Per Acre": 248.0,
"Beef Per Ton": 1975.0
},
"entry_num": null
}
],
"n_results": 10,
"source_urls": [
"https://www.goldenharvestseeds.com/silage/plot-report/mi/2024/2414728"
],
"fetched_at": "2026-05-25T19:19:52.555672+00:00",
"scraper_version": "0.1.0"
}