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-soybeans-wi-2024-2440896.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

715 lines
14 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-wi-2024-2440896",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Wisconsin",
"state_abbrev": "wi",
"year": 2024,
"plot_id": "2440896",
"cooperator": "University of Wisconsin - Menomonie",
"planted_date": "2024-05-10",
"harvested_date": "2024-10-08",
"population_seeds_per_acre": null,
"row_width_in": null,
"results": [
{
"rank": 1,
"brand": "Asgrow",
"product": "AG17XF5",
"traits": "",
"metrics": {
"Yield": 65.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 682.5
},
"entry_num": 8
},
{
"rank": 2,
"brand": "Golden Harvest",
"product": "GH1555XF",
"traits": "",
"metrics": {
"Yield": 64.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 672.0
},
"entry_num": 17
},
{
"rank": 2,
"brand": "Stine",
"product": "11EC02",
"traits": "",
"metrics": {
"Yield": 64.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 672.0
},
"entry_num": 38
},
{
"rank": 2,
"brand": "Stine",
"product": "13EG23",
"traits": "",
"metrics": {
"Yield": 64.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 672.0
},
"entry_num": 39
},
{
"rank": 5,
"brand": "APEX",
"product": "AE1220",
"traits": "",
"metrics": {
"Yield": 62.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 651.0
},
"entry_num": 1
},
{
"rank": 5,
"brand": "Asgrow",
"product": "AG16XF5",
"traits": "",
"metrics": {
"Yield": 62.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 651.0
},
"entry_num": 7
},
{
"rank": 7,
"brand": "Asgrow",
"product": "AG12XF5",
"traits": "",
"metrics": {
"Yield": 60.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 630.0
},
"entry_num": 5
},
{
"rank": 7,
"brand": "Genesis",
"product": "G1560E",
"traits": "",
"metrics": {
"Yield": 60.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 630.0
},
"entry_num": 13
},
{
"rank": 7,
"brand": "Golden Harvest",
"product": "GH1614E3",
"traits": "",
"metrics": {
"Yield": 60.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 630.0
},
"entry_num": 18
},
{
"rank": 7,
"brand": "Legacy",
"product": "Seeds",
"traits": "LS144-24XF",
"metrics": {
"Yield": 60.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 630.0
},
"entry_num": 21
},
{
"rank": 11,
"brand": "APEX",
"product": "AE1410",
"traits": "",
"metrics": {
"Yield": 59.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 619.5
},
"entry_num": 3
},
{
"rank": 11,
"brand": "Asgrow",
"product": "AG19XF3",
"traits": "",
"metrics": {
"Yield": 59.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 619.5
},
"entry_num": 9
},
{
"rank": 11,
"brand": "Legacy",
"product": "Seeds",
"traits": "LS194-23XF",
"metrics": {
"Yield": 59.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 619.5
},
"entry_num": 23
},
{
"rank": 11,
"brand": "NK",
"product": "NK11-A4E3",
"traits": "",
"metrics": {
"Yield": 59.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 619.5
},
"entry_num": 32
},
{
"rank": 11,
"brand": "NK",
"product": "NK14-U5E3",
"traits": "",
"metrics": {
"Yield": 59.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 619.5
},
"entry_num": 33
},
{
"rank": 11,
"brand": "O'Brien",
"product": "Hybrids",
"traits": "O'Soy 1524EL-3",
"metrics": {
"Yield": 59.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 619.5
},
"entry_num": 35
},
{
"rank": 11,
"brand": "Renk",
"product": "Seed",
"traits": "RS155NXF",
"metrics": {
"Yield": 59.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 619.5
},
"entry_num": 36
},
{
"rank": 11,
"brand": "Stine",
"product": "17EE32",
"traits": "",
"metrics": {
"Yield": 59.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 619.5
},
"entry_num": 41
},
{
"rank": 19,
"brand": "BioGene",
"product": "Seeds",
"traits": "BG9150E3",
"metrics": {
"Yield": 58.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 609.0
},
"entry_num": 10
},
{
"rank": 19,
"brand": "Genesis",
"product": "G1260E",
"traits": "",
"metrics": {
"Yield": 58.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 609.0
},
"entry_num": 11
},
{
"rank": 19,
"brand": "Xitavo",
"product": "XO",
"traits": "1372E",
"metrics": {
"Yield": 58.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 609.0
},
"entry_num": 50
},
{
"rank": 19,
"brand": "Xitavo",
"product": "XO",
"traits": "1404E",
"metrics": {
"Yield": 58.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 609.0
},
"entry_num": 51
},
{
"rank": 23,
"brand": "APEX",
"product": "AE1710",
"traits": "",
"metrics": {
"Yield": 57.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 598.5
},
"entry_num": 4
},
{
"rank": 23,
"brand": "Genesis",
"product": "G1590E",
"traits": "",
"metrics": {
"Yield": 57.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 598.5
},
"entry_num": 14
},
{
"rank": 23,
"brand": "Genesis",
"product": "G1760E",
"traits": "",
"metrics": {
"Yield": 57.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 598.5
},
"entry_num": 15
},
{
"rank": 23,
"brand": "Legacy",
"product": "Seeds",
"traits": "LS112-24 E",
"metrics": {
"Yield": 57.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 598.5
},
"entry_num": 19
},
{
"rank": 23,
"brand": "Loyal",
"product": "Brand",
"traits": "L1270E",
"metrics": {
"Yield": 57.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 598.5
},
"entry_num": 26
},
{
"rank": 23,
"brand": "Stine",
"product": "15EE32",
"traits": "",
"metrics": {
"Yield": 57.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 598.5
},
"entry_num": 40
},
{
"rank": 23,
"brand": "Xitavo",
"product": "XO",
"traits": "1095E",
"metrics": {
"Yield": 57.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 598.5
},
"entry_num": 48
},
{
"rank": 23,
"brand": "Xitavo",
"product": "XO",
"traits": "1632E",
"metrics": {
"Yield": 57.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 598.5
},
"entry_num": 53
},
{
"rank": 31,
"brand": "Asgrow",
"product": "AG14XF4",
"traits": "",
"metrics": {
"Yield": 56.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 588.0
},
"entry_num": 6
},
{
"rank": 31,
"brand": "Golden Harvest",
"product": "GH1534E3S",
"traits": "",
"metrics": {
"Yield": 56.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 588.0
},
"entry_num": 16
},
{
"rank": 31,
"brand": "Loyal",
"product": "Brand",
"traits": "L1540E",
"metrics": {
"Yield": 56.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 588.0
},
"entry_num": 27
},
{
"rank": 31,
"brand": "Loyal",
"product": "Brand",
"traits": "L2070E",
"metrics": {
"Yield": 56.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 588.0
},
"entry_num": 30
},
{
"rank": 35,
"brand": "Genesis",
"product": "G1290E",
"traits": "",
"metrics": {
"Yield": 55.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 577.5
},
"entry_num": 12
},
{
"rank": 35,
"brand": "Legacy",
"product": "Seeds",
"traits": "LS154-24XF",
"metrics": {
"Yield": 55.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 577.5
},
"entry_num": 22
},
{
"rank": 35,
"brand": "NK",
"product": "NK15-G9E3S",
"traits": "",
"metrics": {
"Yield": 55.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 577.5
},
"entry_num": 34
},
{
"rank": 35,
"brand": "Tracy",
"product": "Seeds",
"traits": "1055E",
"metrics": {
"Yield": 55.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 577.5
},
"entry_num": 42
},
{
"rank": 35,
"brand": "Tracy",
"product": "Seeds",
"traits": "1654E",
"metrics": {
"Yield": 55.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 577.5
},
"entry_num": 44
},
{
"rank": 35,
"brand": "Tracy",
"product": "Seeds",
"traits": "1655E",
"metrics": {
"Yield": 55.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 577.5
},
"entry_num": 45
},
{
"rank": 41,
"brand": "APEX",
"product": "AE1250",
"traits": "",
"metrics": {
"Yield": 54.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 567.0
},
"entry_num": 2
},
{
"rank": 41,
"brand": "Legacy",
"product": "Seeds",
"traits": "LS132-24 E",
"metrics": {
"Yield": 54.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 567.0
},
"entry_num": 20
},
{
"rank": 41,
"brand": "NK",
"product": "NK08-Z4E3",
"traits": "",
"metrics": {
"Yield": 54.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 567.0
},
"entry_num": 31
},
{
"rank": 41,
"brand": "Tracy",
"product": "Seeds",
"traits": "1255E",
"metrics": {
"Yield": 54.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 567.0
},
"entry_num": 43
},
{
"rank": 41,
"brand": "Xitavo",
"product": "XO",
"traits": "1545E",
"metrics": {
"Yield": 54.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 567.0
},
"entry_num": 52
},
{
"rank": 46,
"brand": "Loyal",
"product": "Brand",
"traits": "L1160E",
"metrics": {
"Yield": 52.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 546.0
},
"entry_num": 25
},
{
"rank": 46,
"brand": "Loyal",
"product": "Brand",
"traits": "L1670E",
"metrics": {
"Yield": 52.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 546.0
},
"entry_num": 28
},
{
"rank": 46,
"brand": "Loyal",
"product": "Brand",
"traits": "L1860E",
"metrics": {
"Yield": 52.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 546.0
},
"entry_num": 29
},
{
"rank": 49,
"brand": "Loyal",
"product": "Brand",
"traits": "L1070E",
"metrics": {
"Yield": 51.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 535.5
},
"entry_num": 24
},
{
"rank": 49,
"brand": "Tracy",
"product": "Seeds",
"traits": "1854E",
"metrics": {
"Yield": 51.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 535.5
},
"entry_num": 46
},
{
"rank": 49,
"brand": "Xitavo",
"product": "XO",
"traits": "0993E",
"metrics": {
"Yield": 51.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 535.5
},
"entry_num": 47
},
{
"rank": 49,
"brand": "Xitavo",
"product": "XO",
"traits": "1225E",
"metrics": {
"Yield": 51.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 535.5
},
"entry_num": 49
},
{
"rank": 53,
"brand": "Stine",
"product": "10EG20",
"traits": "",
"metrics": {
"Yield": 42.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 441.0
},
"entry_num": 37
}
],
"n_results": 53,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/wi/2024/2440896"
],
"fetched_at": "2026-05-25T19:40:35.483000+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink