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-soybeans-de-2024-2435170.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

845 lines
17 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-de-2024-2435170",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Delaware",
"state_abbrev": "de",
"year": 2024,
"plot_id": "2435170",
"cooperator": "University of Delaware - Kent Trial",
"planted_date": "2024-05-31",
"harvested_date": "2024-10-29",
"population_seeds_per_acre": 150000,
"row_width_in": null,
"results": [
{
"rank": 1,
"brand": "Seed",
"product": "Consultants",
"traits": "SC7485E",
"metrics": {
"Yield": 89.0,
"%MST": 7.3,
"Test Weight": 57.8,
"Gross Revenue": 934.5
},
"entry_num": 1
},
{
"rank": 2,
"brand": "NK",
"product": "NK42-A6E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 87.5,
"%MST": 8.6,
"Test Weight": 58.2,
"Gross Revenue": 918.75
},
"entry_num": 2
},
{
"rank": 3,
"brand": "APEX",
"product": "AE4640S",
"traits": "",
"metrics": {
"Yield": 85.2,
"%MST": 8.4,
"Test Weight": 55.9,
"Gross Revenue": 894.6
},
"entry_num": 4
},
{
"rank": 4,
"brand": "APEX",
"product": "AE3850",
"traits": "",
"metrics": {
"Yield": 84.6,
"%MST": 8.2,
"Test Weight": 56.4,
"Gross Revenue": 888.3
},
"entry_num": 6
},
{
"rank": 5,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions A5284XF",
"metrics": {
"Yield": 84.0,
"%MST": 8.7,
"Test Weight": 57.5,
"Gross Revenue": 882.0
},
"entry_num": 7
},
{
"rank": 6,
"brand": "Revere",
"product": "Seed",
"traits": "Revere 39-F94 XFS",
"metrics": {
"Yield": 83.8,
"%MST": 8.9,
"Test Weight": 57.8,
"Gross Revenue": 879.9
},
"entry_num": 8
},
{
"rank": 7,
"brand": "Catalyst",
"product": "CT4413E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 83.4,
"%MST": 8.3,
"Test Weight": 55.3,
"Gross Revenue": 875.7
},
"entry_num": 9
},
{
"rank": 8,
"brand": "APEX",
"product": "AE4341S",
"traits": "",
"metrics": {
"Yield": 83.2,
"%MST": 8.1,
"Test Weight": 55.8,
"Gross Revenue": 873.6
},
"entry_num": 10
},
{
"rank": 9,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS3525E3",
"metrics": {
"Yield": 82.7,
"%MST": 8.3,
"Test Weight": 56.7,
"Gross Revenue": 868.35
},
"entry_num": 12
},
{
"rank": 10,
"brand": "AgVenture",
"product": "AV38B2E",
"traits": "",
"metrics": {
"Yield": 82.6,
"%MST": 8.0,
"Test Weight": 57.2,
"Gross Revenue": 867.3
},
"entry_num": 13
},
{
"rank": 11,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4045E3",
"metrics": {
"Yield": 82.4,
"%MST": 8.1,
"Test Weight": 57.3,
"Gross Revenue": 865.2
},
"entry_num": 14
},
{
"rank": 12,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7474XFS",
"metrics": {
"Yield": 82.2,
"%MST": 8.4,
"Test Weight": 57.4,
"Gross Revenue": 863.1
},
"entry_num": 16
},
{
"rank": 13,
"brand": "Xitavo",
"product": "XO",
"traits": "4132E",
"metrics": {
"Yield": 82.1,
"%MST": 8.2,
"Test Weight": 55.3,
"Gross Revenue": 862.05
},
"entry_num": 17
},
{
"rank": 13,
"brand": "Revere",
"product": "Seed",
"traits": "Revere 44-F44 XFS",
"metrics": {
"Yield": 82.1,
"%MST": 8.0,
"Test Weight": 56.9,
"Gross Revenue": 862.05
},
"entry_num": 18
},
{
"rank": 15,
"brand": "NK",
"product": "NK44-Q5E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 82.0,
"%MST": 8.4,
"Test Weight": 56.2,
"Gross Revenue": 861.0
},
"entry_num": 19
},
{
"rank": 15,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7415ET",
"metrics": {
"Yield": 82.0,
"%MST": 8.2,
"Test Weight": 56.0,
"Gross Revenue": 861.0
},
"entry_num": 20
},
{
"rank": 17,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4215E3",
"metrics": {
"Yield": 81.9,
"%MST": 8.3,
"Test Weight": 56.4,
"Gross Revenue": 859.95
},
"entry_num": 21
},
{
"rank": 17,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4021E3",
"metrics": {
"Yield": 81.9,
"%MST": 7.6,
"Test Weight": 56.3,
"Gross Revenue": 859.95
},
"entry_num": 22
},
{
"rank": 19,
"brand": "AgVenture",
"product": "AV39B2E",
"traits": "",
"metrics": {
"Yield": 81.4,
"%MST": 7.4,
"Test Weight": 56.1,
"Gross Revenue": 854.7
},
"entry_num": 23
},
{
"rank": 20,
"brand": "Seed",
"product": "Consultants",
"traits": "SC7444E",
"metrics": {
"Yield": 81.3,
"%MST": 8.6,
"Test Weight": 55.8,
"Gross Revenue": 853.65
},
"entry_num": 24
},
{
"rank": 21,
"brand": "Xitavo",
"product": "XO",
"traits": "4364E",
"metrics": {
"Yield": 81.2,
"%MST": 8.5,
"Test Weight": 55.4,
"Gross Revenue": 852.6
},
"entry_num": 25
},
{
"rank": 21,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7483XFS",
"metrics": {
"Yield": 81.2,
"%MST": 8.1,
"Test Weight": 55.6,
"Gross Revenue": 852.6
},
"entry_num": 26
},
{
"rank": 23,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7435ET",
"metrics": {
"Yield": 80.9,
"%MST": 7.8,
"Test Weight": 56.0,
"Gross Revenue": 849.45
},
"entry_num": 27
},
{
"rank": 24,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7424ETS",
"metrics": {
"Yield": 80.7,
"%MST": 8.7,
"Test Weight": 57.0,
"Gross Revenue": 847.35
},
"entry_num": 28
},
{
"rank": 24,
"brand": "AgVenture",
"product": "AV48B2E",
"traits": "",
"metrics": {
"Yield": 80.7,
"%MST": 7.8,
"Test Weight": 57.1,
"Gross Revenue": 847.35
},
"entry_num": 29
},
{
"rank": 26,
"brand": "NK",
"product": "NK47-G5E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 80.5,
"%MST": 8.1,
"Test Weight": 57.5,
"Gross Revenue": 845.25
},
"entry_num": 30
},
{
"rank": 26,
"brand": "Xitavo",
"product": "XO",
"traits": "4522E",
"metrics": {
"Yield": 80.5,
"%MST": 8.2,
"Test Weight": 56.7,
"Gross Revenue": 845.25
},
"entry_num": 32
},
{
"rank": 28,
"brand": "Seed",
"product": "Consultants",
"traits": "SC7465E",
"metrics": {
"Yield": 80.4,
"%MST": 8.6,
"Test Weight": 55.9,
"Gross Revenue": 844.2
},
"entry_num": 33
},
{
"rank": 29,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4723E3",
"metrics": {
"Yield": 80.2,
"%MST": 8.1,
"Test Weight": 54.6,
"Gross Revenue": 842.1
},
"entry_num": 34
},
{
"rank": 30,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions B3934E",
"metrics": {
"Yield": 80.1,
"%MST": 8.3,
"Test Weight": 56.5,
"Gross Revenue": 841.05
},
"entry_num": 35
},
{
"rank": 30,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4423E3",
"metrics": {
"Yield": 80.1,
"%MST": 8.8,
"Test Weight": 55.8,
"Gross Revenue": 841.05
},
"entry_num": 36
},
{
"rank": 32,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7494ETS",
"metrics": {
"Yield": 79.9,
"%MST": 8.7,
"Test Weight": 54.6,
"Gross Revenue": 838.95
},
"entry_num": 38
},
{
"rank": 33,
"brand": "Benson",
"product": "Hill",
"traits": "BX38C615",
"metrics": {
"Yield": 79.6,
"%MST": 7.8,
"Test Weight": 54.8,
"Gross Revenue": 835.8
},
"entry_num": 39
},
{
"rank": 34,
"brand": "AgVenture",
"product": "AV44B2E",
"traits": "",
"metrics": {
"Yield": 79.5,
"%MST": 8.4,
"Test Weight": 55.8,
"Gross Revenue": 834.75
},
"entry_num": 41
},
{
"rank": 34,
"brand": "AgVenture",
"product": "AV43B2BE",
"traits": "",
"metrics": {
"Yield": 79.5,
"%MST": 8.1,
"Test Weight": 55.5,
"Gross Revenue": 834.75
},
"entry_num": 42
},
{
"rank": 36,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4823E3/STS",
"metrics": {
"Yield": 79.0,
"%MST": 8.4,
"Test Weight": 56.8,
"Gross Revenue": 829.5
},
"entry_num": 43
},
{
"rank": 37,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS3723STS",
"metrics": {
"Yield": 78.9,
"%MST": 8.3,
"Test Weight": 57.8,
"Gross Revenue": 828.45
},
"entry_num": 44
},
{
"rank": 38,
"brand": "AgVenture",
"product": "AV47B2BE",
"traits": "",
"metrics": {
"Yield": 78.6,
"%MST": 8.1,
"Test Weight": 57.5,
"Gross Revenue": 825.3
},
"entry_num": 45
},
{
"rank": 39,
"brand": "Xitavo",
"product": "XO",
"traits": "4405E",
"metrics": {
"Yield": 78.3,
"%MST": 8.3,
"Test Weight": 56.5,
"Gross Revenue": 822.15
},
"entry_num": 47
},
{
"rank": 39,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions B4904E",
"metrics": {
"Yield": 78.3,
"%MST": 8.4,
"Test Weight": 55.8,
"Gross Revenue": 822.15
},
"entry_num": 48
},
{
"rank": 41,
"brand": "Benson",
"product": "Hill",
"traits": "C38H052S",
"metrics": {
"Yield": 78.1,
"%MST": 8.3,
"Test Weight": 55.9,
"Gross Revenue": 820.05
},
"entry_num": 49
},
{
"rank": 42,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7485ETS",
"metrics": {
"Yield": 78.0,
"%MST": 8.0,
"Test Weight": 56.3,
"Gross Revenue": 819.0
},
"entry_num": 50
},
{
"rank": 43,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions B4553E",
"metrics": {
"Yield": 77.7,
"%MST": 8.5,
"Test Weight": 56.8,
"Gross Revenue": 815.85
},
"entry_num": 51
},
{
"rank": 44,
"brand": "AgVenture",
"product": "AV45B2E",
"traits": "",
"metrics": {
"Yield": 77.6,
"%MST": 8.2,
"Test Weight": 56.4,
"Gross Revenue": 814.8
},
"entry_num": 52
},
{
"rank": 45,
"brand": "Revere",
"product": "Seed",
"traits": "Revere 46-F57 XFS",
"metrics": {
"Yield": 77.5,
"%MST": 8.5,
"Test Weight": 55.9,
"Gross Revenue": 813.75
},
"entry_num": 53
},
{
"rank": 46,
"brand": "Benson",
"product": "Hill",
"traits": "N44D923S",
"metrics": {
"Yield": 76.7,
"%MST": 9.0,
"Test Weight": 55.8,
"Gross Revenue": 805.35
},
"entry_num": 55
},
{
"rank": 47,
"brand": "Benson",
"product": "Hill",
"traits": "N35D950S",
"metrics": {
"Yield": 76.4,
"%MST": 8.5,
"Test Weight": 56.1,
"Gross Revenue": 802.2
},
"entry_num": 56
},
{
"rank": 47,
"brand": "Benson",
"product": "Hill",
"traits": "BH37Q218",
"metrics": {
"Yield": 76.4,
"%MST": 8.6,
"Test Weight": 55.1,
"Gross Revenue": 802.2
},
"entry_num": 57
},
{
"rank": 49,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS3923E3/STS",
"metrics": {
"Yield": 76.3,
"%MST": 8.8,
"Test Weight": 55.6,
"Gross Revenue": 801.15
},
"entry_num": 58
},
{
"rank": 50,
"brand": "Xitavo",
"product": "XO",
"traits": "4255E",
"metrics": {
"Yield": 75.9,
"%MST": 8.3,
"Test Weight": 53.4,
"Gross Revenue": 796.04
},
"entry_num": 59
},
{
"rank": 51,
"brand": "Benson",
"product": "Hill",
"traits": "C44H054S",
"metrics": {
"Yield": 74.5,
"%MST": 8.1,
"Test Weight": 55.1,
"Gross Revenue": 782.25
},
"entry_num": 60
},
{
"rank": 52,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7434XF",
"metrics": {
"Yield": 74.2,
"%MST": 8.2,
"Test Weight": 55.2,
"Gross Revenue": 779.1
},
"entry_num": 61
},
{
"rank": 53,
"brand": "Benson",
"product": "Hill",
"traits": "BH43Q207",
"metrics": {
"Yield": 73.8,
"%MST": 8.4,
"Test Weight": 56.0,
"Gross Revenue": 774.9
},
"entry_num": 62
},
{
"rank": 54,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4623E3/STS",
"metrics": {
"Yield": 73.5,
"%MST": 8.6,
"Test Weight": 55.8,
"Gross Revenue": 771.75
},
"entry_num": 63
},
{
"rank": 55,
"brand": "Public",
"product": "P41MO21",
"traits": "",
"metrics": {
"Yield": 71.8,
"%MST": 8.3,
"Test Weight": 54.8,
"Gross Revenue": 753.9
},
"entry_num": 65
},
{
"rank": 55,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4675E3/STS",
"metrics": {
"Yield": 71.8,
"%MST": 8.8,
"Test Weight": 55.6,
"Gross Revenue": 753.9
},
"entry_num": 66
},
{
"rank": 57,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions A5813XF",
"metrics": {
"Yield": 70.6,
"%MST": 9.6,
"Test Weight": 54.6,
"Gross Revenue": 741.3
},
"entry_num": 67
},
{
"rank": 58,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions B4574E",
"metrics": {
"Yield": 68.5,
"%MST": 8.8,
"Test Weight": 55.3,
"Gross Revenue": 719.25
},
"entry_num": 68
},
{
"rank": 59,
"brand": "Public",
"product": "P48MO21",
"traits": "",
"metrics": {
"Yield": 68.3,
"%MST": 8.7,
"Test Weight": 55.1,
"Gross Revenue": 717.15
},
"entry_num": 69
},
{
"rank": 60,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7495XFS",
"metrics": {
"Yield": 66.4,
"%MST": 8.4,
"Test Weight": 54.6,
"Gross Revenue": 697.2
},
"entry_num": 70
},
{
"rank": 61,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4320E3/STS",
"metrics": {
"Yield": 64.0,
"%MST": 8.7,
"Test Weight": 54.8,
"Gross Revenue": 672.0
},
"entry_num": 71
},
{
"rank": 62,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions A5994XF",
"metrics": {
"Yield": 57.3,
"%MST": 12.9,
"Test Weight": 55.6,
"Gross Revenue": 601.65
},
"entry_num": 72
},
{
"rank": 63,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions A6314XF",
"metrics": {
"Yield": 56.6,
"%MST": 9.7,
"Test Weight": 55.3,
"Gross Revenue": 594.3
},
"entry_num": 73
}
],
"n_results": 63,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/de/2024/2435170"
],
"fetched_at": "2026-05-25T19:39:52.973660+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink