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-wi-2024-2440890.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

793 lines
16 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-wi-2024-2440890",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Wisconsin",
"state_abbrev": "wi",
"year": 2024,
"plot_id": "2440890",
"cooperator": "University of Wisconsin - Arlington",
"planted_date": "2024-05-06",
"harvested_date": "2024-10-03",
"population_seeds_per_acre": null,
"row_width_in": null,
"results": [
{
"rank": 1,
"brand": "P3",
"product": "Genetics",
"traits": "2527E",
"metrics": {
"Yield": 81.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 850.5
},
"entry_num": 49
},
{
"rank": 2,
"brand": "Asgrow",
"product": "AG20XF4",
"traits": "",
"metrics": {
"Yield": 80.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 840.0
},
"entry_num": 1
},
{
"rank": 2,
"brand": "P3",
"product": "Genetics",
"traits": "2429E",
"metrics": {
"Yield": 80.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 840.0
},
"entry_num": 50
},
{
"rank": 4,
"brand": "Burrus",
"product": "2681E",
"traits": "",
"metrics": {
"Yield": 79.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 829.5
},
"entry_num": 10
},
{
"rank": 4,
"brand": "DonMario",
"product": "Seeds",
"traits": "DM22E64",
"metrics": {
"Yield": 79.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 829.5
},
"entry_num": 15
},
{
"rank": 4,
"brand": "Genesis",
"product": "G2960E",
"traits": "",
"metrics": {
"Yield": 79.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 829.5
},
"entry_num": 33
},
{
"rank": 4,
"brand": "Renk",
"product": "Seed",
"traits": "RS255NXF",
"metrics": {
"Yield": 79.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 829.5
},
"entry_num": 51
},
{
"rank": 4,
"brand": "Stine",
"product": "25EG23",
"traits": "",
"metrics": {
"Yield": 79.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 829.5
},
"entry_num": 57
},
{
"rank": 4,
"brand": "Tracy",
"product": "Seeds",
"traits": "2655E",
"metrics": {
"Yield": 79.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 829.5
},
"entry_num": 62
},
{
"rank": 4,
"brand": "Tracy",
"product": "Seeds",
"traits": "2754E",
"metrics": {
"Yield": 79.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 829.5
},
"entry_num": 63
},
{
"rank": 4,
"brand": "Xitavo",
"product": "XO",
"traits": "2444E",
"metrics": {
"Yield": 79.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 829.5
},
"entry_num": 68
},
{
"rank": 12,
"brand": "DonMario",
"product": "Seeds",
"traits": "DM24E84",
"metrics": {
"Yield": 78.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 819.0
},
"entry_num": 16
},
{
"rank": 12,
"brand": "P3",
"product": "Genetics",
"traits": "2424E",
"metrics": {
"Yield": 78.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 819.0
},
"entry_num": 47
},
{
"rank": 12,
"brand": "Stine",
"product": "19EC12",
"traits": "",
"metrics": {
"Yield": 78.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 819.0
},
"entry_num": 52
},
{
"rank": 12,
"brand": "Stine",
"product": "22EG02",
"traits": "",
"metrics": {
"Yield": 78.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 819.0
},
"entry_num": 55
},
{
"rank": 16,
"brand": "Asgrow",
"product": "AG26XF4",
"traits": "",
"metrics": {
"Yield": 77.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 808.5
},
"entry_num": 7
},
{
"rank": 16,
"brand": "Xitavo",
"product": "XO",
"traits": "2832E",
"metrics": {
"Yield": 77.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 808.5
},
"entry_num": 71
},
{
"rank": 18,
"brand": "Genesis",
"product": "G2790E",
"traits": "",
"metrics": {
"Yield": 76.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 798.0
},
"entry_num": 32
},
{
"rank": 18,
"brand": "NK",
"product": "NK26-M6E3",
"traits": "",
"metrics": {
"Yield": 76.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 798.0
},
"entry_num": 43
},
{
"rank": 20,
"brand": "Asgrow",
"product": "AG24XF4",
"traits": "",
"metrics": {
"Yield": 75.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 787.5
},
"entry_num": 5
},
{
"rank": 20,
"brand": "Burrus",
"product": "2729E",
"traits": "",
"metrics": {
"Yield": 75.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 787.5
},
"entry_num": 11
},
{
"rank": 20,
"brand": "DonMario",
"product": "Seeds",
"traits": "DM24E84",
"metrics": {
"Yield": 75.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 787.5
},
"entry_num": 14
},
{
"rank": 20,
"brand": "Genesis",
"product": "G2570ES",
"traits": "",
"metrics": {
"Yield": 75.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 787.5
},
"entry_num": 31
},
{
"rank": 20,
"brand": "Stine",
"product": "19EG92",
"traits": "",
"metrics": {
"Yield": 75.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 787.5
},
"entry_num": 53
},
{
"rank": 20,
"brand": "Xitavo",
"product": "XO",
"traits": "2282E",
"metrics": {
"Yield": 75.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 787.5
},
"entry_num": 66
},
{
"rank": 26,
"brand": "Asgrow",
"product": "AG21XF2",
"traits": "",
"metrics": {
"Yield": 74.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 777.0
},
"entry_num": 2
},
{
"rank": 26,
"brand": "Burrus",
"product": "2335E",
"traits": "",
"metrics": {
"Yield": 74.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 777.0
},
"entry_num": 9
},
{
"rank": 26,
"brand": "Cornelius",
"product": "Seed",
"traits": "CB25XF99",
"metrics": {
"Yield": 74.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 777.0
},
"entry_num": 13
},
{
"rank": 26,
"brand": "Golden Harvest",
"product": "GH2674E3",
"traits": "",
"metrics": {
"Yield": 74.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 777.0
},
"entry_num": 34
},
{
"rank": 26,
"brand": "P3",
"product": "Genetics",
"traits": "2325E",
"metrics": {
"Yield": 74.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 777.0
},
"entry_num": 48
},
{
"rank": 26,
"brand": "Stine",
"product": "24EG23",
"traits": "",
"metrics": {
"Yield": 74.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 777.0
},
"entry_num": 56
},
{
"rank": 26,
"brand": "Stine",
"product": "28EG32",
"traits": "",
"metrics": {
"Yield": 74.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 777.0
},
"entry_num": 58
},
{
"rank": 26,
"brand": "Xitavo",
"product": "XO",
"traits": "2865E",
"metrics": {
"Yield": 74.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 777.0
},
"entry_num": 72
},
{
"rank": 26,
"brand": "Xitavo",
"product": "XO",
"traits": "2985E",
"metrics": {
"Yield": 74.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 777.0
},
"entry_num": 73
},
{
"rank": 35,
"brand": "Asgrow",
"product": "AG25XF5",
"traits": "",
"metrics": {
"Yield": 73.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 766.5
},
"entry_num": 6
},
{
"rank": 35,
"brand": "Golden Harvest",
"product": "GH2775E3",
"traits": "",
"metrics": {
"Yield": 73.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 766.5
},
"entry_num": 35
},
{
"rank": 35,
"brand": "Loyal",
"product": "Brand",
"traits": "L2560E",
"metrics": {
"Yield": 73.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 766.5
},
"entry_num": 39
},
{
"rank": 35,
"brand": "NK",
"product": "NK21-C2E3",
"traits": "",
"metrics": {
"Yield": 73.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 766.5
},
"entry_num": 41
},
{
"rank": 39,
"brand": "NK",
"product": "NK27-J5E3",
"traits": "",
"metrics": {
"Yield": 72.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 756.0
},
"entry_num": 44
},
{
"rank": 39,
"brand": "O'Brien",
"product": "Hybrids",
"traits": "O'Soy 2523EL-3",
"metrics": {
"Yield": 72.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 756.0
},
"entry_num": 46
},
{
"rank": 39,
"brand": "Tracy",
"product": "Seeds",
"traits": "2355E",
"metrics": {
"Yield": 72.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 756.0
},
"entry_num": 61
},
{
"rank": 39,
"brand": "Xitavo",
"product": "XO",
"traits": "2181E",
"metrics": {
"Yield": 72.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 756.0
},
"entry_num": 65
},
{
"rank": 43,
"brand": "Cornelius",
"product": "Seed",
"traits": "CB24XF75",
"metrics": {
"Yield": 71.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 745.5
},
"entry_num": 12
},
{
"rank": 43,
"brand": "NK",
"product": "NK23-P1E3",
"traits": "",
"metrics": {
"Yield": 71.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 745.5
},
"entry_num": 42
},
{
"rank": 43,
"brand": "O'Brien",
"product": "Hybrids",
"traits": "O'Soy 2024EL-3",
"metrics": {
"Yield": 71.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 745.5
},
"entry_num": 45
},
{
"rank": 43,
"brand": "Xitavo",
"product": "XO",
"traits": "1822E",
"metrics": {
"Yield": 71.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 745.5
},
"entry_num": 64
},
{
"rank": 43,
"brand": "Xitavo",
"product": "XO",
"traits": "2735E",
"metrics": {
"Yield": 71.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 745.5
},
"entry_num": 70
},
{
"rank": 48,
"brand": "Xitavo",
"product": "XO",
"traits": "2625E",
"metrics": {
"Yield": 70.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 735.0
},
"entry_num": 69
},
{
"rank": 49,
"brand": "Xitavo",
"product": "XO",
"traits": "2305E",
"metrics": {
"Yield": 69.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 724.5
},
"entry_num": 67
},
{
"rank": 50,
"brand": "Stine",
"product": "21EG32",
"traits": "",
"metrics": {
"Yield": 68.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 714.0
},
"entry_num": 54
},
{
"rank": 51,
"brand": "Asgrow",
"product": "AG22XF5",
"traits": "",
"metrics": {
"Yield": 67.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 703.5
},
"entry_num": 3
},
{
"rank": 51,
"brand": "Loyal",
"product": "Brand",
"traits": "L2070E",
"metrics": {
"Yield": 67.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 703.5
},
"entry_num": 36
},
{
"rank": 51,
"brand": "NK",
"product": "NK19-T8E3S",
"traits": "",
"metrics": {
"Yield": 67.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 703.5
},
"entry_num": 40
},
{
"rank": 54,
"brand": "Loyal",
"product": "Brand",
"traits": "L2160E",
"metrics": {
"Yield": 66.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 693.0
},
"entry_num": 37
},
{
"rank": 54,
"brand": "Loyal",
"product": "Brand",
"traits": "L2370E",
"metrics": {
"Yield": 66.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 693.0
},
"entry_num": 38
},
{
"rank": 56,
"brand": "Burrus",
"product": "2084E",
"traits": "",
"metrics": {
"Yield": 65.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 682.5
},
"entry_num": 8
},
{
"rank": 56,
"brand": "Tracy",
"product": "Seeds",
"traits": "2255E",
"metrics": {
"Yield": 65.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 682.5
},
"entry_num": 60
},
{
"rank": 58,
"brand": "Tracy",
"product": "Seeds",
"traits": "2055E",
"metrics": {
"Yield": 63.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 661.5
},
"entry_num": 59
},
{
"rank": 59,
"brand": "Asgrow",
"product": "AG24XF1",
"traits": "",
"metrics": {
"Yield": 62.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 651.0
},
"entry_num": 4
}
],
"n_results": 59,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/wi/2024/2440890"
],
"fetched_at": "2026-05-25T19:40:33.304821+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink