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-mo-2024-2420198.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

598 lines
12 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-mo-2024-2420198",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Missouri",
"state_abbrev": "mo",
"year": 2024,
"plot_id": "2420198",
"cooperator": "University of Missouri - Dexter",
"planted_date": "2024-04-24",
"harvested_date": "2024-10-04",
"population_seeds_per_acre": null,
"row_width_in": null,
"results": [
{
"rank": 1,
"brand": "Delta",
"product": "Grow",
"traits": "DG43XF65STS",
"metrics": {
"Yield": 93.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 984.9
},
"entry_num": 2
},
{
"rank": 2,
"brand": "Delta",
"product": "Grow",
"traits": "DG48XF70STS",
"metrics": {
"Yield": 92.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 968.1
},
"entry_num": 4
},
{
"rank": 3,
"brand": "Golden Harvest",
"product": "GH4452XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 92.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 967.05
},
"entry_num": 5
},
{
"rank": 4,
"brand": "Golden Harvest",
"product": "GH4944XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 91.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 964.95
},
"entry_num": 6
},
{
"rank": 5,
"brand": "Pioneer",
"product": "P45A70LX",
"traits": "",
"metrics": {
"Yield": 91.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 962.85
},
"entry_num": 7
},
{
"rank": 6,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7461XFS",
"metrics": {
"Yield": 90.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 952.35
},
"entry_num": 8
},
{
"rank": 7,
"brand": "Axis",
"product": "Seed",
"traits": "4815XFS",
"metrics": {
"Yield": 90.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 949.2
},
"entry_num": 9
},
{
"rank": 8,
"brand": "Pioneer",
"product": "P48Z70BLX",
"traits": "",
"metrics": {
"Yield": 89.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 938.7
},
"entry_num": 10
},
{
"rank": 9,
"brand": "Delta",
"product": "Grow",
"traits": "DG46XF54STS",
"metrics": {
"Yield": 89.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 934.5
},
"entry_num": 11
},
{
"rank": 10,
"brand": "Axis",
"product": "Seed",
"traits": "4613XF",
"metrics": {
"Yield": 88.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 932.4
},
"entry_num": 12
},
{
"rank": 11,
"brand": "Axis",
"product": "Seed",
"traits": "4625XFS",
"metrics": {
"Yield": 87.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 921.9
},
"entry_num": 14
},
{
"rank": 12,
"brand": "Channel",
"product": "4720RXF/SR",
"traits": "",
"metrics": {
"Yield": 86.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 908.25
},
"entry_num": 17
},
{
"rank": 13,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7463XF",
"metrics": {
"Yield": 85.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 900.9
},
"entry_num": 18
},
{
"rank": 14,
"brand": "Asgrow",
"product": "AG40XF1",
"traits": "",
"metrics": {
"Yield": 84.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 890.4
},
"entry_num": 19
},
{
"rank": 15,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7495XFS",
"metrics": {
"Yield": 84.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 882.0
},
"entry_num": 21
},
{
"rank": 16,
"brand": "Pioneer",
"product": "P46A90LX",
"traits": "",
"metrics": {
"Yield": 83.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 879.9
},
"entry_num": 22
},
{
"rank": 17,
"brand": "Channel",
"product": "3823RXF",
"traits": "",
"metrics": {
"Yield": 81.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 852.6
},
"entry_num": 24
},
{
"rank": 18,
"brand": "Channel",
"product": "4823RXF/SR",
"traits": "",
"metrics": {
"Yield": 79.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 829.5
},
"entry_num": 26
},
{
"rank": 19,
"brand": "Golden Harvest",
"product": "GH4864XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 78.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 824.25
},
"entry_num": 27
},
{
"rank": 20,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7435XFS",
"metrics": {
"Yield": 78.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 823.2
},
"entry_num": 28
},
{
"rank": 21,
"brand": "Asgrow",
"product": "AG36XF4",
"traits": "",
"metrics": {
"Yield": 78.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 820.05
},
"entry_num": 29
},
{
"rank": 21,
"brand": "Asgrow",
"product": "AG38XF1",
"traits": "",
"metrics": {
"Yield": 78.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 820.05
},
"entry_num": 30
},
{
"rank": 21,
"brand": "Asgrow",
"product": "AG47XF2",
"traits": "",
"metrics": {
"Yield": 78.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 820.05
},
"entry_num": 31
},
{
"rank": 24,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7474XFS",
"metrics": {
"Yield": 77.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 814.8
},
"entry_num": 32
},
{
"rank": 25,
"brand": "Axis",
"product": "Seed",
"traits": "4105XF",
"metrics": {
"Yield": 77.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 810.6
},
"entry_num": 33
},
{
"rank": 26,
"brand": "Axis",
"product": "Seed",
"traits": "4905XF",
"metrics": {
"Yield": 76.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 798.0
},
"entry_num": 34
},
{
"rank": 27,
"brand": "Asgrow",
"product": "AG39XF3",
"traits": "",
"metrics": {
"Yield": 73.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 774.9
},
"entry_num": 37
},
{
"rank": 28,
"brand": "Asgrow",
"product": "AG37XF1",
"traits": "",
"metrics": {
"Yield": 69.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 727.65
},
"entry_num": 40
},
{
"rank": 29,
"brand": "AgVenture",
"product": "AV48B2E",
"traits": "",
"metrics": {
"Yield": 68.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 714.0
},
"entry_num": 41
},
{
"rank": 30,
"brand": "Asgrow",
"product": "AG44XF4",
"traits": "",
"metrics": {
"Yield": 66.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 697.2
},
"entry_num": 42
},
{
"rank": 31,
"brand": "Pioneer",
"product": "P37A18E",
"traits": "",
"metrics": {
"Yield": 65.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 686.7
},
"entry_num": 43
},
{
"rank": 32,
"brand": "Delta",
"product": "Grow",
"traits": "DG49XF85STS",
"metrics": {
"Yield": 64.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 676.2
},
"entry_num": 45
},
{
"rank": 33,
"brand": "Pioneer",
"product": "P44A91E",
"traits": "",
"metrics": {
"Yield": 63.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 661.5
},
"entry_num": 46
},
{
"rank": 34,
"brand": "Delta",
"product": "Grow",
"traits": "DG47XF90STS",
"metrics": {
"Yield": 62.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 654.15
},
"entry_num": 47
},
{
"rank": 35,
"brand": "Pioneer",
"product": "P34A98E",
"traits": "",
"metrics": {
"Yield": 60.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 636.3
},
"entry_num": 48
},
{
"rank": 36,
"brand": "Pioneer",
"product": "P40A23E",
"traits": "",
"metrics": {
"Yield": 60.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 632.1
},
"entry_num": 49
},
{
"rank": 37,
"brand": "Pioneer",
"product": "P46A09E",
"traits": "",
"metrics": {
"Yield": 60.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 631.05
},
"entry_num": 50
},
{
"rank": 38,
"brand": "AgVenture",
"product": "AV47Y6E",
"traits": "",
"metrics": {
"Yield": 59.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 623.7
},
"entry_num": 51
},
{
"rank": 39,
"brand": "AgVenture",
"product": "AV45B2E",
"traits": "",
"metrics": {
"Yield": 59.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 621.6
},
"entry_num": 52
},
{
"rank": 40,
"brand": "Benson",
"product": "Hill",
"traits": "BH43Q207",
"metrics": {
"Yield": 59.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 620.55
},
"entry_num": 53
},
{
"rank": 41,
"brand": "AgVenture",
"product": "AV44B2E",
"traits": "",
"metrics": {
"Yield": 58.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 617.4
},
"entry_num": 54
},
{
"rank": 42,
"brand": "Pioneer",
"product": "P38A28E",
"traits": "",
"metrics": {
"Yield": 58.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 616.35
},
"entry_num": 55
},
{
"rank": 43,
"brand": "Brevant",
"product": "B364EE",
"traits": "",
"metrics": {
"Yield": 55.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 579.6
},
"entry_num": 56
},
{
"rank": 44,
"brand": "Brevant",
"product": "B394EE",
"traits": "",
"metrics": {
"Yield": 50.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 528.15
},
"entry_num": 57
}
],
"n_results": 44,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/mo/2024/2420198"
],
"fetched_at": "2026-05-25T19:35:19.526630+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink