justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
d60d747858ddaf4ff7835ade281150d0d5424bf3
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-mi-2024-2452444.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

442 lines
8.9 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-mi-2024-2452444",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Michigan",
"state_abbrev": "mi",
"year": 2024,
"plot_id": "2452444",
"cooperator": "Michigan State University - Hillsdale Early",
"planted_date": "2024-06-04",
"harvested_date": "2024-11-12",
"population_seeds_per_acre": null,
"row_width_in": null,
"results": [
{
"rank": 1,
"brand": "Renk",
"product": "Seed",
"traits": "RS255NXF",
"metrics": {
"Yield": 68.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 718.2
},
"entry_num": 30
},
{
"rank": 2,
"brand": "Xitavo",
"product": "XO",
"traits": "2075E",
"metrics": {
"Yield": 67.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 706.65
},
"entry_num": 36
},
{
"rank": 3,
"brand": "Xitavo",
"product": "XO",
"traits": "2181E",
"metrics": {
"Yield": 67.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 703.5
},
"entry_num": 37
},
{
"rank": 4,
"brand": "NK",
"product": "NK23-D7E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 66.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 702.45
},
"entry_num": 26
},
{
"rank": 5,
"brand": "D.F.",
"product": "Seeds",
"traits": "DF 3245 N E3",
"metrics": {
"Yield": 66.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 700.35
},
"entry_num": 3
},
{
"rank": 6,
"brand": "Xitavo",
"product": "XO",
"traits": "2625E",
"metrics": {
"Yield": 66.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 699.3
},
"entry_num": 40
},
{
"rank": 7,
"brand": "M",
"product": "&",
"traits": "W Seeds 26E08",
"metrics": {
"Yield": 66.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 697.2
},
"entry_num": 24
},
{
"rank": 8,
"brand": "Loyal",
"product": "Brand",
"traits": "L2560E",
"metrics": {
"Yield": 66.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 695.1
},
"entry_num": 19
},
{
"rank": 9,
"brand": "Golden Harvest",
"product": "GH2674E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 65.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 691.95
},
"entry_num": 16
},
{
"rank": 10,
"brand": "D.F.",
"product": "Seeds",
"traits": "DF 3225 N E3",
"metrics": {
"Yield": 65.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 689.85
},
"entry_num": 2
},
{
"rank": 11,
"brand": "Xitavo",
"product": "XO",
"traits": "2735E",
"metrics": {
"Yield": 64.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 681.45
},
"entry_num": 41
},
{
"rank": 12,
"brand": "Xitavo",
"product": "XO",
"traits": "2444E",
"metrics": {
"Yield": 64.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 678.3
},
"entry_num": 39
},
{
"rank": 13,
"brand": "NK",
"product": "NK23-P1E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 64.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 676.2
},
"entry_num": 27
},
{
"rank": 14,
"brand": "Wyckoff",
"product": "Hybrids",
"traits": "W2495E3",
"metrics": {
"Yield": 63.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 670.95
},
"entry_num": 33
},
{
"rank": 15,
"brand": "M",
"product": "&",
"traits": "W Seeds 25E25",
"metrics": {
"Yield": 63.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 668.85
},
"entry_num": 23
},
{
"rank": 16,
"brand": "DonMario",
"product": "Seeds",
"traits": "DM22E64",
"metrics": {
"Yield": 63.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 661.5
},
"entry_num": 5
},
{
"rank": 16,
"brand": "Wyckoff",
"product": "Hybrids",
"traits": "W2570E3",
"metrics": {
"Yield": 63.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 661.5
},
"entry_num": 34
},
{
"rank": 18,
"brand": "Loyal",
"product": "Brand",
"traits": "LSX232-24E",
"metrics": {
"Yield": 62.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 658.35
},
"entry_num": 18
},
{
"rank": 19,
"brand": "D.F.",
"product": "Seeds",
"traits": "DF 3211 N E3",
"metrics": {
"Yield": 62.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 656.25
},
"entry_num": 1
},
{
"rank": 20,
"brand": "DonMario",
"product": "Seeds",
"traits": "DM24E84",
"metrics": {
"Yield": 62.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 655.2
},
"entry_num": 6
},
{
"rank": 21,
"brand": "D.F.",
"product": "Seeds",
"traits": "DF 3264 N E3",
"metrics": {
"Yield": 61.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 649.95
},
"entry_num": 4
},
{
"rank": 22,
"brand": "Golden Harvest",
"product": "GH2745XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 61.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 646.8
},
"entry_num": 17
},
{
"rank": 23,
"brand": "Wyckoff",
"product": "Hybrids",
"traits": "W2695E3",
"metrics": {
"Yield": 61.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 645.75
},
"entry_num": 35
},
{
"rank": 24,
"brand": "M",
"product": "&",
"traits": "W Seeds 18E89",
"metrics": {
"Yield": 60.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 634.2
},
"entry_num": 20
},
{
"rank": 25,
"brand": "Xitavo",
"product": "XO",
"traits": "2305E",
"metrics": {
"Yield": 60.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 631.05
},
"entry_num": 38
},
{
"rank": 26,
"brand": "Renk",
"product": "Seed",
"traits": "G2790E",
"metrics": {
"Yield": 59.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 623.7
},
"entry_num": 29
},
{
"rank": 27,
"brand": "M",
"product": "&",
"traits": "W Seeds 20E71",
"metrics": {
"Yield": 59.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 622.65
},
"entry_num": 21
},
{
"rank": 28,
"brand": "Wyckoff",
"product": "Hybrids",
"traits": "W2095E3",
"metrics": {
"Yield": 56.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 595.35
},
"entry_num": 31
},
{
"rank": 29,
"brand": "M",
"product": "&",
"traits": "W Seeds 27E42",
"metrics": {
"Yield": 54.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 574.35
},
"entry_num": 25
},
{
"rank": 30,
"brand": "M",
"product": "&",
"traits": "W Seeds 23E05",
"metrics": {
"Yield": 53.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 565.95
},
"entry_num": 22
},
{
"rank": 31,
"brand": "Renk",
"product": "Seed",
"traits": "G2390E",
"metrics": {
"Yield": 53.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 564.9
},
"entry_num": 28
},
{
"rank": 32,
"brand": "Wyckoff",
"product": "Hybrids",
"traits": "W2390E3",
"metrics": {
"Yield": 53.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 563.85
},
"entry_num": 32
}
],
"n_results": 32,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/mi/2024/2452444"
],
"fetched_at": "2026-05-25T19:41:22.361988+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink