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-ok-2025-2470359.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

559 lines
11 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-ok-2025-2470359",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Oklahoma",
"state_abbrev": "ok",
"year": 2025,
"plot_id": "2470359",
"cooperator": "Wright Seed Llc",
"planted_date": "2025-06-15",
"harvested_date": "2025-11-05",
"population_seeds_per_acre": 140000,
"row_width_in": 30,
"results": [
{
"rank": 1,
"brand": "Beck's",
"product": "4661XF",
"traits": "",
"metrics": {
"Yield": 51.1,
"%MST": 5.9,
"Test Weight": 53.4,
"Gross Revenue": 535.94
},
"entry_num": 18
},
{
"rank": 2,
"brand": "AgriGold",
"product": "G5364XF",
"traits": "",
"metrics": {
"Yield": 48.4,
"%MST": 6.3,
"Test Weight": 55.5,
"Gross Revenue": 508.2
},
"entry_num": 4
},
{
"rank": 3,
"brand": "Pioneer",
"product": "P48A14E",
"traits": "",
"metrics": {
"Yield": 46.0,
"%MST": 5.9,
"Test Weight": 54.6,
"Gross Revenue": 483.0
},
"entry_num": 35
},
{
"rank": 4,
"brand": "Asgrow",
"product": "AG48XF5",
"traits": "",
"metrics": {
"Yield": 45.4,
"%MST": 6.0,
"Test Weight": 53.2,
"Gross Revenue": 475.97
},
"entry_num": 9
},
{
"rank": 4,
"brand": "NSGA",
"product": "Sitzer",
"traits": "4.9",
"metrics": {
"Yield": 45.4,
"%MST": 5.5,
"Test Weight": 56.8,
"Gross Revenue": 476.7
},
"entry_num": 29
},
{
"rank": 6,
"brand": "Asgrow",
"product": "AG46XF2",
"traits": "",
"metrics": {
"Yield": 45.2,
"%MST": 5.6,
"Test Weight": 54.5,
"Gross Revenue": 474.6
},
"entry_num": 7
},
{
"rank": 7,
"brand": "NSGA",
"product": "Drew",
"traits": "III",
"metrics": {
"Yield": 44.4,
"%MST": 5.9,
"Test Weight": 56.5,
"Gross Revenue": 466.2
},
"entry_num": 31
},
{
"rank": 8,
"brand": "Asgrow",
"product": "AG48XF6",
"traits": "",
"metrics": {
"Yield": 43.6,
"%MST": 5.6,
"Test Weight": 54.5,
"Gross Revenue": 457.8
},
"entry_num": 10
},
{
"rank": 9,
"brand": "Golden Harvest",
"product": "GH4775E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 42.8,
"%MST": 5.5,
"Test Weight": 54.3,
"Gross Revenue": 449.4
},
"entry_num": 39
},
{
"rank": 10,
"brand": "AgriGold",
"product": "G4650XF",
"traits": "",
"metrics": {
"Yield": 40.2,
"%MST": 5.6,
"Test Weight": 53.6,
"Gross Revenue": 421.78
},
"entry_num": 1
},
{
"rank": 11,
"brand": "Golden Harvest",
"product": "GH4696E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 39.7,
"%MST": 5.2,
"Test Weight": 53.7,
"Gross Revenue": 416.61
},
"entry_num": 38
},
{
"rank": 12,
"brand": "Pioneer",
"product": "P49Z02E",
"traits": "",
"metrics": {
"Yield": 39.1,
"%MST": 5.3,
"Test Weight": 53.3,
"Gross Revenue": 410.0
},
"entry_num": 36
},
{
"rank": 13,
"brand": "Pioneer",
"product": "P44Z67BE",
"traits": "",
"metrics": {
"Yield": 39.0,
"%MST": 5.4,
"Test Weight": 52.3,
"Gross Revenue": 408.17
},
"entry_num": 32
},
{
"rank": 14,
"brand": "Beck's",
"product": "4760E3",
"traits": "",
"metrics": {
"Yield": 38.9,
"%MST": 5.4,
"Test Weight": 53.4,
"Gross Revenue": 407.98
},
"entry_num": 19
},
{
"rank": 15,
"brand": "AgriGold",
"product": "G5104XF",
"traits": "",
"metrics": {
"Yield": 38.5,
"%MST": 6.0,
"Test Weight": 52.8,
"Gross Revenue": 403.33
},
"entry_num": 3
},
{
"rank": 16,
"brand": "Beck's",
"product": "4860E3",
"traits": "",
"metrics": {
"Yield": 37.9,
"%MST": 5.3,
"Test Weight": 55.0,
"Gross Revenue": 397.95
},
"entry_num": 21
},
{
"rank": 17,
"brand": "Golden Harvest",
"product": "GH4766XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 37.3,
"%MST": 5.2,
"Test Weight": 54.5,
"Gross Revenue": 391.65
},
"entry_num": 25
},
{
"rank": 18,
"brand": "Beck's",
"product": "4551XF",
"traits": "",
"metrics": {
"Yield": 37.1,
"%MST": 5.9,
"Test Weight": 52.9,
"Gross Revenue": 388.73
},
"entry_num": 17
},
{
"rank": 19,
"brand": "Golden Harvest",
"product": "GH4995E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 37.0,
"%MST": 5.2,
"Test Weight": 53.8,
"Gross Revenue": 388.35
},
"entry_num": 40
},
{
"rank": 20,
"brand": "AgriGold",
"product": "G4755XF",
"traits": "",
"metrics": {
"Yield": 36.6,
"%MST": 5.5,
"Test Weight": 53.8,
"Gross Revenue": 384.15
},
"entry_num": 2
},
{
"rank": 21,
"brand": "Beck's",
"product": "4777XF",
"traits": "",
"metrics": {
"Yield": 36.3,
"%MST": 5.6,
"Test Weight": 52.9,
"Gross Revenue": 380.35
},
"entry_num": 20
},
{
"rank": 22,
"brand": "Golden Harvest",
"product": "GH4882XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 36.1,
"%MST": 5.6,
"Test Weight": 53.9,
"Gross Revenue": 378.98
},
"entry_num": 26
},
{
"rank": 23,
"brand": "Asgrow",
"product": "AG49XF3",
"traits": "",
"metrics": {
"Yield": 36.0,
"%MST": 5.7,
"Test Weight": 54.4,
"Gross Revenue": 378.0
},
"entry_num": 11
},
{
"rank": 24,
"brand": "Golden Harvest",
"product": "GH4944XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 35.8,
"%MST": 5.2,
"Test Weight": 53.6,
"Gross Revenue": 375.61
},
"entry_num": 27
},
{
"rank": 24,
"brand": "Pioneer",
"product": "P47Z15BE",
"traits": "",
"metrics": {
"Yield": 35.8,
"%MST": 5.3,
"Test Weight": 55.1,
"Gross Revenue": 375.9
},
"entry_num": 34
},
{
"rank": 26,
"brand": "Golden Harvest",
"product": "GH5056E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 35.1,
"%MST": 5.7,
"Test Weight": 52.1,
"Gross Revenue": 367.22
},
"entry_num": 41
},
{
"rank": 27,
"brand": "Alloy",
"product": "A47E35",
"traits": "",
"metrics": {
"Yield": 34.1,
"%MST": 5.7,
"Test Weight": 54.6,
"Gross Revenue": 358.05
},
"entry_num": 5
},
{
"rank": 28,
"brand": "Asgrow",
"product": "AG49XF6",
"traits": "",
"metrics": {
"Yield": 33.0,
"%MST": 5.3,
"Test Weight": 54.2,
"Gross Revenue": 346.5
},
"entry_num": 12
},
{
"rank": 28,
"brand": "Pioneer",
"product": "P50Z95E",
"traits": "",
"metrics": {
"Yield": 33.0,
"%MST": 5.2,
"Test Weight": 53.7,
"Gross Revenue": 346.3
},
"entry_num": 37
},
{
"rank": 30,
"brand": "Asgrow",
"product": "AG52XF5",
"traits": "",
"metrics": {
"Yield": 32.9,
"%MST": 5.2,
"Test Weight": 49.8,
"Gross Revenue": 342.69
},
"entry_num": 14
},
{
"rank": 31,
"brand": "Beck's",
"product": "4999XF",
"traits": "",
"metrics": {
"Yield": 32.7,
"%MST": 5.2,
"Test Weight": 54.1,
"Gross Revenue": 343.35
},
"entry_num": 22
},
{
"rank": 32,
"brand": "Golden Harvest",
"product": "GH5226XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 31.3,
"%MST": 5.6,
"Test Weight": 54.1,
"Gross Revenue": 328.65
},
"entry_num": 28
},
{
"rank": 33,
"brand": "Asgrow",
"product": "AG52XF0",
"traits": "",
"metrics": {
"Yield": 30.8,
"%MST": 5.8,
"Test Weight": 53.8,
"Gross Revenue": 323.28
},
"entry_num": 13
},
{
"rank": 34,
"brand": "NSGA",
"product": "52Cl22",
"traits": "",
"metrics": {
"Yield": 30.3,
"%MST": 6.2,
"Test Weight": 54.5,
"Gross Revenue": 318.15
},
"entry_num": 30
},
{
"rank": 35,
"brand": "Asgrow",
"product": "AG47XF2",
"traits": "",
"metrics": {
"Yield": 30.2,
"%MST": 5.4,
"Test Weight": 54.1,
"Gross Revenue": 317.1
},
"entry_num": 8
},
{
"rank": 36,
"brand": "Pioneer",
"product": "P45Z75E",
"traits": "",
"metrics": {
"Yield": 29.8,
"%MST": 5.1,
"Test Weight": 54.3,
"Gross Revenue": 312.9
},
"entry_num": 33
},
{
"rank": 37,
"brand": "Golden Harvest",
"product": "GH4546XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 29.5,
"%MST": 5.4,
"Test Weight": 51.5,
"Gross Revenue": 308.28
},
"entry_num": 24
},
{
"rank": 38,
"brand": "Alloy",
"product": "A49E34",
"traits": "",
"metrics": {
"Yield": 28.5,
"%MST": 5.9,
"Test Weight": 49.2,
"Gross Revenue": 296.51
},
"entry_num": 6
},
{
"rank": 39,
"brand": "Beck's",
"product": "4991X2",
"traits": "",
"metrics": {
"Yield": 24.4,
"%MST": 5.2,
"Test Weight": 53.8,
"Gross Revenue": 256.1
},
"entry_num": 23
},
{
"rank": 40,
"brand": "Beck's",
"product": "4337XF",
"traits": "",
"metrics": {
"Yield": 24.0,
"%MST": 5.5,
"Test Weight": 49.8,
"Gross Revenue": 249.98
},
"entry_num": 16
},
{
"rank": 41,
"brand": "Beck's",
"product": "4320E3",
"traits": "",
"metrics": {
"Yield": 21.7,
"%MST": 7.9,
"Test Weight": 51.2,
"Gross Revenue": 226.63
},
"entry_num": 15
}
],
"n_results": 41,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/ok/2025/2470359"
],
"fetched_at": "2026-05-25T19:52:53.267015+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink