justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
eaa7e0789bd3b8800de494cc17103ee16d79a4c3
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-mo-2024-2420189.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

481 lines
9.7 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-mo-2024-2420189",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Missouri",
"state_abbrev": "mo",
"year": 2024,
"plot_id": "2420189",
"cooperator": "University of Missouri - Truxton",
"planted_date": "2024-05-20",
"harvested_date": "2024-10-02",
"population_seeds_per_acre": null,
"row_width_in": null,
"results": [
{
"rank": 1,
"brand": "Asgrow",
"product": "AG40XF1",
"traits": "",
"metrics": {
"Yield": 62.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 656.25
},
"entry_num": 2
},
{
"rank": 2,
"brand": "Lakeview",
"product": "Farms",
"traits": "Experimental",
"metrics": {
"Yield": 60.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 639.45
},
"entry_num": 4
},
{
"rank": 3,
"brand": "Golden Harvest",
"product": "GH4093E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 60.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 637.35
},
"entry_num": 5
},
{
"rank": 4,
"brand": "NuTech",
"product": "Seed",
"traits": "43N06E",
"metrics": {
"Yield": 60.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 635.25
},
"entry_num": 6
},
{
"rank": 5,
"brand": "Pioneer",
"product": "P44A91E",
"traits": "",
"metrics": {
"Yield": 59.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 625.8
},
"entry_num": 7
},
{
"rank": 6,
"brand": "Pioneer",
"product": "P40A23E",
"traits": "",
"metrics": {
"Yield": 59.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 620.55
},
"entry_num": 8
},
{
"rank": 7,
"brand": "NuTech",
"product": "Seed",
"traits": "45N10E",
"metrics": {
"Yield": 58.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 618.45
},
"entry_num": 9
},
{
"rank": 8,
"brand": "AgVenture",
"product": "AV47Y6E",
"traits": "",
"metrics": {
"Yield": 58.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 614.25
},
"entry_num": 10
},
{
"rank": 9,
"brand": "NK",
"product": "NK40-P5E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 58.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 612.15
},
"entry_num": 11
},
{
"rank": 10,
"brand": "Asgrow",
"product": "AG42XF4",
"traits": "",
"metrics": {
"Yield": 57.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 601.65
},
"entry_num": 12
},
{
"rank": 11,
"brand": "Pioneer",
"product": "P47Z15BE",
"traits": "",
"metrics": {
"Yield": 57.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 598.5
},
"entry_num": 13
},
{
"rank": 12,
"brand": "Channel",
"product": "4720RXF/SR",
"traits": "",
"metrics": {
"Yield": 56.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 597.45
},
"entry_num": 14
},
{
"rank": 13,
"brand": "Asgrow",
"product": "AG47XF2",
"traits": "",
"metrics": {
"Yield": 56.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 594.3
},
"entry_num": 15
},
{
"rank": 14,
"brand": "NuTech",
"product": "Seed",
"traits": "47N04E",
"metrics": {
"Yield": 56.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 593.25
},
"entry_num": 16
},
{
"rank": 15,
"brand": "Missouri",
"product": "U",
"traits": "S20-2227",
"metrics": {
"Yield": 56.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 590.1
},
"entry_num": 17
},
{
"rank": 16,
"brand": "Lakeview",
"product": "Farms",
"traits": "LVF4331",
"metrics": {
"Yield": 56.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 588.0
},
"entry_num": 18
},
{
"rank": 17,
"brand": "Asgrow",
"product": "AG41XF2",
"traits": "",
"metrics": {
"Yield": 55.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 586.95
},
"entry_num": 19
},
{
"rank": 18,
"brand": "Golden Harvest",
"product": "GH4214E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 55.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 583.8
},
"entry_num": 20
},
{
"rank": 19,
"brand": "Pioneer",
"product": "P45A70LX",
"traits": "",
"metrics": {
"Yield": 55.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 582.75
},
"entry_num": 21
},
{
"rank": 19,
"brand": "Pioneer",
"product": "P45Z75E",
"traits": "",
"metrics": {
"Yield": 55.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 582.75
},
"entry_num": 22
},
{
"rank": 21,
"brand": "NuTech",
"product": "Seed",
"traits": "49N05E",
"metrics": {
"Yield": 55.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 577.5
},
"entry_num": 23
},
{
"rank": 22,
"brand": "NuTech",
"product": "Seed",
"traits": "42N05E",
"metrics": {
"Yield": 54.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 574.35
},
"entry_num": 24
},
{
"rank": 22,
"brand": "Pioneer",
"product": "P42A84E",
"traits": "",
"metrics": {
"Yield": 54.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 574.35
},
"entry_num": 25
},
{
"rank": 22,
"brand": "Pioneer",
"product": "P43Z44SE",
"traits": "",
"metrics": {
"Yield": 54.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 574.35
},
"entry_num": 26
},
{
"rank": 25,
"brand": "Golden Harvest",
"product": "GH4433E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 54.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 569.1
},
"entry_num": 27
},
{
"rank": 26,
"brand": "Pioneer",
"product": "P49Z02E",
"traits": "",
"metrics": {
"Yield": 53.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 564.9
},
"entry_num": 28
},
{
"rank": 27,
"brand": "NK",
"product": "NK42-A6E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 53.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 562.8
},
"entry_num": 29
},
{
"rank": 28,
"brand": "Pioneer",
"product": "P46A09E",
"traits": "",
"metrics": {
"Yield": 53.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 556.5
},
"entry_num": 30
},
{
"rank": 29,
"brand": "Channel",
"product": "4823RXF/SR",
"traits": "",
"metrics": {
"Yield": 52.7,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 553.35
},
"entry_num": 31
},
{
"rank": 30,
"brand": "Pioneer",
"product": "P46A90LX",
"traits": "",
"metrics": {
"Yield": 52.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 551.25
},
"entry_num": 33
},
{
"rank": 31,
"brand": "Pioneer",
"product": "P48Z70BLX",
"traits": "",
"metrics": {
"Yield": 52.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 547.05
},
"entry_num": 35
},
{
"rank": 32,
"brand": "AgVenture",
"product": "AV45B2E",
"traits": "",
"metrics": {
"Yield": 52.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 546.0
},
"entry_num": 36
},
{
"rank": 32,
"brand": "Asgrow",
"product": "AG44XF4",
"traits": "",
"metrics": {
"Yield": 52.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 546.0
},
"entry_num": 37
},
{
"rank": 34,
"brand": "AgVenture",
"product": "AV44B2E",
"traits": "",
"metrics": {
"Yield": 50.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 528.15
},
"entry_num": 38
},
{
"rank": 35,
"brand": "Brevant",
"product": "B402EE",
"traits": "",
"metrics": {
"Yield": 46.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 487.2
},
"entry_num": 40
}
],
"n_results": 35,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/mo/2024/2420189"
],
"fetched_at": "2026-05-25T19:35:15.812253+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink