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-nd-2025-2466623.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

364 lines
7.4 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-nd-2025-2466623",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "North Dakota",
"state_abbrev": "nd",
"year": 2025,
"plot_id": "2466623",
"cooperator": "Chs Dakota Plains Ag",
"planted_date": "2025-05-29",
"harvested_date": "2025-10-09",
"population_seeds_per_acre": 145000,
"row_width_in": 22,
"results": [
{
"rank": 1,
"brand": "Brevant",
"product": "B054EE",
"traits": "",
"metrics": {
"Yield": 44.9,
"%MST": 10.6,
"Test Weight": 56.8,
"Gross Revenue": 471.45
},
"entry_num": 7
},
{
"rank": 2,
"brand": "NK",
"product": "NK04-Q9XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 42.8,
"%MST": 10.8,
"Test Weight": 58.9,
"Gross Revenue": 449.4
},
"entry_num": 3
},
{
"rank": 3,
"brand": "Asgrow",
"product": "AG05XF4",
"traits": "",
"metrics": {
"Yield": 40.5,
"%MST": 10.7,
"Test Weight": 56.3,
"Gross Revenue": 425.25
},
"entry_num": 6
},
{
"rank": 3,
"brand": "NK",
"product": "NK11-U2XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 40.5,
"%MST": 10.5,
"Test Weight": 58.9,
"Gross Revenue": 425.25
},
"entry_num": 26
},
{
"rank": 5,
"brand": "NK",
"product": "NK06-C4XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 40.3,
"%MST": 10.4,
"Test Weight": 57.7,
"Gross Revenue": 423.15
},
"entry_num": 11
},
{
"rank": 6,
"brand": "NK",
"product": "NK06-A1E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 40.2,
"%MST": 10.8,
"Test Weight": 57.6,
"Gross Revenue": 422.1
},
"entry_num": 9
},
{
"rank": 7,
"brand": "Brevant",
"product": "B074EE",
"traits": "",
"metrics": {
"Yield": 39.9,
"%MST": 10.2,
"Test Weight": 57.8,
"Gross Revenue": 418.95
},
"entry_num": 15
},
{
"rank": 8,
"brand": "Asgrow",
"product": "AG06XF3",
"traits": "",
"metrics": {
"Yield": 39.6,
"%MST": 10.5,
"Test Weight": 58.2,
"Gross Revenue": 415.8
},
"entry_num": 10
},
{
"rank": 9,
"brand": "Brevant",
"product": "B032EE",
"traits": "",
"metrics": {
"Yield": 39.5,
"%MST": 10.7,
"Test Weight": 57.2,
"Gross Revenue": 414.75
},
"entry_num": 2
},
{
"rank": 10,
"brand": "Asgrow",
"product": "AG04XF4",
"traits": "",
"metrics": {
"Yield": 39.3,
"%MST": 10.4,
"Test Weight": 57.4,
"Gross Revenue": 412.65
},
"entry_num": 4
},
{
"rank": 11,
"brand": "Attain",
"product": "Attain",
"traits": "06A5N",
"metrics": {
"Yield": 39.1,
"%MST": 10.5,
"Test Weight": 58.1,
"Gross Revenue": 410.55
},
"entry_num": 8
},
{
"rank": 12,
"brand": "Allegiant",
"product": "Allegiant",
"traits": "07F36N XF",
"metrics": {
"Yield": 38.9,
"%MST": 10.3,
"Test Weight": 56.8,
"Gross Revenue": 408.45
},
"entry_num": 12
},
{
"rank": 13,
"brand": "NK",
"product": "NK08-R3XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 37.7,
"%MST": 10.6,
"Test Weight": 58.7,
"Gross Revenue": 395.85
},
"entry_num": 17
},
{
"rank": 14,
"brand": "NK",
"product": "NK11-A4E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 36.6,
"%MST": 11.2,
"Test Weight": 58.4,
"Gross Revenue": 384.3
},
"entry_num": 25
},
{
"rank": 15,
"brand": "Allegiant",
"product": "Allegiant",
"traits": "05F54N XF",
"metrics": {
"Yield": 36.3,
"%MST": 10.9,
"Test Weight": 57.6,
"Gross Revenue": 381.15
},
"entry_num": 5
},
{
"rank": 16,
"brand": "Attain",
"product": "Attain",
"traits": "08A6N",
"metrics": {
"Yield": 36.2,
"%MST": 10.4,
"Test Weight": 58.8,
"Gross Revenue": 380.1
},
"entry_num": 16
},
{
"rank": 17,
"brand": "Asgrow",
"product": "AG07XF4",
"traits": "",
"metrics": {
"Yield": 35.9,
"%MST": 10.1,
"Test Weight": 58.1,
"Gross Revenue": 376.95
},
"entry_num": 13
},
{
"rank": 18,
"brand": "NK",
"product": "NK09-V2E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 35.7,
"%MST": 10.4,
"Test Weight": 57.4,
"Gross Revenue": 374.85
},
"entry_num": 20
},
{
"rank": 19,
"brand": "Brevant",
"product": "B095EE",
"traits": "",
"metrics": {
"Yield": 35.1,
"%MST": 10.2,
"Test Weight": 58.4,
"Gross Revenue": 368.55
},
"entry_num": 21
},
{
"rank": 20,
"brand": "Allegiant",
"product": "Allegiant",
"traits": "02F96N XF",
"metrics": {
"Yield": 35.0,
"%MST": 10.4,
"Test Weight": 57.9,
"Gross Revenue": 367.5
},
"entry_num": 1
},
{
"rank": 20,
"brand": "Allegiant",
"product": "Allegiant",
"traits": "09F16N XF",
"metrics": {
"Yield": 35.0,
"%MST": 10.4,
"Test Weight": 59.2,
"Gross Revenue": 367.5
},
"entry_num": 22
},
{
"rank": 22,
"brand": "Attain",
"product": "Attain",
"traits": "09A5N",
"metrics": {
"Yield": 34.1,
"%MST": 10.6,
"Test Weight": 58.8,
"Gross Revenue": 358.05
},
"entry_num": 18
},
{
"rank": 23,
"brand": "NK",
"product": "NK07-G5E3",
"traits": "Enlist E3 ®",
"metrics": {
"Yield": 33.9,
"%MST": 10.1,
"Test Weight": 58.3,
"Gross Revenue": 355.95
},
"entry_num": 14
},
{
"rank": 24,
"brand": "Asgrow",
"product": "AG10XF4",
"traits": "",
"metrics": {
"Yield": 33.8,
"%MST": 10.5,
"Test Weight": 58.3,
"Gross Revenue": 354.9
},
"entry_num": 23
},
{
"rank": 25,
"brand": "Asgrow",
"product": "AG09XF3",
"traits": "",
"metrics": {
"Yield": 33.3,
"%MST": 10.4,
"Test Weight": 59.6,
"Gross Revenue": 349.65
},
"entry_num": 19
},
{
"rank": 26,
"brand": "NK",
"product": "NK10-P7XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 32.4,
"%MST": 10.7,
"Test Weight": 58.8,
"Gross Revenue": 340.2
},
"entry_num": 24
}
],
"n_results": 26,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/nd/2025/2466623"
],
"fetched_at": "2026-05-25T19:46:20.567811+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink