justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
06461ade1d07d3e7ced12c26cd3a8b5f8fda9572
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-oh-2024-2420171.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-oh-2024-2420171",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Ohio",
"state_abbrev": "oh",
"year": 2024,
"plot_id": "2420171",
"cooperator": "Ohio State University - Preble County (Early)",
"planted_date": "2024-05-16",
"harvested_date": "2024-10-07",
"population_seeds_per_acre": null,
"row_width_in": null,
"results": [
{
"rank": 1,
"brand": "Axis",
"product": "Seed",
"traits": "3605XF",
"metrics": {
"Yield": 81.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 852.6
},
"entry_num": 1
},
{
"rank": 2,
"brand": "Xitavo",
"product": "XO",
"traits": "3555E",
"metrics": {
"Yield": 80.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 843.15
},
"entry_num": 2
},
{
"rank": 3,
"brand": "Asgrow",
"product": "AG33XF3",
"traits": "",
"metrics": {
"Yield": 80.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 841.05
},
"entry_num": 3
},
{
"rank": 4,
"brand": "Xitavo",
"product": "XO",
"traits": "3014E",
"metrics": {
"Yield": 79.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 834.75
},
"entry_num": 4
},
{
"rank": 5,
"brand": "Seed",
"product": "Consultants",
"traits": "SC7355E",
"metrics": {
"Yield": 78.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 827.4
},
"entry_num": 6
},
{
"rank": 6,
"brand": "Asgrow",
"product": "AG36XF4",
"traits": "",
"metrics": {
"Yield": 78.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 822.15
},
"entry_num": 7
},
{
"rank": 7,
"brand": "Seed",
"product": "Genetics",
"traits": "Direct ET-4736E3 Enlist E3 ®",
"metrics": {
"Yield": 78.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 821.1
},
"entry_num": 8
},
{
"rank": 8,
"brand": "Ebberts",
"product": "G3580ES",
"traits": "",
"metrics": {
"Yield": 77.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 813.75
},
"entry_num": 10
},
{
"rank": 9,
"brand": "Seed",
"product": "Consultants",
"traits": "SC7364E",
"metrics": {
"Yield": 77.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 810.6
},
"entry_num": 11
},
{
"rank": 10,
"brand": "Ebberts",
"product": "G3171ES",
"traits": "",
"metrics": {
"Yield": 77.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 809.55
},
"entry_num": 12
},
{
"rank": 10,
"brand": "Ebberts",
"product": "G3690E",
"traits": "",
"metrics": {
"Yield": 77.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 809.55
},
"entry_num": 13
},
{
"rank": 12,
"brand": "Asgrow",
"product": "AG30XF4",
"traits": "",
"metrics": {
"Yield": 76.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 804.3
},
"entry_num": 14
},
{
"rank": 13,
"brand": "Xitavo",
"product": "XO",
"traits": "3224E",
"metrics": {
"Yield": 76.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 800.1
},
"entry_num": 16
},
{
"rank": 14,
"brand": "Seed",
"product": "Genetics",
"traits": "Direct ET-3733E3S",
"metrics": {
"Yield": 76.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 799.05
},
"entry_num": 17
},
{
"rank": 15,
"brand": "Asgrow",
"product": "AG27XF3",
"traits": "",
"metrics": {
"Yield": 76.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 798.0
},
"entry_num": 18
},
{
"rank": 16,
"brand": "Axis",
"product": "Seed",
"traits": "3314E",
"metrics": {
"Yield": 75.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 796.95
},
"entry_num": 19
},
{
"rank": 17,
"brand": "Xitavo",
"product": "XO",
"traits": "3105E",
"metrics": {
"Yield": 75.2,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 789.6
},
"entry_num": 22
},
{
"rank": 18,
"brand": "Xitavo",
"product": "XO",
"traits": "3375E",
"metrics": {
"Yield": 74.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 782.25
},
"entry_num": 23
},
{
"rank": 19,
"brand": "Seed",
"product": "Genetics",
"traits": "Direct ET-4732E3 Enlist E3 ®",
"metrics": {
"Yield": 73.8,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 774.9
},
"entry_num": 25
},
{
"rank": 20,
"brand": "DonMario",
"product": "Seeds",
"traits": "DM36E94",
"metrics": {
"Yield": 72.9,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 765.45
},
"entry_num": 27
},
{
"rank": 21,
"brand": "Axis",
"product": "Seed",
"traits": "3514ES",
"metrics": {
"Yield": 72.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 760.2
},
"entry_num": 28
},
{
"rank": 22,
"brand": "Ebberts",
"product": "G3380E",
"traits": "",
"metrics": {
"Yield": 72.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 759.15
},
"entry_num": 29
},
{
"rank": 23,
"brand": "Benson",
"product": "Hill",
"traits": "BH35A233",
"metrics": {
"Yield": 72.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 757.05
},
"entry_num": 31
},
{
"rank": 24,
"brand": "Seed",
"product": "Genetics",
"traits": "Direct ET-4734E3S",
"metrics": {
"Yield": 72.0,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 756.0
},
"entry_num": 32
},
{
"rank": 25,
"brand": "Seed",
"product": "Consultants",
"traits": "SC7332E",
"metrics": {
"Yield": 71.6,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 751.8
},
"entry_num": 33
},
{
"rank": 26,
"brand": "Xitavo",
"product": "XO",
"traits": "3655E",
"metrics": {
"Yield": 71.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 749.7
},
"entry_num": 34
},
{
"rank": 27,
"brand": "Seed",
"product": "Genetics",
"traits": "Direct ET-0733E3",
"metrics": {
"Yield": 71.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 748.65
},
"entry_num": 35
},
{
"rank": 28,
"brand": "Benson",
"product": "Hill",
"traits": "BH35A231",
"metrics": {
"Yield": 71.1,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 746.55
},
"entry_num": 36
},
{
"rank": 29,
"brand": "Seed",
"product": "Genetics",
"traits": "Direct ET-3735E3",
"metrics": {
"Yield": 70.5,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 740.25
},
"entry_num": 38
},
{
"rank": 30,
"brand": "Benson",
"product": "Hill",
"traits": "N35D950S",
"metrics": {
"Yield": 69.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 728.7
},
"entry_num": 39
},
{
"rank": 31,
"brand": "NK",
"product": "NK36-Q6E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 65.4,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 686.7
},
"entry_num": 40
},
{
"rank": 32,
"brand": "Benson",
"product": "Hill",
"traits": "BX36Q861",
"metrics": {
"Yield": 62.3,
"%MST": null,
"Test Weight": null,
"Gross Revenue": 654.15
},
"entry_num": 42
}
],
"n_results": 32,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/oh/2024/2420171"
],
"fetched_at": "2026-05-25T19:35:08.827441+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink