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-md-2024-2426824.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

286 lines
6.0 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-md-2024-2426824",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Maryland",
"state_abbrev": "md",
"year": 2024,
"plot_id": "2426824",
"cooperator": "University of Maryland - Western Maryland Research & Education Center MG 4 (Early)",
"planted_date": "2024-05-17",
"harvested_date": "2024-11-07",
"population_seeds_per_acre": null,
"row_width_in": null,
"results": [
{
"rank": 1,
"brand": "Catalyst",
"product": "CT4413E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 88.9,
"%MST": null,
"Test Weight": 50.3,
"Gross Revenue": 926.87
},
"entry_num": 2
},
{
"rank": 2,
"brand": "APEX",
"product": "AE4341S",
"traits": "",
"metrics": {
"Yield": 87.4,
"%MST": null,
"Test Weight": 54.7,
"Gross Revenue": 917.7
},
"entry_num": 1
},
{
"rank": 2,
"brand": "Xitavo",
"product": "XO",
"traits": "4255E",
"metrics": {
"Yield": 87.4,
"%MST": null,
"Test Weight": 50.2,
"Gross Revenue": 911.06
},
"entry_num": 22
},
{
"rank": 4,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7415ET",
"metrics": {
"Yield": 87.1,
"%MST": null,
"Test Weight": 53.1,
"Gross Revenue": 912.98
},
"entry_num": 17
},
{
"rank": 5,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4045E3",
"metrics": {
"Yield": 86.6,
"%MST": null,
"Test Weight": 48.9,
"Gross Revenue": 900.47
},
"entry_num": 7
},
{
"rank": 5,
"brand": "Xitavo",
"product": "XO",
"traits": "4132E",
"metrics": {
"Yield": 86.6,
"%MST": null,
"Test Weight": 49.6,
"Gross Revenue": 901.68
},
"entry_num": 21
},
{
"rank": 7,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4423E3",
"metrics": {
"Yield": 86.0,
"%MST": null,
"Test Weight": 53.5,
"Gross Revenue": 902.14
},
"entry_num": 10
},
{
"rank": 8,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4320E3/STS",
"metrics": {
"Yield": 82.4,
"%MST": null,
"Test Weight": 52.3,
"Gross Revenue": 862.4
},
"entry_num": 9
},
{
"rank": 9,
"brand": "NK",
"product": "NK42-A6E3S",
"traits": "Enlist E3 ® STS ®",
"metrics": {
"Yield": 82.3,
"%MST": null,
"Test Weight": 50.6,
"Gross Revenue": 858.55
},
"entry_num": 15
},
{
"rank": 10,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7434XF",
"metrics": {
"Yield": 80.7,
"%MST": null,
"Test Weight": 53.9,
"Gross Revenue": 847.19
},
"entry_num": 18
},
{
"rank": 11,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4021E3",
"metrics": {
"Yield": 79.5,
"%MST": null,
"Test Weight": 49.6,
"Gross Revenue": 827.75
},
"entry_num": 6
},
{
"rank": 12,
"brand": "Pioneer",
"product": "P42A84E",
"traits": "",
"metrics": {
"Yield": 78.8,
"%MST": null,
"Test Weight": 52.6,
"Gross Revenue": 825.19
},
"entry_num": 11
},
{
"rank": 13,
"brand": "Mid-Atlantic",
"product": "Seeds",
"traits": "MAS4215E3",
"metrics": {
"Yield": 77.7,
"%MST": null,
"Test Weight": 53.0,
"Gross Revenue": 814.3
},
"entry_num": 8
},
{
"rank": 14,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7435ET",
"metrics": {
"Yield": 77.2,
"%MST": null,
"Test Weight": 54.6,
"Gross Revenue": 810.6
},
"entry_num": 19
},
{
"rank": 15,
"brand": "UniSouth",
"product": "Genetics",
"traits": "USG 7435XFS",
"metrics": {
"Yield": 76.1,
"%MST": null,
"Test Weight": 52.2,
"Gross Revenue": 796.31
},
"entry_num": 20
},
{
"rank": 16,
"brand": "Xitavo",
"product": "XO",
"traits": "4364E",
"metrics": {
"Yield": 75.8,
"%MST": null,
"Test Weight": 50.0,
"Gross Revenue": 789.84
},
"entry_num": 23
},
{
"rank": 17,
"brand": "NK",
"product": "NK43-W1XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 75.6,
"%MST": null,
"Test Weight": 48.5,
"Gross Revenue": 785.48
},
"entry_num": 16
},
{
"rank": 18,
"brand": "Southern",
"product": "Harvest",
"traits": "SH4024 E3",
"metrics": {
"Yield": 75.4,
"%MST": null,
"Test Weight": 49.5,
"Gross Revenue": 784.91
},
"entry_num": 14
},
{
"rank": 19,
"brand": "Xitavo",
"product": "XO",
"traits": "4405E",
"metrics": {
"Yield": 73.5,
"%MST": null,
"Test Weight": 47.4,
"Gross Revenue": 762.05
},
"entry_num": 24
},
{
"rank": 20,
"brand": "Revere",
"product": "Seed",
"traits": "Revere 44-F44 XFS",
"metrics": {
"Yield": 72.0,
"%MST": null,
"Test Weight": 49.1,
"Gross Revenue": 748.94
},
"entry_num": 12
}
],
"n_results": 20,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/md/2024/2426824"
],
"fetched_at": "2026-05-25T19:39:16.215922+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink