justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
d60d747858ddaf4ff7835ade281150d0d5424bf3
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-ms-2024-2419597.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-ms-2024-2419597",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Mississippi",
"state_abbrev": "ms",
"year": 2024,
"plot_id": "2419597",
"cooperator": "Dean Partnership",
"planted_date": "2024-05-08",
"harvested_date": "2024-10-04",
"population_seeds_per_acre": 125000,
"row_width_in": 38,
"results": [
{
"rank": 1,
"brand": "Armor",
"product": "Seed",
"traits": "Armor 46-F96",
"metrics": {
"Yield": 96.9,
"%MST": 11.4,
"Test Weight": 61.0,
"Gross Revenue": 1017.45
},
"entry_num": 12
},
{
"rank": 2,
"brand": "Armor",
"product": "Seed",
"traits": "Armor 45-F65",
"metrics": {
"Yield": 93.7,
"%MST": 12.0,
"Test Weight": 51.0,
"Gross Revenue": 978.23
},
"entry_num": 15
},
{
"rank": 3,
"brand": "NK",
"product": "NK44-J4XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 92.0,
"%MST": 10.4,
"Test Weight": 59.9,
"Gross Revenue": 966.0
},
"entry_num": 3
},
{
"rank": 4,
"brand": "Armor",
"product": "Seed",
"traits": "Armor 45-F02",
"metrics": {
"Yield": 91.3,
"%MST": 11.5,
"Test Weight": 59.3,
"Gross Revenue": 958.65
},
"entry_num": 16
},
{
"rank": 5,
"brand": "Asgrow",
"product": "AG44XF4",
"traits": "",
"metrics": {
"Yield": 90.6,
"%MST": 11.1,
"Test Weight": 57.6,
"Gross Revenue": 951.3
},
"entry_num": 31
},
{
"rank": 5,
"brand": "Beck's",
"product": "4337XF",
"traits": "",
"metrics": {
"Yield": 90.6,
"%MST": 10.5,
"Test Weight": 54.3,
"Gross Revenue": 951.3
},
"entry_num": 38
},
{
"rank": 7,
"brand": "Armor",
"product": "Seed",
"traits": "Armor 48-F55S",
"metrics": {
"Yield": 90.0,
"%MST": 12.2,
"Test Weight": 58.7,
"Gross Revenue": 945.0
},
"entry_num": 11
},
{
"rank": 8,
"brand": "NK",
"product": "NK42-T5XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 89.9,
"%MST": 9.7,
"Test Weight": 57.0,
"Gross Revenue": 943.95
},
"entry_num": 1
},
{
"rank": 9,
"brand": "Pioneer",
"product": "P45A70LX",
"traits": "",
"metrics": {
"Yield": 89.6,
"%MST": 10.9,
"Test Weight": 60.4,
"Gross Revenue": 940.8
},
"entry_num": 28
},
{
"rank": 10,
"brand": "Pioneer",
"product": "P41Z80BLX",
"traits": "",
"metrics": {
"Yield": 89.0,
"%MST": 10.8,
"Test Weight": 59.8,
"Gross Revenue": 934.5
},
"entry_num": 30
},
{
"rank": 10,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions A4924XF",
"metrics": {
"Yield": 89.0,
"%MST": 10.0,
"Test Weight": 60.9,
"Gross Revenue": 934.5
},
"entry_num": 37
},
{
"rank": 12,
"brand": "Pioneer",
"product": "P48Z70BLX",
"traits": "",
"metrics": {
"Yield": 88.5,
"%MST": 11.6,
"Test Weight": 56.7,
"Gross Revenue": 929.25
},
"entry_num": 25
},
{
"rank": 13,
"brand": "Asgrow",
"product": "AG45XF3",
"traits": "",
"metrics": {
"Yield": 88.4,
"%MST": 10.9,
"Test Weight": 58.7,
"Gross Revenue": 928.2
},
"entry_num": 32
},
{
"rank": 14,
"brand": "Armor",
"product": "Seed",
"traits": "Armor 46-F15S",
"metrics": {
"Yield": 87.8,
"%MST": 11.3,
"Test Weight": 57.1,
"Gross Revenue": 921.9
},
"entry_num": 14
},
{
"rank": 15,
"brand": "Pioneer",
"product": "P48A04LX",
"traits": "",
"metrics": {
"Yield": 87.0,
"%MST": 11.4,
"Test Weight": 59.3,
"Gross Revenue": 913.5
},
"entry_num": 26
},
{
"rank": 16,
"brand": "Pioneer",
"product": "P44A60LX",
"traits": "",
"metrics": {
"Yield": 85.7,
"%MST": 11.8,
"Test Weight": 51.7,
"Gross Revenue": 895.91
},
"entry_num": 29
},
{
"rank": 17,
"brand": "Pioneer",
"product": "P46A90LX",
"traits": "",
"metrics": {
"Yield": 85.5,
"%MST": 12.1,
"Test Weight": 56.4,
"Gross Revenue": 897.75
},
"entry_num": 27
},
{
"rank": 18,
"brand": "NK",
"product": "NK49-N7XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 84.3,
"%MST": 10.2,
"Test Weight": 58.5,
"Gross Revenue": 885.15
},
"entry_num": 7
},
{
"rank": 19,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions A4862XF",
"metrics": {
"Yield": 84.1,
"%MST": 11.4,
"Test Weight": 55.0,
"Gross Revenue": 883.05
},
"entry_num": 36
},
{
"rank": 20,
"brand": "NK",
"product": "NK48-A8XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 83.9,
"%MST": 10.0,
"Test Weight": 59.6,
"Gross Revenue": 880.95
},
"entry_num": 5
},
{
"rank": 21,
"brand": "Armor",
"product": "Seed",
"traits": "Armor 50-F96",
"metrics": {
"Yield": 83.8,
"%MST": 12.2,
"Test Weight": 58.7,
"Gross Revenue": 879.9
},
"entry_num": 10
},
{
"rank": 21,
"brand": "Asgrow",
"product": "AG46XF3",
"traits": "",
"metrics": {
"Yield": 83.8,
"%MST": 11.1,
"Test Weight": 57.8,
"Gross Revenue": 879.9
},
"entry_num": 33
},
{
"rank": 23,
"brand": "NK",
"product": "NK43-W1XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 83.2,
"%MST": 10.9,
"Test Weight": 55.2,
"Gross Revenue": 873.6
},
"entry_num": 2
},
{
"rank": 24,
"brand": "NK",
"product": "NK49-C2XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 81.4,
"%MST": 11.2,
"Test Weight": 54.3,
"Gross Revenue": 854.7
},
"entry_num": 8
},
{
"rank": 24,
"brand": "Beck's",
"product": "4999XF",
"traits": "",
"metrics": {
"Yield": 81.4,
"%MST": 10.8,
"Test Weight": 56.1,
"Gross Revenue": 854.7
},
"entry_num": 42
},
{
"rank": 26,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions A4814XF",
"metrics": {
"Yield": 80.8,
"%MST": 11.1,
"Test Weight": 60.0,
"Gross Revenue": 848.4
},
"entry_num": 35
},
{
"rank": 27,
"brand": "Beck's",
"product": "4777XF",
"traits": "",
"metrics": {
"Yield": 79.5,
"%MST": 10.5,
"Test Weight": 55.2,
"Gross Revenue": 834.75
},
"entry_num": 39
},
{
"rank": 28,
"brand": "Innvictis",
"product": "Seed",
"traits": "Solutions A4503XF",
"metrics": {
"Yield": 79.3,
"%MST": 11.1,
"Test Weight": 56.1,
"Gross Revenue": 832.65
},
"entry_num": 34
},
{
"rank": 29,
"brand": "Beck's",
"product": "4991X2",
"traits": "",
"metrics": {
"Yield": 79.1,
"%MST": 9.8,
"Test Weight": 59.4,
"Gross Revenue": 830.55
},
"entry_num": 43
},
{
"rank": 30,
"brand": "Asgrow",
"product": "AG49XF4",
"traits": "",
"metrics": {
"Yield": 77.8,
"%MST": 10.7,
"Test Weight": 59.0,
"Gross Revenue": 816.9
},
"entry_num": 9
},
{
"rank": 31,
"brand": "NK",
"product": "S49-F5X",
"traits": "Roundup Ready 2 Xtend ®",
"metrics": {
"Yield": 77.5,
"%MST": 10.9,
"Test Weight": 55.0,
"Gross Revenue": 813.75
},
"entry_num": 6
},
{
"rank": 32,
"brand": "Beck's",
"product": "4661XF",
"traits": "",
"metrics": {
"Yield": 76.9,
"%MST": 9.6,
"Test Weight": 59.3,
"Gross Revenue": 807.45
},
"entry_num": 40
},
{
"rank": 33,
"brand": "Beck's",
"product": "4887XF",
"traits": "",
"metrics": {
"Yield": 76.8,
"%MST": 9.7,
"Test Weight": 58.3,
"Gross Revenue": 806.4
},
"entry_num": 41
},
{
"rank": 34,
"brand": "Armor",
"product": "Seed",
"traits": "Armor 46-F35S",
"metrics": {
"Yield": 74.6,
"%MST": 12.5,
"Test Weight": 56.3,
"Gross Revenue": 783.3
},
"entry_num": 13
},
{
"rank": 35,
"brand": "NK",
"product": "NK46-B4XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 68.1,
"%MST": 10.9,
"Test Weight": 57.6,
"Gross Revenue": 715.05
},
"entry_num": 4
}
],
"n_results": 35,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/ms/2024/2419597"
],
"fetched_at": "2026-05-25T19:32:57.532439+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink