justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
cd4a0f3148156d2d08bd47a8b1b3e6a20b8d3fbb
seed-mcp/corpus/gh_plot_reports/ghpr-soybeans-ar-2025-2466505.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

234 lines
4.8 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-ar-2025-2466505",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Arkansas",
"state_abbrev": "ar",
"year": 2025,
"plot_id": "2466505",
"cooperator": "Carnathan Family Farms",
"planted_date": "2025-04-16",
"harvested_date": "2025-10-13",
"population_seeds_per_acre": 135000,
"row_width_in": 30,
"results": [
{
"rank": 1,
"brand": "Asgrow",
"product": "AG47XF6",
"traits": "",
"metrics": {
"Yield": 72.3,
"%MST": 14.1,
"Test Weight": 53.7,
"Gross Revenue": 758.72
},
"entry_num": 4
},
{
"rank": 2,
"brand": "Asgrow",
"product": "AG49XF6",
"traits": "",
"metrics": {
"Yield": 67.4,
"%MST": 14.0,
"Test Weight": 55.4,
"Gross Revenue": 707.7
},
"entry_num": 10
},
{
"rank": 3,
"brand": "Asgrow",
"product": "AG43XF5",
"traits": "",
"metrics": {
"Yield": 66.8,
"%MST": 14.0,
"Test Weight": 51.8,
"Gross Revenue": 698.46
},
"entry_num": 2
},
{
"rank": 4,
"brand": "NK",
"product": "NK49-N7XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 65.9,
"%MST": 14.2,
"Test Weight": 49.9,
"Gross Revenue": 686.55
},
"entry_num": 16
},
{
"rank": 5,
"brand": "Asgrow",
"product": "AG48XF5",
"traits": "",
"metrics": {
"Yield": 65.8,
"%MST": 14.5,
"Test Weight": 53.5,
"Gross Revenue": 690.24
},
"entry_num": 7
},
{
"rank": 6,
"brand": "Asgrow",
"product": "AG48XF2",
"traits": "",
"metrics": {
"Yield": 65.7,
"%MST": 14.2,
"Test Weight": 53.0,
"Gross Revenue": 688.54
},
"entry_num": 5
},
{
"rank": 7,
"brand": "Asgrow",
"product": "AG48XF3",
"traits": "",
"metrics": {
"Yield": 65.0,
"%MST": 14.1,
"Test Weight": 54.6,
"Gross Revenue": 682.5
},
"entry_num": 6
},
{
"rank": 8,
"brand": "Asgrow",
"product": "AG49XF4",
"traits": "",
"metrics": {
"Yield": 64.8,
"%MST": 14.1,
"Test Weight": 53.2,
"Gross Revenue": 679.36
},
"entry_num": 9
},
{
"rank": 9,
"brand": "NK",
"product": "NK47-U1XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 64.2,
"%MST": 14.3,
"Test Weight": 52.6,
"Gross Revenue": 672.3
},
"entry_num": 14
},
{
"rank": 10,
"brand": "Asgrow",
"product": "AG48XF6",
"traits": "",
"metrics": {
"Yield": 63.7,
"%MST": 14.6,
"Test Weight": 53.0,
"Gross Revenue": 667.58
},
"entry_num": 8
},
{
"rank": 11,
"brand": "NK",
"product": "NK42-T5XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 61.7,
"%MST": 13.9,
"Test Weight": 52.6,
"Gross Revenue": 646.12
},
"entry_num": 11
},
{
"rank": 12,
"brand": "NK",
"product": "NK43-W1XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 61.1,
"%MST": 13.9,
"Test Weight": 49.7,
"Gross Revenue": 636.3
},
"entry_num": 12
},
{
"rank": 13,
"brand": "NK",
"product": "NK49-C2XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 60.8,
"%MST": 14.4,
"Test Weight": 53.1,
"Gross Revenue": 637.31
},
"entry_num": 15
},
{
"rank": 14,
"brand": "Asgrow",
"product": "AG44XF4",
"traits": "",
"metrics": {
"Yield": 59.2,
"%MST": 15.0,
"Test Weight": 47.2,
"Gross Revenue": 613.55
},
"entry_num": 3
},
{
"rank": 15,
"brand": "Asgrow",
"product": "AG42XF6",
"traits": "",
"metrics": {
"Yield": 58.3,
"%MST": 13.7,
"Test Weight": 50.4,
"Gross Revenue": 607.95
},
"entry_num": 1
},
{
"rank": 16,
"brand": "NK",
"product": "NK45-M6XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 57.3,
"%MST": 14.6,
"Test Weight": 49.4,
"Gross Revenue": 596.38
},
"entry_num": 13
}
],
"n_results": 16,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/ar/2025/2466505"
],
"fetched_at": "2026-05-25T19:45:41.141738+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink