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-ar-2024-2414624.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

325 lines
6.6 KiB
JSON
Raw Blame History

{
"source": "gh_plot_reports",
"source_key": "ghpr-soybeans-ar-2024-2414624",
"data_type": "trial",
"vendor": "Syngenta",
"brand": "Golden Harvest",
"crop": "soybeans",
"state": "Arkansas",
"state_abbrev": "ar",
"year": 2024,
"plot_id": "2414624",
"cooperator": "Long Lake Plantation",
"planted_date": "2024-04-05",
"harvested_date": "2024-08-28",
"population_seeds_per_acre": 120000,
"row_width_in": 30,
"results": [
{
"rank": 1,
"brand": "NK",
"product": "NK49-C2XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 101.1,
"%MST": 12.6,
"Test Weight": 55.5,
"Gross Revenue": 1061.55
},
"entry_num": 11
},
{
"rank": 2,
"brand": "Asgrow",
"product": "AG43XF5",
"traits": "",
"metrics": {
"Yield": 99.6,
"%MST": 10.4,
"Test Weight": 57.3,
"Gross Revenue": 1045.8
},
"entry_num": 14
},
{
"rank": 3,
"brand": "NK",
"product": "NK49-N7XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 97.9,
"%MST": 9.4,
"Test Weight": 58.3,
"Gross Revenue": 1027.95
},
"entry_num": 12
},
{
"rank": 4,
"brand": "NK",
"product": "NK42-T5XF",
"traits": "XtendFlex ®",
"metrics": {
"Yield": 96.5,
"%MST": 9.6,
"Test Weight": 59.4,
"Gross Revenue": 1013.25
},
"entry_num": 6
},
{
"rank": 5,
"brand": "Asgrow",
"product": "AG49XF4",
"traits": "",
"metrics": {
"Yield": 96.0,
"%MST": 9.1,
"Test Weight": 57.4,
"Gross Revenue": 1008.0
},
"entry_num": 23
},
{
"rank": 6,
"brand": "Pioneer",
"product": "P48A04LX",
"traits": "",
"metrics": {
"Yield": 95.6,
"%MST": 11.1,
"Test Weight": 58.6,
"Gross Revenue": 1003.8
},
"entry_num": 4
},
{
"rank": 7,
"brand": "NK",
"product": "NK43-W1XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 95.5,
"%MST": 9.0,
"Test Weight": 57.8,
"Gross Revenue": 1002.75
},
"entry_num": 7
},
{
"rank": 7,
"brand": "NK",
"product": "NK48-H3XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 95.5,
"%MST": 10.6,
"Test Weight": 58.6,
"Gross Revenue": 1002.75
},
"entry_num": 10
},
{
"rank": 9,
"brand": "Pioneer",
"product": "P46A90LX",
"traits": "",
"metrics": {
"Yield": 94.7,
"%MST": 9.3,
"Test Weight": 59.1,
"Gross Revenue": 994.35
},
"entry_num": 3
},
{
"rank": 10,
"brand": "Pioneer",
"product": "P48Z70BLX",
"traits": "",
"metrics": {
"Yield": 93.3,
"%MST": 8.7,
"Test Weight": 58.5,
"Gross Revenue": 979.65
},
"entry_num": 5
},
{
"rank": 10,
"brand": "NK",
"product": "NK48-A8XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 93.3,
"%MST": 10.6,
"Test Weight": 59.4,
"Gross Revenue": 979.65
},
"entry_num": 9
},
{
"rank": 10,
"brand": "Asgrow",
"product": "AG44XF4",
"traits": "",
"metrics": {
"Yield": 93.3,
"%MST": 8.8,
"Test Weight": 58.1,
"Gross Revenue": 979.65
},
"entry_num": 15
},
{
"rank": 13,
"brand": "NK",
"product": "NK44-J4XFS",
"traits": "XtendFlex ® STS ®",
"metrics": {
"Yield": 92.6,
"%MST": 9.5,
"Test Weight": 58.7,
"Gross Revenue": 972.3
},
"entry_num": 8
},
{
"rank": 14,
"brand": "Pioneer",
"product": "P45A70LX",
"traits": "",
"metrics": {
"Yield": 92.0,
"%MST": 9.4,
"Test Weight": 58.8,
"Gross Revenue": 966.0
},
"entry_num": 2
},
{
"rank": 15,
"brand": "Asgrow",
"product": "AG48XF5",
"traits": "",
"metrics": {
"Yield": 91.9,
"%MST": 10.1,
"Test Weight": 58.0,
"Gross Revenue": 964.95
},
"entry_num": 22
},
{
"rank": 16,
"brand": "Asgrow",
"product": "AG46XF3",
"traits": "",
"metrics": {
"Yield": 91.4,
"%MST": 9.1,
"Test Weight": 57.4,
"Gross Revenue": 959.7
},
"entry_num": 17
},
{
"rank": 17,
"brand": "Asgrow",
"product": "AG48XF3",
"traits": "",
"metrics": {
"Yield": 91.2,
"%MST": 9.7,
"Test Weight": 58.8,
"Gross Revenue": 957.6
},
"entry_num": 21
},
{
"rank": 18,
"brand": "Asgrow",
"product": "AG45XF3",
"traits": "",
"metrics": {
"Yield": 90.6,
"%MST": 9.2,
"Test Weight": 58.9,
"Gross Revenue": 951.3
},
"entry_num": 16
},
{
"rank": 19,
"brand": "Pioneer",
"product": "P44A60LX",
"traits": "",
"metrics": {
"Yield": 90.0,
"%MST": 8.7,
"Test Weight": 58.6,
"Gross Revenue": 945.0
},
"entry_num": 1
},
{
"rank": 20,
"brand": "Asgrow",
"product": "AG47XF2",
"traits": "",
"metrics": {
"Yield": 89.8,
"%MST": 9.6,
"Test Weight": 58.6,
"Gross Revenue": 942.9
},
"entry_num": 18
},
{
"rank": 21,
"brand": "Asgrow",
"product": "AG48XF2",
"traits": "",
"metrics": {
"Yield": 89.5,
"%MST": 9.8,
"Test Weight": 58.4,
"Gross Revenue": 939.75
},
"entry_num": 20
},
{
"rank": 22,
"brand": "Asgrow",
"product": "AG47XF5",
"traits": "",
"metrics": {
"Yield": 89.3,
"%MST": 8.7,
"Test Weight": 58.7,
"Gross Revenue": 937.65
},
"entry_num": 19
},
{
"rank": 23,
"brand": "Asgrow",
"product": "AG42XF4",
"traits": "",
"metrics": {
"Yield": 87.1,
"%MST": 8.8,
"Test Weight": 56.4,
"Gross Revenue": 914.55
},
"entry_num": 13
}
],
"n_results": 23,
"source_urls": [
"https://www.goldenharvestseeds.com/soybean/plot-report/ar/2024/2414624"
],
"fetched_at": "2026-05-25T19:18:35.568682+00:00",
"scraper_version": "0.1.0"
}
Reference in New Issue View Git Blame Copy Permalink