justin
0e625553e5
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>
585 lines
12 KiB
JSON
585 lines
12 KiB
JSON
{
|
|
"source": "gh_plot_reports",
|
|
"source_key": "ghpr-soybeans-ga-2024-2465706",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "soybeans",
|
|
"state": "Georgia",
|
|
"state_abbrev": "ga",
|
|
"year": 2024,
|
|
"plot_id": "2465706",
|
|
"cooperator": "University of Georgia - Griffin (Ultra Late)",
|
|
"planted_date": "2024-07-18",
|
|
"harvested_date": "2024-12-02",
|
|
"population_seeds_per_acre": 250000,
|
|
"row_width_in": null,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "Innvictis",
|
|
"product": "Seed",
|
|
"traits": "Solutions A5994XF",
|
|
"metrics": {
|
|
"Yield": 49.8,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 522.9
|
|
},
|
|
"entry_num": 1
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "Progeny",
|
|
"product": "P",
|
|
"traits": "6685XFS",
|
|
"metrics": {
|
|
"Yield": 47.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 496.65
|
|
},
|
|
"entry_num": 2
|
|
},
|
|
{
|
|
"rank": 3,
|
|
"brand": "DonMario",
|
|
"product": "Seeds",
|
|
"traits": "DM69E83S",
|
|
"metrics": {
|
|
"Yield": 46.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 488.25
|
|
},
|
|
"entry_num": 3
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "Pioneer",
|
|
"product": "P68A41BE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 45.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 478.8
|
|
},
|
|
"entry_num": 4
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "UniSouth",
|
|
"product": "Genetics",
|
|
"traits": "USG 7633XF",
|
|
"metrics": {
|
|
"Yield": 45.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 475.65
|
|
},
|
|
"entry_num": 5
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed XF4875S",
|
|
"metrics": {
|
|
"Yield": 44.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 466.2
|
|
},
|
|
"entry_num": 6
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"brand": "DonMario",
|
|
"product": "Seeds",
|
|
"traits": "DM55F62S",
|
|
"metrics": {
|
|
"Yield": 43.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 457.8
|
|
},
|
|
"entry_num": 7
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "Georgia",
|
|
"product": "Seed",
|
|
"traits": "G21-230R2X",
|
|
"metrics": {
|
|
"Yield": 43.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 456.75
|
|
},
|
|
"entry_num": 8
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "Progeny",
|
|
"product": "P",
|
|
"traits": "4947XFS",
|
|
"metrics": {
|
|
"Yield": 43.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 456.75
|
|
},
|
|
"entry_num": 9
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Revere",
|
|
"product": "Seed",
|
|
"traits": "Revere 4826XFS",
|
|
"metrics": {
|
|
"Yield": 43.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 454.65
|
|
},
|
|
"entry_num": 10
|
|
},
|
|
{
|
|
"rank": 11,
|
|
"brand": "Innvictis",
|
|
"product": "Seed",
|
|
"traits": "Solutions A5813XF",
|
|
"metrics": {
|
|
"Yield": 42.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 450.45
|
|
},
|
|
"entry_num": 12
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"brand": "Armor",
|
|
"product": "Seed",
|
|
"traits": "Armor 71-F12",
|
|
"metrics": {
|
|
"Yield": 42.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 446.25
|
|
},
|
|
"entry_num": 14
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "Innvictis",
|
|
"product": "Seed",
|
|
"traits": "Solutions A4924XF",
|
|
"metrics": {
|
|
"Yield": 42.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 443.1
|
|
},
|
|
"entry_num": 15
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed XF4914S",
|
|
"metrics": {
|
|
"Yield": 42.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 443.1
|
|
},
|
|
"entry_num": 16
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"brand": "DonMario",
|
|
"product": "Seeds",
|
|
"traits": "DM59E01S",
|
|
"metrics": {
|
|
"Yield": 41.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 434.7
|
|
},
|
|
"entry_num": 17
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "UniSouth",
|
|
"product": "Genetics",
|
|
"traits": "USG 7495XFS",
|
|
"metrics": {
|
|
"Yield": 41.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 432.6
|
|
},
|
|
"entry_num": 18
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "Pioneer",
|
|
"product": "P56A71E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 41.2,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 432.6
|
|
},
|
|
"entry_num": 19
|
|
},
|
|
{
|
|
"rank": 18,
|
|
"brand": "Revere",
|
|
"product": "Seed",
|
|
"traits": "Revere 53-F84 XFS",
|
|
"metrics": {
|
|
"Yield": 40.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 427.35
|
|
},
|
|
"entry_num": 20
|
|
},
|
|
{
|
|
"rank": 19,
|
|
"brand": "Integra",
|
|
"product": "Fortified",
|
|
"traits": "Seed 6984XF",
|
|
"metrics": {
|
|
"Yield": 39.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 412.65
|
|
},
|
|
"entry_num": 21
|
|
},
|
|
{
|
|
"rank": 20,
|
|
"brand": "Armor",
|
|
"product": "Seed",
|
|
"traits": "Armor 49-F37",
|
|
"metrics": {
|
|
"Yield": 39.0,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 409.5
|
|
},
|
|
"entry_num": 22
|
|
},
|
|
{
|
|
"rank": 21,
|
|
"brand": "Revere",
|
|
"product": "Seed",
|
|
"traits": "Revere 49-F36 XF",
|
|
"metrics": {
|
|
"Yield": 38.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 408.45
|
|
},
|
|
"entry_num": 23
|
|
},
|
|
{
|
|
"rank": 22,
|
|
"brand": "Armor",
|
|
"product": "Seed",
|
|
"traits": "Armor 59-F21",
|
|
"metrics": {
|
|
"Yield": 38.8,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 407.4
|
|
},
|
|
"entry_num": 24
|
|
},
|
|
{
|
|
"rank": 23,
|
|
"brand": "Clemson",
|
|
"product": "U",
|
|
"traits": "SC17-5517",
|
|
"metrics": {
|
|
"Yield": 38.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 405.3
|
|
},
|
|
"entry_num": 25
|
|
},
|
|
{
|
|
"rank": 24,
|
|
"brand": "Asgrow",
|
|
"product": "AG69XF5",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 37.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 397.95
|
|
},
|
|
"entry_num": 26
|
|
},
|
|
{
|
|
"rank": 24,
|
|
"brand": "Georgia",
|
|
"product": "Seed",
|
|
"traits": "G21-245R2X",
|
|
"metrics": {
|
|
"Yield": 37.9,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 397.95
|
|
},
|
|
"entry_num": 27
|
|
},
|
|
{
|
|
"rank": 26,
|
|
"brand": "Revere",
|
|
"product": "Seed",
|
|
"traits": "Revere 6927XF",
|
|
"metrics": {
|
|
"Yield": 37.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 394.8
|
|
},
|
|
"entry_num": 28
|
|
},
|
|
{
|
|
"rank": 27,
|
|
"brand": "NK",
|
|
"product": "NK63-U7XF",
|
|
"traits": "XtendFlex ®",
|
|
"metrics": {
|
|
"Yield": 36.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 383.25
|
|
},
|
|
"entry_num": 29
|
|
},
|
|
{
|
|
"rank": 28,
|
|
"brand": "NK",
|
|
"product": "NK58-B8E3S",
|
|
"traits": "Enlist E3 ® STS ®",
|
|
"metrics": {
|
|
"Yield": 36.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 379.05
|
|
},
|
|
"entry_num": 30
|
|
},
|
|
{
|
|
"rank": 29,
|
|
"brand": "Armor",
|
|
"product": "Seed",
|
|
"traits": "Armor 68-F35",
|
|
"metrics": {
|
|
"Yield": 35.8,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 375.9
|
|
},
|
|
"entry_num": 31
|
|
},
|
|
{
|
|
"rank": 30,
|
|
"brand": "Innvictis",
|
|
"product": "Seed",
|
|
"traits": "Solutions A5284XF",
|
|
"metrics": {
|
|
"Yield": 35.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 374.85
|
|
},
|
|
"entry_num": 32
|
|
},
|
|
{
|
|
"rank": 31,
|
|
"brand": "Revere",
|
|
"product": "Seed",
|
|
"traits": "Revere 62-F24 XF",
|
|
"metrics": {
|
|
"Yield": 35.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 368.55
|
|
},
|
|
"entry_num": 33
|
|
},
|
|
{
|
|
"rank": 32,
|
|
"brand": "DonMario",
|
|
"product": "Seeds",
|
|
"traits": "DM48E54",
|
|
"metrics": {
|
|
"Yield": 34.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 361.2
|
|
},
|
|
"entry_num": 34
|
|
},
|
|
{
|
|
"rank": 33,
|
|
"brand": "Asgrow",
|
|
"product": "AG54XF5",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 33.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 349.65
|
|
},
|
|
"entry_num": 35
|
|
},
|
|
{
|
|
"rank": 34,
|
|
"brand": "Asgrow",
|
|
"product": "AG48XF5",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 32.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 341.25
|
|
},
|
|
"entry_num": 36
|
|
},
|
|
{
|
|
"rank": 35,
|
|
"brand": "Progeny",
|
|
"product": "P",
|
|
"traits": "5056XFS",
|
|
"metrics": {
|
|
"Yield": 32.4,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 340.2
|
|
},
|
|
"entry_num": 37
|
|
},
|
|
{
|
|
"rank": 36,
|
|
"brand": "DonMario",
|
|
"product": "Seeds",
|
|
"traits": "DM 53E53",
|
|
"metrics": {
|
|
"Yield": 32.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 339.15
|
|
},
|
|
"entry_num": 38
|
|
},
|
|
{
|
|
"rank": 37,
|
|
"brand": "Revere",
|
|
"product": "Seed",
|
|
"traits": "Revere 48-F72",
|
|
"metrics": {
|
|
"Yield": 32.0,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 336.0
|
|
},
|
|
"entry_num": 39
|
|
},
|
|
{
|
|
"rank": 38,
|
|
"brand": "AgSouth",
|
|
"product": "Genetics",
|
|
"traits": "AGS 738 RR",
|
|
"metrics": {
|
|
"Yield": 31.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 332.85
|
|
},
|
|
"entry_num": 40
|
|
},
|
|
{
|
|
"rank": 39,
|
|
"brand": "Progeny",
|
|
"product": "P",
|
|
"traits": "4848XF",
|
|
"metrics": {
|
|
"Yield": 31.1,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 326.55
|
|
},
|
|
"entry_num": 41
|
|
},
|
|
{
|
|
"rank": 40,
|
|
"brand": "Asgrow",
|
|
"product": "AG55XF5",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 27.5,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 288.75
|
|
},
|
|
"entry_num": 42
|
|
},
|
|
{
|
|
"rank": 41,
|
|
"brand": "Asgrow",
|
|
"product": "AG50XF5",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 27.3,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 286.65
|
|
},
|
|
"entry_num": 43
|
|
},
|
|
{
|
|
"rank": 42,
|
|
"brand": "Progeny",
|
|
"product": "P",
|
|
"traits": "4806XFS",
|
|
"metrics": {
|
|
"Yield": 24.7,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 259.35
|
|
},
|
|
"entry_num": 44
|
|
},
|
|
{
|
|
"rank": 43,
|
|
"brand": "Asgrow",
|
|
"product": "AG52XF5",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 23.6,
|
|
"%MST": null,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 247.8
|
|
},
|
|
"entry_num": 45
|
|
}
|
|
],
|
|
"n_results": 43,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/soybean/plot-report/ga/2024/2465706"
|
|
],
|
|
"fetched_at": "2026-05-25T19:43:00.590586+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|