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>
260 lines
5.2 KiB
JSON
260 lines
5.2 KiB
JSON
{
|
|
"source": "gh_plot_reports",
|
|
"source_key": "ghpr-soybeans-on-2025-2466814",
|
|
"data_type": "trial",
|
|
"vendor": "Syngenta",
|
|
"brand": "Golden Harvest",
|
|
"crop": "soybeans",
|
|
"state": "ON",
|
|
"state_abbrev": "on",
|
|
"year": 2025,
|
|
"plot_id": "2466814",
|
|
"cooperator": "Michael Maynard",
|
|
"planted_date": "2025-06-02",
|
|
"harvested_date": "2025-10-08",
|
|
"population_seeds_per_acre": 155000,
|
|
"row_width_in": 24,
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"brand": "Pioneer",
|
|
"product": "P23Z58E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 73.1,
|
|
"%MST": 14.3,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 767.55
|
|
},
|
|
"entry_num": 1
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "Pioneer",
|
|
"product": "P28Z89E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 72.8,
|
|
"%MST": 13.5,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 764.4
|
|
},
|
|
"entry_num": 3
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"brand": "Pride",
|
|
"product": "Seeds",
|
|
"traits": "PS 2325 EN",
|
|
"metrics": {
|
|
"Yield": 72.8,
|
|
"%MST": 14.5,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 764.4
|
|
},
|
|
"entry_num": 20
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"brand": "Brevant",
|
|
"product": "B243EE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 72.1,
|
|
"%MST": 14.3,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 757.05
|
|
},
|
|
"entry_num": 8
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"brand": "Pride",
|
|
"product": "Seeds",
|
|
"traits": "PS 2120 EN",
|
|
"metrics": {
|
|
"Yield": 71.8,
|
|
"%MST": 15.1,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 753.9
|
|
},
|
|
"entry_num": 19
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"brand": "NK",
|
|
"product": "S23-P1E3",
|
|
"traits": "Enlist E3 ®",
|
|
"metrics": {
|
|
"Yield": 71.6,
|
|
"%MST": 14.1,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 751.8
|
|
},
|
|
"entry_num": 4
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"brand": "Pioneer",
|
|
"product": "P21Z88E",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 71.5,
|
|
"%MST": 13.4,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 750.75
|
|
},
|
|
"entry_num": 2
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"brand": "Brevant",
|
|
"product": "B214EE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 71.4,
|
|
"%MST": 13.6,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 749.7
|
|
},
|
|
"entry_num": 7
|
|
},
|
|
{
|
|
"rank": 9,
|
|
"brand": "NK",
|
|
"product": "S22-D6XF",
|
|
"traits": "XtendFlex ®",
|
|
"metrics": {
|
|
"Yield": 71.0,
|
|
"%MST": 14.1,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 745.5
|
|
},
|
|
"entry_num": 6
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Maizex",
|
|
"product": "Ocelot",
|
|
"traits": "E3",
|
|
"metrics": {
|
|
"Yield": 68.3,
|
|
"%MST": 13.8,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 717.15
|
|
},
|
|
"entry_num": 12
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"brand": "Pride",
|
|
"product": "Seeds",
|
|
"traits": "PS 1923 XFN",
|
|
"metrics": {
|
|
"Yield": 68.3,
|
|
"%MST": 14.3,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 717.15
|
|
},
|
|
"entry_num": 21
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"brand": "Maizex",
|
|
"product": "Prosper",
|
|
"traits": "XF",
|
|
"metrics": {
|
|
"Yield": 67.9,
|
|
"%MST": 13.8,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 712.95
|
|
},
|
|
"entry_num": 10
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"brand": "Secan",
|
|
"product": "Lindros",
|
|
"traits": "E3",
|
|
"metrics": {
|
|
"Yield": 67.9,
|
|
"%MST": 14.6,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 712.95
|
|
},
|
|
"entry_num": 16
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"brand": "NK",
|
|
"product": "S26-E3",
|
|
"traits": "Enlist E3 ®",
|
|
"metrics": {
|
|
"Yield": 67.2,
|
|
"%MST": 14.1,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 705.6
|
|
},
|
|
"entry_num": 5
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"brand": "Secan",
|
|
"product": "Hayley",
|
|
"traits": "XF",
|
|
"metrics": {
|
|
"Yield": 66.2,
|
|
"%MST": 14.1,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 695.1
|
|
},
|
|
"entry_num": 17
|
|
},
|
|
{
|
|
"rank": 16,
|
|
"brand": "Maizex",
|
|
"product": "Emerald",
|
|
"traits": "E3",
|
|
"metrics": {
|
|
"Yield": 65.7,
|
|
"%MST": 13.8,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 689.85
|
|
},
|
|
"entry_num": 11
|
|
},
|
|
{
|
|
"rank": 17,
|
|
"brand": "Pride",
|
|
"product": "Seeds",
|
|
"traits": "PS 2923 EN",
|
|
"metrics": {
|
|
"Yield": 65.2,
|
|
"%MST": 14.6,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 684.6
|
|
},
|
|
"entry_num": 18
|
|
},
|
|
{
|
|
"rank": 18,
|
|
"brand": "Brevant",
|
|
"product": "B289EE",
|
|
"traits": "",
|
|
"metrics": {
|
|
"Yield": 59.1,
|
|
"%MST": 14.0,
|
|
"Test Weight": null,
|
|
"Gross Revenue": 620.55
|
|
},
|
|
"entry_num": 9
|
|
}
|
|
],
|
|
"n_results": 18,
|
|
"source_urls": [
|
|
"https://www.goldenharvestseeds.com/soybean/plot-report/on/2025/2466814"
|
|
],
|
|
"fetched_at": "2026-05-25T19:47:14.489699+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|