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>
3.3 KiB
3.3 KiB
Soybean yield trial — Georgia, 2024
- Source: Golden Harvest plot report (cross-vendor head-to-head)
- Crop: Soybean
- State: Georgia (GA)
- Year: 2024
- Plot ID: 2465706
- Cooperator: University of Georgia - Griffin (Ultra Late)
- Planted: 2024-07-18
- Harvested: 2024-12-02
- Population: 250,000 seeds/acre
- URL: https://www.goldenharvestseeds.com/soybean/plot-report/ga/2024/2465706
Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Innvictis | Seed | Solutions A5994XF | 49.8 | - | - | $522.90 |
| 2 | Progeny | P | 6685XFS | 47.3 | - | - | $496.65 |
| 3 | DonMario | Seeds | DM69E83S | 46.5 | - | - | $488.25 |
| 4 | Pioneer | P68A41BE | - | 45.6 | - | - | $478.80 |
| 5 | UniSouth | Genetics | USG 7633XF | 45.3 | - | - | $475.65 |
| 6 | Integra | Fortified | Seed XF4875S | 44.4 | - | - | $466.20 |
| 7 | DonMario | Seeds | DM55F62S | 43.6 | - | - | $457.80 |
| 8 | Georgia | Seed | G21-230R2X | 43.5 | - | - | $456.75 |
| 8 | Progeny | P | 4947XFS | 43.5 | - | - | $456.75 |
| 10 | Revere | Seed | Revere 4826XFS | 43.3 | - | - | $454.65 |
| 11 | Innvictis | Seed | Solutions A5813XF | 42.9 | - | - | $450.45 |
| 12 | Armor | Seed | Armor 71-F12 | 42.5 | - | - | $446.25 |
| 13 | Innvictis | Seed | Solutions A4924XF | 42.2 | - | - | $443.10 |
| 13 | Integra | Fortified | Seed XF4914S | 42.2 | - | - | $443.10 |
| 15 | DonMario | Seeds | DM59E01S | 41.4 | - | - | $434.70 |
| 16 | UniSouth | Genetics | USG 7495XFS | 41.2 | - | - | $432.60 |
| 16 | Pioneer | P56A71E | - | 41.2 | - | - | $432.60 |
| 18 | Revere | Seed | Revere 53-F84 XFS | 40.7 | - | - | $427.35 |
| 19 | Integra | Fortified | Seed 6984XF | 39.3 | - | - | $412.65 |
| 20 | Armor | Seed | Armor 49-F37 | 39.0 | - | - | $409.50 |
| 21 | Revere | Seed | Revere 49-F36 XF | 38.9 | - | - | $408.45 |
| 22 | Armor | Seed | Armor 59-F21 | 38.8 | - | - | $407.40 |
| 23 | Clemson | U | SC17-5517 | 38.6 | - | - | $405.30 |
| 24 | Asgrow | AG69XF5 | - | 37.9 | - | - | $397.95 |
| 24 | Georgia | Seed | G21-245R2X | 37.9 | - | - | $397.95 |
| 26 | Revere | Seed | Revere 6927XF | 37.6 | - | - | $394.80 |
| 27 | NK | NK63-U7XF | XtendFlex ® | 36.5 | - | - | $383.25 |
| 28 | NK | NK58-B8E3S | Enlist E3 ® STS ® | 36.1 | - | - | $379.05 |
| 29 | Armor | Seed | Armor 68-F35 | 35.8 | - | - | $375.90 |
| 30 | Innvictis | Seed | Solutions A5284XF | 35.7 | - | - | $374.85 |
| 31 | Revere | Seed | Revere 62-F24 XF | 35.1 | - | - | $368.55 |
| 32 | DonMario | Seeds | DM48E54 | 34.4 | - | - | $361.20 |
| 33 | Asgrow | AG54XF5 | - | 33.3 | - | - | $349.65 |
| 34 | Asgrow | AG48XF5 | - | 32.5 | - | - | $341.25 |
| 35 | Progeny | P | 5056XFS | 32.4 | - | - | $340.20 |
| 36 | DonMario | Seeds | DM 53E53 | 32.3 | - | - | $339.15 |
| 37 | Revere | Seed | Revere 48-F72 | 32.0 | - | - | $336.00 |
| 38 | AgSouth | Genetics | AGS 738 RR | 31.7 | - | - | $332.85 |
| 39 | Progeny | P | 4848XF | 31.1 | - | - | $326.55 |
| 40 | Asgrow | AG55XF5 | - | 27.5 | - | - | $288.75 |
| 41 | Asgrow | AG50XF5 | - | 27.3 | - | - | $286.65 |
| 42 | Progeny | P | 4806XFS | 24.7 | - | - | $259.35 |
| 43 | Asgrow | AG52XF5 | - | 23.6 | - | - | $247.80 |
Top 5 by Yield: Seed (Innvictis) 49.8, P (Progeny) 47.3, Seeds (DonMario) 46.5, P68A41BE (Pioneer) 45.6, Genetics (UniSouth) 45.3.