justin/seed-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

gh_plot_reports corpus (4,299 plots) + concurrency + 4-GPU pool

Browse Source 
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>
This commit is contained in:
Justin Paul
2026-05-25 16:46:35 -04:00
parent cfa27d0bca
commit 0e625553e5
8602 changed files with 1013877 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
corpus/gh_plot_reports/ghpr-silage-wi-2024-2414863.md
+35
View File
@@ -0,0 +1,35 @@
# Silage yield trial — Wisconsin, 2024
- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
- **Crop:** Silage
- **State:** Wisconsin (WI)
- **Year:** 2024
- **Plot ID:** 2414863
- **Cooperator:** Syngenta Seeds, Inc
- **Planted:** 2024-05-12
- **Harvested:** 2024-09-05
- **Population:** 30,000 seeds/acre
- **Row width:** 30"
- **URL:** https://www.goldenharvestseeds.com/silage/plot-report/wi/2024/2414863
---
## Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | Golden Harvest | G13U96-DV | - | 35.9 | 3729.0 | 40146.0 | 274.0 | 2523.0 |
| 2 | Enogen | E105Z5-D | - | 35.4 | 3488.0 | 37018.0 | 269.0 | 2468.0 |
| 3 | Pioneer | P1185Q | - | 35.1 | 3708.0 | 39045.0 | 271.0 | 2456.0 |
| 4 | Enogen | E095D3-D | - | 34.6 | 3352.0 | 34826.0 | 253.0 | 2358.0 |
| 5 | Golden Harvest | G14B32-DV | - | 33.3 | 3505.0 | 35027.0 | 249.0 | 2251.0 |
| 6 | Pioneer | P0622Q | - | 32.9 | 3762.0 | 37186.0 | 278.0 | 2332.0 |
| 7 | Enogen | E111V7-D | - | 32.7 | 3652.0 | 35781.0 | 278.0 | 2312.0 |
| 7 | Enogen | E112S5-D | - | 32.7 | 3374.0 | 33066.0 | 239.0 | 2174.0 |
| 9 | Enogen | E107C1-D | - | 31.7 | 3090.0 | 29369.0 | 211.0 | 2014.0 |
| 10 | Enogen | E094Z4-D | - | 31.6 | 3350.0 | 31775.0 | 245.0 | 2123.0 |
| 11 | Enogen | E114C4-DV-LL | - | 30.7 | 3347.0 | 30864.0 | 239.0 | 2045.0 |
| 12 | Enogen | E110F4-D | - | 30.5 | 3581.0 | 32798.0 | 266.0 | 2121.0 |
| 13 | Golden Harvest | G03U08-D | - | 29.9 | 3429.0 | 30794.0 | 231.0 | 1965.0 |
| 14 | Enogen | E100A3-D | - | 29.8 | 3490.0 | 31199.0 | 269.0 | 2078.0 |
Top 5 by Ton/Acre: G13U96-DV (Golden Harvest) 35.9, E105Z5-D (Enogen) 35.4, P1185Q (Pioneer) 35.1, E095D3-D (Enogen) 34.6, G14B32-DV (Golden Harvest) 33.3.