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-va-2024-2419138.md
+30
View File
@@ -0,0 +1,30 @@
# Silage yield trial — Virginia, 2024
- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
- **Crop:** Silage
- **State:** Virginia (VA)
- **Year:** 2024
- **Plot ID:** 2419138
- **Cooperator:** Kegley Farms
- **Planted:** 2024-06-07
- **Harvested:** 2024-10-02
- **Population:** 29,000 seeds/acre
- **Row width:** 30"
- **URL:** https://www.goldenharvestseeds.com/silage/plot-report/va/2024/2419138
---
## Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | NK | NK1677-3110 | - | 33.5 | 3544.0 | 35639.0 | 228.0 | 2190.0 |
| 2 | Enogen | E113Z5-D | - | 32.5 | 3264.0 | 31828.0 | 213.0 | 2076.0 |
| 3 | NK | NK1402-DV | - | 31.3 | 3140.0 | 29464.0 | 219.0 | 2016.0 |
| 4 | Enogen | E117Z7-D | - | 30.5 | 3351.0 | 30625.0 | 207.0 | 1925.0 |
| 5 | Enogen | E112S5-D | - | 30.3 | 3498.0 | 31831.0 | 241.0 | 2026.0 |
| 6 | Enogen | E114C4-DV-LL | - | 30.2 | 3270.0 | 29585.0 | 194.0 | 1867.0 |
| 7 | NK | NK1838-3110 | - | 29.4 | 3370.0 | 29741.0 | 202.0 | 1845.0 |
| 8 | NK | NK1480-DV | - | 29.2 | 3159.0 | 27706.0 | 186.0 | 1787.0 |
| 9 | NK | NK1701-V | - | 26.8 | 3342.0 | 26898.0 | 204.0 | 1688.0 |
Top 5 by Ton/Acre: NK1677-3110 (NK) 33.5, E113Z5-D (Enogen) 32.5, NK1402-DV (NK) 31.3, E117Z7-D (Enogen) 30.5, E112S5-D (Enogen) 30.3.