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-mn-2024-2414892.md
+36
View File
@@ -0,0 +1,36 @@
# Silage yield trial — Minnesota, 2024
- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
- **Crop:** Silage
- **State:** Minnesota (MN)
- **Year:** 2024
- **Plot ID:** 2414892
- **Cooperator:** Zach Euteneuer/ Hobby Hill Farms
- **Planted:** 2024-05-10
- **Harvested:** 2024-09-13
- **Population:** 33,600 seeds/acre
- **Row width:** 22"
- **URL:** https://www.goldenharvestseeds.com/silage/plot-report/mn/2024/2414892
---
## Results (top-down by rank)
| Rank | Brand | Product | Traits | Ton/Acre | Milk Per Acre | Milk Per Ton | Beef Per Acre | Beef Per Ton |
|---|---|---|---|---|---|---|---|---|
| 1 | DEKALB | DKC102-13 | - | 36.4 | 3314.0 | 36222.0 | 249.0 | 2463.0 |
| 2 | Dairyland | Seed | HIDF-4321V | 35.6 | 3406.0 | 36413.0 | 241.0 | 2377.0 |
| 3 | Pioneer | P0720Q | - | 34.8 | 3252.0 | 33971.0 | 232.0 | 2293.0 |
| 4 | Dairyland | Seed | HiDF-4808V | 34.6 | 3281.0 | 34077.0 | 232.0 | 2279.0 |
| 5 | Pioneer | P0953AM | - | 34.1 | 3562.0 | 36477.0 | 252.0 | 2320.0 |
| 6 | Enogen | E114C4-DV-LL | - | 33.5 | 3574.0 | 35956.0 | 264.0 | 2321.0 |
| 7 | Dairyland | Seed | HIDF-4545Q | 33.3 | 3135.0 | 31306.0 | 216.0 | 2136.0 |
| 8 | DEKALB | DKC098-88 | - | 32.9 | 3126.0 | 30898.0 | 225.0 | 2143.0 |
| 9 | Pioneer | P0529Q | - | 32.3 | 3237.0 | 31376.0 | 211.0 | 2057.0 |
| 10 | DEKALB | DKC105-33 | - | 31.8 | 3474.0 | 33134.0 | 247.0 | 2142.0 |
| 10 | Dairyland | Seed | HIDF-4540V | 31.8 | 3127.0 | 29809.0 | 210.0 | 2019.0 |
| 12 | Enogen | E111V7-D | - | 31.5 | 3246.0 | 30722.0 | 224.0 | 2050.0 |
| 13 | Golden Harvest | G07G73-D | - | 28.5 | 2888.0 | 24710.0 | 201.0 | 1786.0 |
| 14 | Pioneer | P1089AMXT | - | 28.1 | 3372.0 | 28461.0 | 230.0 | 1847.0 |
| 15 | Enogen | E110F4-D | - | 27.6 | 3065.0 | 25403.0 | 196.0 | 1716.0 |
Top 5 by Ton/Acre: DKC102-13 (DEKALB) 36.4, Seed (Dairyland) 35.6, P0720Q (Pioneer) 34.8, Seed (Dairyland) 34.6, P0953AM (Pioneer) 34.1.