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-soybeans-sd-2025-2466217.md
+44
View File
@@ -0,0 +1,44 @@
# Soybean yield trial — South Dakota, 2025
- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
- **Crop:** Soybean
- **State:** South Dakota (SD)
- **Year:** 2025
- **Plot ID:** 2466217
- **Cooperator:** Labolt Farmers Grain
- **Planted:** 2025-05-14
- **Harvested:** 2025-10-03
- **Population:** 160,000 seeds/acre
- **Row width:** 30"
- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/sd/2025/2466217
---
## Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Mustang | Seeds | 14E535 | 55.2 | 11.7 | - | $579.60 |
| 2 | Dairyland | Seed | DSR-0678E | 54.7 | 10.1 | - | $574.35 |
| 3 | Dairyland | Seed | DSR-0799E | 54.6 | 10.0 | - | $573.30 |
| 4 | Dairyland | Seed | DSR-0585E | 51.2 | 7.1 | - | $537.60 |
| 4 | Dairyland | Seed | DSR-1505E | 51.2 | 10.5 | - | $537.60 |
| 4 | NK | NK17-H1E3 | Enlist E3 ® | 51.2 | 10.6 | - | $537.60 |
| 7 | NK | NK09-V2E3 | Enlist E3 ® | 50.8 | 10.0 | - | $533.40 |
| 8 | Dairyland | Seed | DSR-1099E | 50.2 | 11.4 | - | $527.10 |
| 9 | NK | NK07-G5E3 | Enlist E3 ® | 49.6 | 10.1 | - | $520.80 |
| 10 | Mustang | Seeds | 14E535 | 48.3 | 10.9 | - | $507.15 |
| 11 | NK | NK16-Z6E3 | Enlist E3 ® | 47.5 | 10.9 | - | $498.75 |
| 12 | Dairyland | Seed | DSR-1476E | 46.3 | 10.5 | - | $486.15 |
| 13 | NK | NK14-U5E3 | Enlist E3 ® | 45.3 | 10.6 | - | $475.65 |
| 14 | NK | NK11-A4E3 | Enlist E3 ® | 44.6 | 10.3 | - | $468.30 |
| 15 | Mustang | Seeds | 10E125 | 44.1 | 10.4 | - | $463.05 |
| 16 | Dairyland | Seed | DSR-1345E | 42.7 | 10.1 | - | $448.35 |
| 17 | Mustang | Seeds | 08E426 | 41.1 | 9.8 | - | $431.55 |
| 18 | Dairyland | Seed | DSR-1150E | 39.5 | 10.2 | - | $414.75 |
| 19 | Mustang | Seeds | 14E535 | 39.4 | 11.0 | - | $413.70 |
| 20 | Mustang | Seeds | 16E725 | 39.0 | 10.7 | - | $409.50 |
| 21 | NK | NK08-Z4E3 | Enlist E3 ® | 36.6 | 10.1 | - | $384.30 |
| 22 | Mustang | Seeds | 13E335 | 35.3 | 10.1 | - | $370.65 |
| 23 | Mustang | Seeds | 05E626 | 30.9 | 10.4 | - | $324.45 |
Top 5 by Yield: Seeds (Mustang) 55.2, Seed (Dairyland) 54.7, Seed (Dairyland) 54.6, Seed (Dairyland) 51.2, Seed (Dairyland) 51.2.