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-nd-2024-2438063.md
+44
View File
@@ -0,0 +1,44 @@
# Soybean yield trial — North Dakota, 2024
- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
- **Crop:** Soybean
- **State:** North Dakota (ND)
- **Year:** 2024
- **Plot ID:** 2438063
- **Cooperator:** NDSU - Langdon Research Extension Center (Nelson Cnty)
- **Planted:** 2024-06-06
- **Harvested:** 2024-10-09
- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/nd/2024/2438063
---
## Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Proseed | XF | 50-52N | 66.7 | - | - | $700.35 |
| 2 | Legacy | Seeds | LS044-23 XF | 63.2 | - | - | $663.60 |
| 3 | Golden Harvest | GH0384XF | XtendFlex ® | 62.5 | - | - | $656.25 |
| 4 | Proseed | XF | 30-42 | 62.1 | - | - | $652.05 |
| 5 | Legacy | Seeds | LS034-24 XF | 61.6 | - | - | $646.80 |
| 6 | Xitavo | XO | 0234E | 60.7 | - | - | $637.35 |
| 7 | Legacy | Seeds | LS032-23 E | 59.9 | - | - | $628.95 |
| 8 | Golden Harvest | GH0225XF | XtendFlex ® | 58.6 | - | - | $615.30 |
| 9 | Channel | 0325RXF | - | 58.4 | - | - | $613.20 |
| 10 | Legacy | Seeds | LS022-24 E | 57.3 | - | - | $601.65 |
| 11 | Proseed | EL | 50-33N | 56.6 | - | - | $594.30 |
| 12 | Channel | 0225RXF | - | 55.3 | - | - | $580.65 |
| 13 | Proseed | XF | 40-12 | 53.2 | - | - | $558.60 |
| 14 | Integra | Fortified | Seed XF0115 | 51.7 | - | - | $542.85 |
| 15 | Xitavo | XO | 0094E | 51.0 | - | - | $535.50 |
| 16 | Fortus | 0324E | - | 50.7 | - | - | $532.35 |
| 17 | Fortus | 0544E | - | 49.4 | - | - | $518.70 |
| 18 | Fortus | 0084E | - | 48.4 | - | - | $508.20 |
| 19 | Legacy | Seeds | LS014-23 XF | 48.1 | - | - | $505.05 |
| 20 | Legacy | Seeds | LS024-23 XF | 47.3 | - | - | $496.65 |
| 21 | NDSU | ND17009GT | - | 47.0 | - | - | $493.50 |
| 22 | Fortus | 0165E | - | 46.5 | - | - | $488.25 |
| 23 | Integra | Fortified | Seed XF0493 | 46.1 | - | - | $484.05 |
| 24 | Integra | Fortified | Seed XF0212 | 45.5 | - | - | $477.75 |
| 25 | NDSU | ND21008GT20 | - | 44.8 | - | - | $470.40 |
Top 5 by Yield: XF (Proseed) 66.7, Seeds (Legacy) 63.2, GH0384XF (Golden Harvest) 62.5, XF (Proseed) 62.1, Seeds (Legacy) 61.6.