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-al-2024-2465716.md
+43
View File
@@ -0,0 +1,43 @@
# Soybean yield trial — Alabama, 2024
- **Source:** Golden Harvest plot report (cross-vendor head-to-head)
- **Crop:** Soybean
- **State:** Alabama (AL)
- **Year:** 2024
- **Plot ID:** 2465716
- **Cooperator:** Auburn University - Shorter MG IV
- **Planted:** 2024-05-23
- **Harvested:** 2024-11-05
- **URL:** https://www.goldenharvestseeds.com/soybean/plot-report/al/2024/2465716
---
## Results (top-down by rank)
| Rank | Brand | Product | Traits | Yield | %MST | Test Weight | Gross Revenue |
|---|---|---|---|---|---|---|---|
| 1 | Innvictis | Seed | Solutions A4642XF | 29.0 | - | - | $304.50 |
| 2 | Integra | Fortified | Seed XF4634S | 28.0 | - | - | $294.00 |
| 2 | Progeny | P | 4691XFS | 28.0 | - | - | $294.00 |
| 2 | Progeny | P | 4604XFS | 28.0 | - | - | $294.00 |
| 5 | Progeny | P | 4848XF | 27.0 | - | - | $283.50 |
| 5 | NK | NK49-N7XF | XtendFlex ® | 27.0 | - | - | $283.50 |
| 7 | Integra | Fortified | Seed XF4914S | 26.0 | - | - | $273.00 |
| 7 | NK | NK49-C2XFS | XtendFlex ® STS ® | 26.0 | - | - | $273.00 |
| 7 | Innvictis | Seed | Solutions A4503XF | 26.0 | - | - | $273.00 |
| 7 | UniSouth | Genetics | USG 7495XFS | 26.0 | - | - | $273.00 |
| 7 | Asgrow | AG47XF5 | - | 26.0 | - | - | $273.00 |
| 12 | Integra | Fortified | Seed XF4875S | 25.0 | - | - | $262.50 |
| 12 | Innvictis | Seed | Solutions A4862XF | 25.0 | - | - | $262.50 |
| 12 | UniSouth | Genetics | USG 7474XFS | 25.0 | - | - | $262.50 |
| 12 | Armor | Seed | Armor 49-F37 | 25.0 | - | - | $262.50 |
| 16 | Progeny | P | 4623XF | 24.0 | - | - | $252.00 |
| 16 | Progeny | P | 4806XFS | 24.0 | - | - | $252.00 |
| 16 | NK | NK48-A8XFS | XtendFlex ® STS ® | 24.0 | - | - | $252.00 |
| 19 | Pioneer | P49Z02E | - | 23.0 | - | - | $241.50 |
| 19 | UniSouth | Genetics | USG 7461XFS | 23.0 | - | - | $241.50 |
| 19 | Pioneer | P48A14E | - | 23.0 | - | - | $241.50 |
| 22 | Innvictis | Seed | Solutions A4814XF | 22.0 | - | - | $231.00 |
| 23 | Progeny | P | 4947XFS | 20.0 | - | - | $210.00 |
| 24 | Progeny | P | 4798XF | 19.0 | - | - | $199.50 |
Top 5 by Yield: Seed (Innvictis) 29.0, Fortified (Integra) 28.0, P (Progeny) 28.0, P (Progeny) 28.0, P (Progeny) 27.0.