main
9 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 claude
|
a54fac240f |
Add university-extension trials: Illinois VT + Iowa ICPT + Ohio OCPT (+123 cross-vendor trial docs) (#19)
Image rebuild (skip scrape) / build (push) Successful in 5m54s
Co-authored-by: claude <claude@jpaul.io> Co-committed-by: claude <claude@jpaul.io> |
||
|
claude
|
22e8092faf |
Add ProHarvest Seeds: 119 varieties + 161 cross-vendor plot reports (#16)
Image rebuild (skip scrape) / build (push) Successful in 5m46s
Co-authored-by: claude <claude@jpaul.io> Co-committed-by: claude <claude@jpaul.io> |
||
 justin
|
b98965a68a |
Two new trial sources: LG Seeds + AgriGold plot reports (+2,307 cross-vendor yield trials)
Adds the **first non-Syngenta trial coverage** to the corpus:
| Source | Docs | Publisher | URL pattern |
|---|---|---|---|
| lg_plot_reports | 1,304 | LG Seeds (AgReliant) | lgseeds.com/performance/{crop} JSON XHR |
| agrigold_plot_reports | 1,003 | AgriGold (AgReliant) | agrigold.com/{crop}/performance/{crop}-yield-results |
Total trial coverage now: gh_plot_reports (4,299) + agripro_trials (14) +
lg_plot_reports (1,304) + agrigold_plot_reports (1,003) = 6,620 trial docs.
**Both scrapers follow the gh_plot_reports template** — same RateLimitedSession
primitive, same TrialResult/PlotReport dataclass shape, same data_type="trial"
sidecar convention. The trial chunker (`rag/chunk.py:_render_trial_chunk`) is
extended to recognize both new sources; they share `_render_gh_plot_chunk`
since their sidecars are structurally identical (just different brand label).
**LG specifics:**
- POST `/performance/{crop}/GetPlots/` returns sparse listing (id, year, lat/lng)
- GET `/performance/{crop}/GetPlotData/?PlotId=X&IsSilage=Y` returns full detail
with state, cooperator, planting/harvest dates, and **top-5 hybrids** (LG +
competitors). Top-5 is what LG publishes publicly; not the full ranking.
- 4 crops: corn (963), soybeans (287), sorghum (10), silage (50) — first
alfalfa absent because LG doesn't run alfalfa plots; that's variety-only data.
- 301 gotcha: www.lgseeds.com redirects to lgseeds.com which drops POST body,
so the scraper hits the apex host directly.
**AgriGold specifics:**
- Listing: GET `/{crop}/performance/{crop}-yield-results?harvestYear={year}`
(server-rendered HTML, ~1MB; 408 corn plots in 2025 alone)
- Detail: GET `/{crop_url}/performance/{slug}/{plot_id}` returns the **full
ranking** (not just top-5) plus rich plot management metadata: tillage,
previous crop, fungicide, herbicide, insecticide, irrigation, soil type,
row width, population. Most metadata-rich of the three trial sources.
- Soybean URL slug is singular: `/soybeans/performance/soybean-yield-results/`
- Columns: Rank | Brand | Product | Trait | Ck | H20 (moisture) | Test Wt. |
Yield | Adj Yield (check-adjusted)
- 2 crops: corn (849) + soybeans (157)
**Indexer needs no changes** — `rag/index.py` auto-discovers any directory
under corpus/ and routes by data_type. Both new sources flow into the
existing trial collection and surface via `search_trials`.
Years scraped: 2024+2025 (matching gh_plot_reports baseline). 2023 is
available via `--include-2023` on either scraper for future backfill.
|
||
|
justin
|
eaa7e0789b |
bayer_seeds: add Channel + DEKALB silage/sorghum/canola + Deltapine cotton
User flagged that Channel is expanding into their area — re-walked the cropscience.bayer.us sitemap and found 8 additional brand×crop paths beyond the original DEKALB/Asgrow/WestBred triple. Patches the scraper to walk all of them; total Bayer varieties roughly doubles from 475 to 931 and the corpus picks up first-ever coverage in sorghum (36), cotton (30), canola (6), and silage as a distinct crop (was conflated with corn before). Net new varieties: 456 Channel corn=181 soy=67 silage=54 sorghum=18 (320) DEKALB silage=82 sorghum=18 canola=6 (106) Deltapine cotton=30 (30) scrape/sources/bayer_seeds.py - Replace `BRANDS` (brand → 1 path) and `CROP_SUFFIX` (brand → 1 suffix) with a flatter `BRAND_PATHS` list of (brand, url_path, crop, is_primary_for_brand) entries. Channel and DEKALB are now multi-crop brands; the same scraper walks every brand×crop pair. - source_key derivation: for a brand's PRIMARY crop, strip the trailing `-<crop>` suffix (matches the existing deployed source keys for DEKALB corn / Asgrow soy / WestBred wheat). For SECONDARY crops, KEEP the suffix so DEKALB-the-same-SKU sold as both grain corn and silage gets two distinct source_keys (collision-safe and unambiguous for `lookup_variety`). - New `--crop` CLI filter for incremental backfills. - Log line shows brand + crop alongside source_key for visibility. rag/chunk.py - Channel + Deltapine pages use slightly different characteristics group labels (DISEASE not DISEASE RATINGS, AGRONOMIC CHARACTERISTICS not GROWTH/HARVEST, plus MATURITY / ADAPTATION / HERBICIDES / OTHER). Fold them into the DISEASE / AGRONOMIC / MANAGEMENT label sets so the chunker buckets them correctly into the standard sections. Smoke-tested cross-brand × cross-crop queries against the rebuilt index (5,529 chunks total) — all 6 sample queries surface the right brand+crop at top-3: Channel corn 110 RM → 210-25TRE BRAND Channel soy 2.5 MG IA → 2622RXF BRAND Deltapine cotton XF → DP 1820 B3XF BRAND Sorghum dryland Kansas → 6B95 BRAND (Channel) Silage corn WI dairy → DKC64-44RIB BRAND BLEND (silage variant) Canola Northern Plains → DK401TL BRAND Watchtower will pull the new image on the next push; deploy is unchanged otherwise. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
justin
|
0e625553e5 |
gh_plot_reports corpus (4,299 plots) + concurrency + 4-GPU pool
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>
|
||
|
justin
|
c737871c4c |
Trial-data scrapers: gh_plot_reports + agripro_trials + search_trials tool
This PR introduces TRIAL data — yield-performance results from real
field trials — as a SEPARATE data type alongside variety identity.
The two are complementary:
search_docs → "What's the disease resistance of DKC62-08RIB?"
(variety identity — what it IS)
search_trials → "Which corn hybrid won the IA 2024 trials?"
(performance data — how it PERFORMED)
scrape/sources/gh_plot_reports.py — Golden Harvest plot reports
- 4,618 expected (2024+2025; 2023 deferred to a backfill pass).
- URL: /<crop>/plot-report/<state>/<year>/<plot_id>
- Cross-vendor: each plot lists products from multiple brands
(NK / DEKALB / Golden Harvest / Enogen / Pioneer / Channel) side
by side at one cooperator's field — the kind of independent
comparison data Bayer doesn't publish itself.
- Generic per-column metrics dict (Yield/MST/Test Weight/$/Ac for
corn+soy, Ton/Acre + Milk + Beef columns for silage).
- Politeness: 1 req/sec, retries on 429/5xx, no redirect-follow.
scrape/sources/agripro_trials.py — AgriPro regional trial PDFs
- 14 unique PDFs (38 sitemap links deduped) at /trials-data
- pdfplumber text extraction, region/year detection from filename
- Verbatim PDF text preserved in chunk body so variety + yield
number adjacency drives retrieval (AP Iliad's Aberdeen ID yield
matches a query about "AP Iliad Idaho yield")
rag/chunk.py — chunks_from_trial() dispatching by source
- Plot reports: identity preamble + Top-5 by primary metric + full
ranking table. Metric labels chosen from the data (corn/soy use
"Yield", silage uses "Ton/Acre").
- AgriPro PDFs: identity preamble + verbatim trial body inline so
per-location yields surface for region+variety queries.
- Variety chunks get data_type="variety" metadata; trial chunks get
data_type="trial". Single Chroma collection; the tool router
filters by data_type rather than maintaining two collections.
rag/index.py — dispatch by sidecar's data_type field
rag/bm25.py — new filter columns (data_type, year, state)
docs_mcp/server.py — sixth MCP tool: search_trials(crop?, state?,
year?, product?, k=10)
- Filters trial chunks via where={"data_type": "trial", ...}
- Optional product substring post-filter for "DKC62-08RIB Iowa 2024"
style searches
- search_docs now defaults to data_type="variety" so trial chunks
don't bleed into variety identity queries
- Tool docstring routes the agent: "use lookup_variety to verify
identity details on any trial winner you surface"
NK trial endpoint (/NKSeeds/wsProxy.asmx/GetPlotResult) is documented
as deferred — the ASMX-SOAP shape returned empty XML on initial
probe. Bayer per-variety yield data is not publicly indexed at all
— documented in the trial-scope note (DEKALB/Asgrow trial data flows
through Channel reps, not the web). AgRevival research books exist
as 10 large annual PDFs but are deferred (low ROI per parse).
Initial corpus shipped in this PR: 14 AgriPro trial PDFs. The 4,618
Golden Harvest plot reports are scraping in background and will be
added in a follow-up corpus-snapshot PR (~70 min ETA).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
justin
|
75f714b454 |
Phase 4-5: deployable container + corpus snapshot + CI fixes
deploy/docker-compose.yml — replace <product>/<registry> placeholders with concrete values for Drawbar's stack: - image: git.jpaul.io/justin/seed-mcp:latest (CF tunnel for pulls; CI pushes via LAN 192.168.0.2:1234 to avoid 100 MB body cap) - container_name: seed-mcp - port 8001:8000 (8001 host-side to not collide with crop-chem-docs on 8000) - PRODUCT_NAME=crop_seed, hybrid search enabled, stateless HTTP - llama-rerank shared with crop-chem-docs (NOT redefined here — expected to already be in Drawbar's parent compose network) - networks.drawbar-mcp external: true so seed-mcp joins the existing cross-MCP shared network .gitignore — corpus/ is now COMMITTED, not ignored. The monthly refresh workflow scrapes and commits corpus changes; the image-only workflow rebuilds indexes from the committed corpus. Allowing the corpus to flow through git means the :corpus-YYYY.MM.DD image tag pins to a specific seed-catalog snapshot. chroma/ and bm25/ remain ignored — those are deterministically derived from corpus. Initial committed snapshot: 614 varieties. - bayer_seeds: 475 (DEKALB 288 + Asgrow 102 + WestBred 85) - golden_harvest: 139 (Syngenta corn + soy; 36 sitemap URLs 302-redirected = discontinued) rag/chunk.py — normalize brand and crop to uppercase/lowercase in Chroma metadata so cross-vendor brand-filter lookups don't break on casing inconsistency (Bayer stores "DEKALB", Golden Harvest stores "Golden Harvest"; _build_where uppercases user-supplied brand which matched the former but not the latter pre-fix). Sidecar JSON keeps original casing for display. Stub scrapers (nk, agripro, becks_pfr, becks_products) — change return code from 2 to 0 so the monthly-refresh CI workflow doesn't fail on deferred sources. Real implementations will return 0 on success / 1 on failure when they ship. Smoke-tested cross-vendor retrieval against the 614-chunk index: - list_versions shows both vendors with correct facet counts - broad "corn hybrid 100 RM" query returns both DEKALB and Golden Harvest hits in top 5 - brand='Golden Harvest' filter returns 3 GH-only varieties - variety-code prefilter still works (E085Z5 → top hit on GH) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
justin
|
a766756a05 |
Phase 2/3: chunker + indexer + MCP server tools
Phase 2 — Chunking and indexing
- rag/chunk.py: replace template chunker with seed-variety-specific
chunks_from_variety(). One chunk per variety (varieties are small
and named-rating retrieval signal is best kept together). Output
is rebuilt deterministically from the sidecar JSON: every value is
verbatim from the source, only framing language ("Disease ratings
(1-9, 9=best):") is template glue. Anti-hallucination contract:
same sidecar in → same chunk out, never a fabricated rating.
Metadata flattened to Chroma-safe primitives (str/int/float/bool):
source, source_key, vendor, brand, crop, product_name,
product_id, source_url, rm (corn), mg (soy), wheat_class,
release_year, trait_codes_csv, rating_scale.
- rag/index.py: walks corpus/<source>/<source_key>.json sidecars
via the new chunker. Default PRODUCT_NAME=crop_seed so the
Chroma collection is crop_seed_docs.
- rag/bm25.py: filterable columns updated to seed-domain facets
(source/vendor/brand/crop/source_key) instead of the template's
version/platform/product.
Phase 3 — MCP server tools wired up
- search_docs: hybrid dense (Chroma) + BM25 (FTS5) retrieval with
RRF fusion. Optional filters: crop, brand, vendor, source.
Variety-code prefilter pins exact source_key / product_name /
hybrid_prefix matches at the top — dense embeddings have no
semantic neighbor for tokens like "DKC62-08RIB" and RRF can let
noise float to #1 without this pin. Each response carries the
variety's source URL inline so the agent can cite.
- get_page(source, source_key): emits a structured ratings header
(verbatim from sidecar, table per characteristics group, vendor
positioning, regional listings) followed by the raw indexed body.
This is the canonical fact-check surface.
- list_versions(): facet discovery — distinct sources, vendors,
brands, crops across the corpus.
- lookup_variety(source_key, source?): returns the raw sidecar JSON
for one variety. The agent should call this BEFORE quoting any
specific rating value to a farmer — guaranteed verbatim.
Smoke tests against 475 indexed Bayer varieties:
- list_versions returns 475 varieties, 1 source, 1 vendor, 3 brands,
3 crops with correct per-brand counts (288/102/85).
- Semantic ag queries find the right candidates: short-season
drought-tolerant corn → DKC44-97RIB at RM 94 (in 90-95 band);
SCN+MG3 soybean → Asgrow XF varieties with explicit SCN R3 ratings;
Phytophthora Rps3a soy → AG07XF4 (right gene); stripe-rust
wheat → WestBred WB1376CLP (Yellow Rust 2 = best).
- Variety-code lookups work via prefilter: DKC62-08RIB, AG29XF4,
WB6430 all return as #1 hit. BM25 confirms ranking unambiguously
(top-1 score -13.2 vs -8.5 for #2 on "DKC62-08RIB ratings").
- Server boots cleanly in stdio AND streamable-http modes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
justin
|
ac40e05734 |
seed-mcp scaffold: clone docs-mcp-template, customize for crop_seed PRODUCT_NAME
Image rebuild (skip scrape) / build (push) Failing after 7s
Sibling project to crop-chem-docs, same MCP-template lineage. Corpus is
seed/hybrid varieties across 6 vendors instead of pesticide labels.
What's customized vs. the template:
- CLAUDE.md: vendor matrix, build priority, Pioneer fallback policy,
canonical sidecar schema (per-crop), Golden Harvest disease-scale
reversal gotcha, no-IPv6 / HTTPS-clone note
- README.md: vendor coverage table, tool list, phase status
- Dockerfile: PRODUCT_NAME=crop_seed default, sources.json (not
bundles.json), HYBRID_SEARCH=true, OLLAMA_URL + RERANK_URL Docker
DNS defaults (same llama-rerank sidecar as crop-chem-docs)
- .gitea/workflows/refresh.yml: monthly cron (seed catalogs move
slowly), 5 GREEN scraper steps, corpus-YYYY.MM.DD tag for Drawbar
pinning, continue-on-error on GC step
- .gitea/workflows/image-only.yml: paths filter + cancel-in-progress
concurrency group
- scripts/registry_gc.py: lifted from crop-chem-docs (correct Gitea
packages API URL + UA header to bypass CF block on default
Python-urllib UA)
- sources.json: catalog of 6 sources + scope_filter + per-source
schema notes + Pioneer-exclusion rationale
- scrape/runner.py: dispatcher with --all = GREEN-only
- scrape/sources/{bayer_seeds,golden_harvest,nk,agripro,becks_pfr,
becks_products}.py: stub modules with implementation notes
- docs_mcp/server.py: PRODUCT_NAME default → crop_seed,
PRODUCT_DOCS_URL → repo URL
Pioneer is intentionally NOT a source. ToS bans automation; dealer
locator is login-gated. The MCP returns a curated fallback lesson
directing the user to pioneer.com.
Next phases:
- Phase 1: implement bayer_seeds (lift-and-shift from crop-chem-docs
Bayer scraper; same __NEXT_DATA__ infra)
- Phase 7: curate eval/queries.jsonl
- Phase 11: lessons.md with Pioneer fallback + disease-scale notes
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|