docker: production image + Gitea Actions for monthly refresh

Dockerfile: self-contained image with corpus + Chroma + BM25 baked
in. Drawbar's compose pulls + runs without volume mounts. Built from
sources.json (labels schema), PRODUCT_NAME=crop_chem by default,
HYBRID_SEARCH=true (always-on for production quality). RERANK_URL +
OLLAMA_URL get set at compose time.

.gitea/workflows/refresh.yml: monthly cron (1st @ 06:00 UTC) does
full scrape → reindex → image push. Scrapes Bayer (~30 min) +
EPA PPLS row-crop filtered (~7h). Skips reindex+push if no corpus
diff. Tags pushed: :latest, :<sha12>, :corpus-<YYYY.MM.DD>.

.gitea/workflows/image-only.yml: on-demand or auto on code-only
pushes to main (paths: docs_mcp/, rag/, scrape/, requirements.txt,
Dockerfile, sources.json). Reindexes from committed corpus, builds
image, pushes. ~10 min vs ~9h full refresh.

.gitignore: corpus/ now COMMITTED (4,159 labels, 265 MB of .md +
sidecars). Lets image-only.yml rebuild indexes without re-scraping.
chroma/ + bm25/ still gitignored (regenerable binary indexes).

.dockerignore: drops venv, eval results, PLAN/README/CLAUDE.md,
deploy/, .git/ — keeps the image lean. corpus + chroma + bm25
explicitly NOT in dockerignore (those go INTO the image).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

corpus/epa_ppls/352-476.md

@@ -0,0 +1,43 @@
+# SHELL NUDRIN *90 METHOMYL INSECTICIDE (WATER SOLUBLE POWDER)
+
+- EPA Reg No: **352-476**
+- Registrant: CORTEVA AGRISCIENCE, LLC
+- Signal word: Danger
+- Active ingredients: Methomyl (90%)
+- Label accepted: 1986-03-04
+- Source PDF: https://www3.epa.gov/pesticides/chem_search/ppls/000201-00324-19860304.pdf
+
+---
+( 
+( 
+Shell 
+Nudrin®90 
+Methomyllnsecticide 
+WATER SOLUBLE POWDER 
+SUPPLHlENTAL LABEll NG 
+EPA REG. NO. 201-324 
+DIRECTIONS FOR USE 
+/ 
+Shell 
+It is a violation of federal law to use this product in a manner inconsistent 
+with its labeling. 
+LAST APPLICATIOI( - DAYS 
+CROPS pourms TO TO LIVESTOCK 
+I1ETHOD OF APPLICATIOI( WSECTS PER ACRE HARVEST GRAZWG/L1VESTOCK 
+Straltberries Beet Armyt/Ol1T1. Thrips 1/2-1 3 Fresh 
+Aphids 10 Processing 
+lygus Bugs. Omnivorous 1 
+leaf Tiers 
+1I1PORTANT 
+Before using NODRIN 90 Methomyl Insecticide \·/ater Soluble Powder, read and 
+carefully observe the cautionary statements and a 11 other i nformati on 
+appearing on the product label. 
+This bulletin contains new or supplemental instructions for use of this 
+product which may not appear on package label and must be in possession of 
+the user at the time of application. Follow the instructions cilrefully • 
+Shell Chemical Company 
+A Division of Shell Oil Company 
+P. O. Box 3B71 
+Houston, TX 77001 
+CAC8529BOl 
+. ......